This document presents two approaches for improving robustness in medical image segmentation using generative adversarial networks (GANs). The first approach, UltraGAN, uses a GAN to enhance the quality of ultrasound images and improve robustness to low image quality. The second approach, MedRobGAN, generates adversarial medical image examples to improve robustness against adversarial attacks. Both methods are evaluated on medical segmentation tasks to validate their effectiveness in improving robustness.
3D Segmentation of Brain Tumor ImagingIJAEMSJORNAL
A brain tumor is a collection of anomalous cells that grow in or around the brain. Brain tumors affect the humans badly, it can disrupt proper brain function and be life-threatening. In this project, we have proposed a system to detect, segment, and classify the tumors present in the brain. Once the brain tumor is identified at the very beginning, proper treatments can be done and it may be cured.
Adversarial attack driven data augmentation for medical imagesIJECEIAES
An important stage in medical image analysis is segmentation, which aids in focusing on the required area of an image and speeds up findings. Fortunately, deep learning models have taken over with their high-performing capabilities, making this process simpler. The deep learning model’s reliance on vast data, however, makes it difficult to utilize for medical image analysis due to the scarcity of data samples. Too far, a number of data augmentations techniques have been employed to address the issue of data unavailability. Here, we present a novel method of augmentation that enabled the UNet model to segment the input dataset with about 90% accuracy in just 30 epochs. We describe the us- age of fast gradient sign method (FGSM) as an augmentation tool for adversarial machine learning attack methods. Besides, we have developed the method of Inverse FGSM, which im- proves performance by operating in the opposite way from FGSM adversarial attacks. In comparison to the conventional FGSM methodology, our strategy boosted performance up to 6% to 7% on average. The model became more resilient to hostile attacks because to these two strategies. An innovative implementation of adversarial machine learning and resilience augmentation is revealed by the overall analysis of this study.
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...IRJET Journal
This document summarizes a research paper that proposes a method for detecting brain tumors by fusing CT and MRI images using stationary wavelet transform and a probabilistic neural network classifier. The proposed method involves preprocessing the CT and MRI images using median filtering for noise removal. It then applies stationary wavelet transform to the images to extract features before segmenting the tumor region using k-means clustering. Finally, the probabilistic neural network classifier determines if the tumor is benign or malignant based on the fused image features. The paper reviews other existing fusion and classification methods and argues that the proposed stationary wavelet transform and probabilistic neural network approach provides better detection of brain tumors.
The biomedical profession has gained importance due to the rapid and accurate diagnosis of clinical patients using computer-aided diagnosis (CAD) tools.
The diagnosis and treatment of Alzheimer’s disease (AD) using complementary multimodalities can improve the quality of life and mental state of patients.
In this study, we integrated a lightweight custom convolutional neural network
(CNN) model and nature-inspired optimization techniques to enhance the performance, robustness, and stability of progress detection in AD. A multi-modal
fusion database approach was implemented, including positron emission tomography (PET) and magnetic resonance imaging (MRI) datasets, to create a fused
database. We compared the performance of custom and pre-trained deep learning models with and without optimization and found that employing natureinspired algorithms like the particle swarm optimization algorithm (PSO) algorithm significantly improved system performance. The proposed methodology,
which includes a fused multimodality database and optimization strategy, improved performance metrics such as training, validation, test accuracy, precision, and recall. Furthermore, PSO was found to improve the performance of
pre-trained models by 3-5% and custom models by up to 22%. Combining different medical imaging modalities improved the overall model performance by
2-5%. In conclusion, a customized lightweight CNN model and nature-inspired
optimization techniques can significantly enhance progress detection, leading to
better biomedical research and patient care.
Generative adversarial deep learning in images using Nash equilibrium game th...IJECEIAES
A generative adversarial learning (GAL) algorithm is presented to overcome the manipulations that take place in adversarial data and to result in a secured convolutional neural network (CNN). The main objective of the generative algorithm is to make some changes to initial data with positive and negative class labels in testing, hence the CNN results in misclassified data. An adversarial algorithm is used to manipulate the input data that represents the boundaries of learner’s decision-making process. The algorithm generates adversarial modifications to the test dataset using a multiplayer stochastic game approach, without learning how to manipulate the data during training. Then the manipulated data is passed through a CNN for evaluation. The multi-player game consists of an interaction between adversaries which generates manipulations and retrains the model by the learner. The Nash equilibrium game theory (NEGT) is applied to Canadian Institute for Advance Research (CIFAR) dataset. This was done to produce a secure CNN output that is more robust to adversarial data manipulations. The experimental results show that proposed NEGT-GAL achieved a grater mean value of 7.92 and takes less wall clock time of 25,243 sec. Therefore, the proposed NEGT-GAL outperforms the compared existing methods and achieves greater performance.
Comparative Study on Medical Image Classification TechniquesINFOGAIN PUBLICATION
This brief study compares the proposed RGSA algorithm with other recent methods by several experiments to indicate that proposed 3DGLCM and SGLDM with SVM classifier is more efficient and accurate. The accuracy results of this study imply how well their experimental results were found to give more accurate results of classifying tumors. The center of interest for this study was made on supervised classification approaches on 2D MRI images of brain tumors. This paper gives the comparative study of various approaches that was used to identify the tumor cells with classifiers.
This document provides a literature survey on methods for detecting brain tumors from MRI images. It discusses several segmentation techniques that have been used for this purpose, including thresholding, edge-based, region-based, k-means clustering, fuzzy c-means clustering, and optimization methods like ant colony optimization, genetic algorithms, and particle swarm optimization. The document reviews related work comparing these methods and evaluates their performance based on metrics like PSNR and RMSE. It concludes that while no single universal method exists, fuzzy c-means is well-suited for medical image segmentation tasks due to its simplicity and ability to provide faster clustering.
Literature Survey on Detection of Brain Tumor from MRI Images IOSR Journals
This document provides a literature survey on methods for detecting brain tumors from MRI images. It discusses several segmentation and clustering techniques that have been used for this purpose, including thresholding, edge-based segmentation, region-based segmentation, fuzzy c-means clustering, and k-means clustering. The document also reviews related work applying these methods and evaluates their effectiveness at automatically detecting and segmenting brain tumors from MRI data.
3D Segmentation of Brain Tumor ImagingIJAEMSJORNAL
A brain tumor is a collection of anomalous cells that grow in or around the brain. Brain tumors affect the humans badly, it can disrupt proper brain function and be life-threatening. In this project, we have proposed a system to detect, segment, and classify the tumors present in the brain. Once the brain tumor is identified at the very beginning, proper treatments can be done and it may be cured.
Adversarial attack driven data augmentation for medical imagesIJECEIAES
An important stage in medical image analysis is segmentation, which aids in focusing on the required area of an image and speeds up findings. Fortunately, deep learning models have taken over with their high-performing capabilities, making this process simpler. The deep learning model’s reliance on vast data, however, makes it difficult to utilize for medical image analysis due to the scarcity of data samples. Too far, a number of data augmentations techniques have been employed to address the issue of data unavailability. Here, we present a novel method of augmentation that enabled the UNet model to segment the input dataset with about 90% accuracy in just 30 epochs. We describe the us- age of fast gradient sign method (FGSM) as an augmentation tool for adversarial machine learning attack methods. Besides, we have developed the method of Inverse FGSM, which im- proves performance by operating in the opposite way from FGSM adversarial attacks. In comparison to the conventional FGSM methodology, our strategy boosted performance up to 6% to 7% on average. The model became more resilient to hostile attacks because to these two strategies. An innovative implementation of adversarial machine learning and resilience augmentation is revealed by the overall analysis of this study.
IRJET - Fusion of CT and MRI for the Detection of Brain Tumor by SWT and Prob...IRJET Journal
This document summarizes a research paper that proposes a method for detecting brain tumors by fusing CT and MRI images using stationary wavelet transform and a probabilistic neural network classifier. The proposed method involves preprocessing the CT and MRI images using median filtering for noise removal. It then applies stationary wavelet transform to the images to extract features before segmenting the tumor region using k-means clustering. Finally, the probabilistic neural network classifier determines if the tumor is benign or malignant based on the fused image features. The paper reviews other existing fusion and classification methods and argues that the proposed stationary wavelet transform and probabilistic neural network approach provides better detection of brain tumors.
The biomedical profession has gained importance due to the rapid and accurate diagnosis of clinical patients using computer-aided diagnosis (CAD) tools.
The diagnosis and treatment of Alzheimer’s disease (AD) using complementary multimodalities can improve the quality of life and mental state of patients.
In this study, we integrated a lightweight custom convolutional neural network
(CNN) model and nature-inspired optimization techniques to enhance the performance, robustness, and stability of progress detection in AD. A multi-modal
fusion database approach was implemented, including positron emission tomography (PET) and magnetic resonance imaging (MRI) datasets, to create a fused
database. We compared the performance of custom and pre-trained deep learning models with and without optimization and found that employing natureinspired algorithms like the particle swarm optimization algorithm (PSO) algorithm significantly improved system performance. The proposed methodology,
which includes a fused multimodality database and optimization strategy, improved performance metrics such as training, validation, test accuracy, precision, and recall. Furthermore, PSO was found to improve the performance of
pre-trained models by 3-5% and custom models by up to 22%. Combining different medical imaging modalities improved the overall model performance by
2-5%. In conclusion, a customized lightweight CNN model and nature-inspired
optimization techniques can significantly enhance progress detection, leading to
better biomedical research and patient care.
Generative adversarial deep learning in images using Nash equilibrium game th...IJECEIAES
A generative adversarial learning (GAL) algorithm is presented to overcome the manipulations that take place in adversarial data and to result in a secured convolutional neural network (CNN). The main objective of the generative algorithm is to make some changes to initial data with positive and negative class labels in testing, hence the CNN results in misclassified data. An adversarial algorithm is used to manipulate the input data that represents the boundaries of learner’s decision-making process. The algorithm generates adversarial modifications to the test dataset using a multiplayer stochastic game approach, without learning how to manipulate the data during training. Then the manipulated data is passed through a CNN for evaluation. The multi-player game consists of an interaction between adversaries which generates manipulations and retrains the model by the learner. The Nash equilibrium game theory (NEGT) is applied to Canadian Institute for Advance Research (CIFAR) dataset. This was done to produce a secure CNN output that is more robust to adversarial data manipulations. The experimental results show that proposed NEGT-GAL achieved a grater mean value of 7.92 and takes less wall clock time of 25,243 sec. Therefore, the proposed NEGT-GAL outperforms the compared existing methods and achieves greater performance.
Comparative Study on Medical Image Classification TechniquesINFOGAIN PUBLICATION
This brief study compares the proposed RGSA algorithm with other recent methods by several experiments to indicate that proposed 3DGLCM and SGLDM with SVM classifier is more efficient and accurate. The accuracy results of this study imply how well their experimental results were found to give more accurate results of classifying tumors. The center of interest for this study was made on supervised classification approaches on 2D MRI images of brain tumors. This paper gives the comparative study of various approaches that was used to identify the tumor cells with classifiers.
This document provides a literature survey on methods for detecting brain tumors from MRI images. It discusses several segmentation techniques that have been used for this purpose, including thresholding, edge-based, region-based, k-means clustering, fuzzy c-means clustering, and optimization methods like ant colony optimization, genetic algorithms, and particle swarm optimization. The document reviews related work comparing these methods and evaluates their performance based on metrics like PSNR and RMSE. It concludes that while no single universal method exists, fuzzy c-means is well-suited for medical image segmentation tasks due to its simplicity and ability to provide faster clustering.
Literature Survey on Detection of Brain Tumor from MRI Images IOSR Journals
This document provides a literature survey on methods for detecting brain tumors from MRI images. It discusses several segmentation and clustering techniques that have been used for this purpose, including thresholding, edge-based segmentation, region-based segmentation, fuzzy c-means clustering, and k-means clustering. The document also reviews related work applying these methods and evaluates their effectiveness at automatically detecting and segmenting brain tumors from MRI data.
The document describes a study that uses convolutional neural networks (CNNs) to detect brain tumors in MRI images. Three CNN models are developed and their performance is evaluated using various metrics like accuracy, precision, recall, F1-score, and confusion matrices. The first two models achieve accuracy of up to 94% in detecting tumors, while the third model is able to train and predict tumors with 94% accuracy as well. In total, over 2000 MRI images are used from a public dataset to train and test the models for brain tumor classification.
The document describes a study that used convolutional neural networks (CNNs) to detect brain tumors in MRI images. Three CNN models were developed and their performance was evaluated using metrics like accuracy, precision, recall, F1-score, and confusion matrices. Model 3 achieved the highest test accuracy of 94% for tumor detection. In total, over 2000 MRI images were used in the study after data augmentation. The CNN models incorporated convolution, pooling, and fully connected layers to analyze image features and classify tumors. This research demonstrates that CNNs can accurately detect brain tumors in medical images.
Computer Aided System for Detection and Classification of Breast CancerIJITCA Journal
Breast cancer is one of the most important causes of death among all type of cancers for grown-up and
older women, mainly in developed countries, and its rate is rising. Since the cause of this disease is not yet
known, early detection is the best way to decrease the breast cancer mortality. At present, early detection of
breast cancer is attained by means of mammography. An intelligent computer-aided diagnosis system can
be very helpful for radiologist in detecting and diagnosing cancerous cell patterns earlier and faster than
typical screening programs. This paper proposes a computer aided system for automatic detection and
classification of breast cancer in mammogram images. Intuitionistic Fuzzy C-Means clustering technique
has been used to identify the suspicious region or the Region of Interest automatically. Then, the feature
data base is designed using histogram features, Gray Level Concurrence wavelet features and wavelet
energy features. Finally, the feature database is submitted to self-adaptive resource allocation network
classifier for classification of mammogram image as normal, benign or malignant. The proposed system is
verified with 322 mammograms from the Mammographic Image Analysis Society Database. The results
show that the proposed system produces better results.
Brain Tumor Detection From MRI Image Using Deep LearningIRJET Journal
This document presents a study on using deep learning techniques for brain tumor detection from MRI images. It proposes two Convolutional Neural Network models - one without transfer learning that achieves 81.42% accuracy, and one with transfer learning using the VGG16 architecture that achieves significantly higher accuracy of 98.8%. The study uses a dataset of over 5,000 MRI images categorized as normal, benign tumor, or malignant tumor. Data preprocessing techniques like filtering and enhancement are applied before training the models. Transfer learning helps reduce training time and improves model performance for tumor classification compared to training from scratch without transferring learned features.
Image segmentation and classification tasks in computer vision have proven to be highly effective using neural networks, specifically Convolutional Neural Networks (CNNs). These tasks have numerous
practical applications, such as in medical imaging, autonomous driving, and surveillance. CNNs are capable
of learning complex features directly from images and achieving outstanding performance across several
datasets. In this work, we have utilized three different datasets to investigate the efficacy of various preprocessing and classification techniques in accurssedately segmenting and classifying different structures
within the MRI and natural images. We have utilized both sample gradient and Canny Edge Detection
methods for pre-processing, and K-means clustering have been applied to segment the images. Image
augmentation improves the size and diversity of datasets for training the models for image classification
Image segmentation and classification tasks in computer vision have proven to be highly effective using neural networks, specifically Convolutional Neural Networks (CNNs). These tasks have numerous
practical applications, such as in medical imaging, autonomous driving, and surveillance. CNNs are capable
of learning complex features directly from images and achieving outstanding performance across several
datasets. In this work, we have utilized three different datasets to investigate the efficacy of various preprocessing and classification techniques in accurssedately segmenting and classifying different structures
within the MRI and natural images. We have utilized both sample gradient and Canny Edge Detection
methods for pre-processing, and K-means clustering have been applied to segment the images. Image
augmentation improves the size and diversity of datasets for training the models for image classification.
This work highlights transfer learning’s effectiveness in image classification using CNNs and VGG 16 that
provides insights into the selection of pre-trained models and hyper parameters for optimal performance.
We have proposed a comprehensive approach for image segmentation and classification, incorporating preprocessing techniques, the K-means algorithm for segmentation, and employing deep learning models such
as CNN and VGG 16 for classification.
Development and Comparison of Image Fusion Techniques for CT&MRI ImagesIJERA Editor
Image processing techniques primarily focus upon enhancing the quality of an image or a set ofimages to derive
the maximum information from them. Image Fusion is a technique of producing a superior quality image from a
set of available images. It is the process of combining relevant information from two or more images into a
single image wherein the resulting image will be more informative and complete than any of the input images. A
lot of research is being done in this field encompassing areas of Computer Vision, Automatic object detection,
Image processing, parallel and distributed processing, Robotics and remote sensing. This project paves way to
explain the theoretical and implementation issues of seven image fusion algorithms and the experimental results
of the same. The fusion algorithms would be assessed based on the study and development of some image
quality metrics
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET Journal
This document summarizes several research papers on techniques for segmenting brain tumors in MRI images. It discusses challenges in brain tumor segmentation and describes various approaches that have been proposed, including methods using feature selection, kernel sparse representation, multiple kernel learning (MKL), and post-processing techniques. The document also reviews state-of-the-art segmentation, registration, and modeling methods for brain tumor images and their performance.
The IoT and registration of MRI brain diagnosis based on genetic algorithm an...IJEECSIAES
The technology of the multimodal brain image registration is the key method for accurate and rapid diagnosis and treatment of brain diseases. For achieving high-resolution image registration, a fast sub pixel registration algorithm is used based on single-step discrete wavelet transform (DWT) combined with phase convolution neural network (CNN) to classify the registration of brain tumors. In this work apply the genetic algorithm and CNN clasifcation in registration of magnetic resonance imaging (MRI) image. This approach follows eight steps, reading the source of MRI brain image and loading the reference image, enhencment all MRI images by bilateral filter, transforming DWT image by applying the DWT2, evaluating (fitness function) each MRI image by using entropy, applying the genetic algorithm, by selecting the two images based on rollout wheel and crossover of the two images, the CNN classify the result of subtraction to normal or abnormal, “in the eighth one,” the Arduino and global system for mobile (GSM) 8080 are applied to send the message to patient. The proposed model is tested on MRI Medical City Hospital in Baghdad database consist 550 normal and 350 abnormal and split to 80% training and 20 testing, the proposed model result achieves the 98.8% accuracy.
The IoT and registration of MRI brain diagnosis based on genetic algorithm an...nooriasukmaningtyas
The document describes a proposed model for MRI brain diagnosis using genetic algorithms, convolutional neural networks, and the Internet of Things. The model has eight steps: loading MRI images, enhancing images, applying discrete wavelet transform, evaluating images using entropy, applying genetic algorithm for registration, subtracting images and using CNN to classify results as normal or abnormal, and sending messages to patients using Arduino and GSM. The model was tested on 550 normal and 350 abnormal MRI images, achieving 98.8% accuracy in classification.
This document describes a study that used deep learning models to diagnose Alzheimer's disease using MRI scans. Specifically, it used convolutional neural networks (CNNs) trained on MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The study achieved an F1-score of 89% for classifying Alzheimer's vs normal cognition. It also used a CycleGAN for data augmentation, which generated additional synthetic MRI images and improved the CNN classification accuracy to 95% F1-score. The document provides background on Alzheimer's diagnosis, CNNs, GANs including CycleGAN, related work applying machine learning to Alzheimer's diagnosis, and the methodology used in this study for data preprocessing, model training, and evaluating the impact of GAN
Classification of MR medical images Based Rough-Fuzzy KMeansIOSRJM
The document summarizes a proposed algorithm for classifying MR medical images using Rough-Fuzzy K-Means (FRKM). It begins with an introduction to the challenges of medical image classification and a literature review of previous techniques. It then provides background on rough set theory, fuzzy set theory, and K-means clustering. The proposed FRKM algorithm is described as using rough set theory for feature selection and dimensionality reduction, followed by a K-means clustering with probabilities assigned based on rough set approximations to classify ambiguous areas. Experimental results show the FRKM approach achieves 94.4% accuracy, higher than other techniques.
The document proposes a semi-supervised learning method called transfer learning with dual-task consistency (TL-DTC) for 3D left atrium segmentation from MRI scans. The method uses a V-Net backbone with a hybrid dilated convolution module. It is trained in two phases: first pre-training on sub-images, then fine-tuning on full images. Dual-task consistency is enforced between segmentation and signed distance map regression tasks to improve predictions. On the left atrium dataset, TL-DTC outperforms other semi-supervised methods with a Dice score of 90.72% using 20% labeled data.
IJCER (www.ijceronline.com) International Journal of computational Engineerin...ijceronline
This document describes a novel approach to automated classification of brain tumors using probabilistic neural networks (PNN). It discusses how principal component analysis (PCA) can be used to reduce the dimensionality of magnetic resonance (MR) brain images, and then a PNN can classify the tumors. The proposed method involves using PCA for feature extraction and a PNN for classification. This is intended to provide faster and more accurate classification of brain tumors in MR images than conventional human-based methods.
An efficient convolutional neural network-based classifier for an imbalanced ...IAESIJAI
Imbalanced datasets pose a major challenge for the researchers while addressing machine learning tasks. In these types of datasets, samples of different classes are not in equal proportion rather the gap between the numbers of individual class samples is significantly large. Classification models perform better for datasets having equal proportion of data tuples in both the classes. But, in reality, the medical image datasets are skewed and hence are not always suitable for a model to achieve improved classification performance. Therefore, various techniques have been suggested in the literature to overcome this challenge. This paper applies oversampling technique on an imbalanced dataset and focuses on a customized convolutional neural network model that classifies the images into two categories: diseased and non-diseased. Outcome of the proposed model can assist the health experts in the detection of oral cancer. The proposed model exhibits 99% accuracy after data augmentation. Performance metrics such as precision, recall and F1-score values are very close to 1. In addition, statistical test is performed to validate the statistical significance of the model. It has been found that the proposed model is an optimised classifier in terms of number of network layers and number of neurons.
Fuzzy k c-means clustering algorithm for medical imageAlexander Decker
This document summarizes and compares several algorithms used for medical image segmentation, including thresholding, classifiers, Markov random field models, artificial neural networks, atlas-guided approaches, deformable models, and clustering analysis methods like k-means and fuzzy c-means. It provides details on the fuzzy c-means and k-means clustering algorithms, including their process and flowcharts. A new fuzzy k-c-means algorithm is proposed that combines fuzzy c-means and k-means clustering to improve segmentation time. The algorithms are tested on MRI brain images and their results are analyzed and compared based on time, iterations, and accuracy.
APPLICATION OF CNN MODEL ON MEDICAL IMAGEIRJET Journal
The document discusses using convolutional neural network (CNN) models to detect diseases from medical images such as chest X-rays. It describes how CNN models can be trained on large labeled datasets of chest X-rays to learn patterns and features that indicate diseases. The document then evaluates several CNN architectures - including VGG-16, ResNet, DenseNet, and InceptionNet - for classifying chest X-rays as normal or infected. It finds these models achieve high accuracy, with metrics like accuracy over 89% and AUC over 0.94. In conclusion, deep learning models show promising results for automated disease detection from medical images.
DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...IRJET Journal
This document presents research on using a convolutional neural network (CNN) model for the detection and classification of brain tumors from MRI images. The CNN model improves the accuracy of tumor detection and can serve as a useful tool for physicians. The researchers trained and tested several CNN architectures, including CNN, ResNet50, MobileNetV2, and VGG19 on an MRI brain image database. Their proposed model uses a modified Residual U-Net architecture with residual blocks and attention gates to better segment tumors and extract local features from MRI images. Evaluation results found their model achieved better accuracy than existing methods like U-Net and CNN for brain tumor segmentation tasks.
This document presents a method for segmenting and detecting tumors in MRI brain images using convolutional neural networks (CNNs) and support vector machine (SVM) classification. The proposed method first performs pre-processing on MRI images, including bias field correction and intensity normalization. CNN is then used to segment the images and identify enhanced tumor (HGG) and edema tumor (LGG) regions. Features are extracted from the images and SVM classification is performed to determine if the tumor is benign or malignant based on calculated parameters like mean, standard deviation, and texture features. Results show the CNN segmentation achieved Dice similarity, positive predictive value, and sensitivity metrics over 98%, demonstrating accurate tumor segmentation. The calculated features and SVM classification then identified a tumor
Brain Tumor Detection and Segmentation using UNETIRJET Journal
This document discusses brain tumor detection and segmentation using the UNET model. It analyzes previous research on brain tumor segmentation techniques and their limitations. The proposed method uses the BraTS 2020 dataset containing 369 MRI images for training and 125 for testing. It develops a 3D UNET model for multimodal brain tumor segmentation. The model generates 3D outputs and achieves 98.5% accuracy in segmenting whole, core and enhancing tumors.
Robustness in Machine Learning Explanations Does It Matter-1.pdfDaniel983829
This document discusses the desirability of robustness in machine learning explanations. It argues that robustness is desirable to the extent we want explanations to reflect real patterns in the data and the world. The importance of explanations capturing real patterns depends on the problem context. In some contexts, non-robust explanations can pose moral hazards. Clarifying how much we want explanations to capture real patterns can help determine whether the "Rashomon effect" is beneficial or problematic.
Robustness and Regularization of Support Vector Machines.pdfDaniel983829
This document summarizes a research paper that establishes an equivalence between robust optimization and regularization as applied to support vector machines (SVMs). It shows that regularized SVMs can be formulated as a robust optimization problem that minimizes error under potential adversarial noise or disturbances in the training data. This provides an alternative explanation for why regularization improves generalization performance of SVMs. The document also discusses implications for algorithm development and analysis, including a new proof of consistency for SVMs based on their robustness interpretation.
More Related Content
Similar to Generative Adversarial Networks for Robust Medical Image Analysis.pdf
The document describes a study that uses convolutional neural networks (CNNs) to detect brain tumors in MRI images. Three CNN models are developed and their performance is evaluated using various metrics like accuracy, precision, recall, F1-score, and confusion matrices. The first two models achieve accuracy of up to 94% in detecting tumors, while the third model is able to train and predict tumors with 94% accuracy as well. In total, over 2000 MRI images are used from a public dataset to train and test the models for brain tumor classification.
The document describes a study that used convolutional neural networks (CNNs) to detect brain tumors in MRI images. Three CNN models were developed and their performance was evaluated using metrics like accuracy, precision, recall, F1-score, and confusion matrices. Model 3 achieved the highest test accuracy of 94% for tumor detection. In total, over 2000 MRI images were used in the study after data augmentation. The CNN models incorporated convolution, pooling, and fully connected layers to analyze image features and classify tumors. This research demonstrates that CNNs can accurately detect brain tumors in medical images.
Computer Aided System for Detection and Classification of Breast CancerIJITCA Journal
Breast cancer is one of the most important causes of death among all type of cancers for grown-up and
older women, mainly in developed countries, and its rate is rising. Since the cause of this disease is not yet
known, early detection is the best way to decrease the breast cancer mortality. At present, early detection of
breast cancer is attained by means of mammography. An intelligent computer-aided diagnosis system can
be very helpful for radiologist in detecting and diagnosing cancerous cell patterns earlier and faster than
typical screening programs. This paper proposes a computer aided system for automatic detection and
classification of breast cancer in mammogram images. Intuitionistic Fuzzy C-Means clustering technique
has been used to identify the suspicious region or the Region of Interest automatically. Then, the feature
data base is designed using histogram features, Gray Level Concurrence wavelet features and wavelet
energy features. Finally, the feature database is submitted to self-adaptive resource allocation network
classifier for classification of mammogram image as normal, benign or malignant. The proposed system is
verified with 322 mammograms from the Mammographic Image Analysis Society Database. The results
show that the proposed system produces better results.
Brain Tumor Detection From MRI Image Using Deep LearningIRJET Journal
This document presents a study on using deep learning techniques for brain tumor detection from MRI images. It proposes two Convolutional Neural Network models - one without transfer learning that achieves 81.42% accuracy, and one with transfer learning using the VGG16 architecture that achieves significantly higher accuracy of 98.8%. The study uses a dataset of over 5,000 MRI images categorized as normal, benign tumor, or malignant tumor. Data preprocessing techniques like filtering and enhancement are applied before training the models. Transfer learning helps reduce training time and improves model performance for tumor classification compared to training from scratch without transferring learned features.
Image segmentation and classification tasks in computer vision have proven to be highly effective using neural networks, specifically Convolutional Neural Networks (CNNs). These tasks have numerous
practical applications, such as in medical imaging, autonomous driving, and surveillance. CNNs are capable
of learning complex features directly from images and achieving outstanding performance across several
datasets. In this work, we have utilized three different datasets to investigate the efficacy of various preprocessing and classification techniques in accurssedately segmenting and classifying different structures
within the MRI and natural images. We have utilized both sample gradient and Canny Edge Detection
methods for pre-processing, and K-means clustering have been applied to segment the images. Image
augmentation improves the size and diversity of datasets for training the models for image classification
Image segmentation and classification tasks in computer vision have proven to be highly effective using neural networks, specifically Convolutional Neural Networks (CNNs). These tasks have numerous
practical applications, such as in medical imaging, autonomous driving, and surveillance. CNNs are capable
of learning complex features directly from images and achieving outstanding performance across several
datasets. In this work, we have utilized three different datasets to investigate the efficacy of various preprocessing and classification techniques in accurssedately segmenting and classifying different structures
within the MRI and natural images. We have utilized both sample gradient and Canny Edge Detection
methods for pre-processing, and K-means clustering have been applied to segment the images. Image
augmentation improves the size and diversity of datasets for training the models for image classification.
This work highlights transfer learning’s effectiveness in image classification using CNNs and VGG 16 that
provides insights into the selection of pre-trained models and hyper parameters for optimal performance.
We have proposed a comprehensive approach for image segmentation and classification, incorporating preprocessing techniques, the K-means algorithm for segmentation, and employing deep learning models such
as CNN and VGG 16 for classification.
Development and Comparison of Image Fusion Techniques for CT&MRI ImagesIJERA Editor
Image processing techniques primarily focus upon enhancing the quality of an image or a set ofimages to derive
the maximum information from them. Image Fusion is a technique of producing a superior quality image from a
set of available images. It is the process of combining relevant information from two or more images into a
single image wherein the resulting image will be more informative and complete than any of the input images. A
lot of research is being done in this field encompassing areas of Computer Vision, Automatic object detection,
Image processing, parallel and distributed processing, Robotics and remote sensing. This project paves way to
explain the theoretical and implementation issues of seven image fusion algorithms and the experimental results
of the same. The fusion algorithms would be assessed based on the study and development of some image
quality metrics
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET Journal
This document summarizes several research papers on techniques for segmenting brain tumors in MRI images. It discusses challenges in brain tumor segmentation and describes various approaches that have been proposed, including methods using feature selection, kernel sparse representation, multiple kernel learning (MKL), and post-processing techniques. The document also reviews state-of-the-art segmentation, registration, and modeling methods for brain tumor images and their performance.
The IoT and registration of MRI brain diagnosis based on genetic algorithm an...IJEECSIAES
The technology of the multimodal brain image registration is the key method for accurate and rapid diagnosis and treatment of brain diseases. For achieving high-resolution image registration, a fast sub pixel registration algorithm is used based on single-step discrete wavelet transform (DWT) combined with phase convolution neural network (CNN) to classify the registration of brain tumors. In this work apply the genetic algorithm and CNN clasifcation in registration of magnetic resonance imaging (MRI) image. This approach follows eight steps, reading the source of MRI brain image and loading the reference image, enhencment all MRI images by bilateral filter, transforming DWT image by applying the DWT2, evaluating (fitness function) each MRI image by using entropy, applying the genetic algorithm, by selecting the two images based on rollout wheel and crossover of the two images, the CNN classify the result of subtraction to normal or abnormal, “in the eighth one,” the Arduino and global system for mobile (GSM) 8080 are applied to send the message to patient. The proposed model is tested on MRI Medical City Hospital in Baghdad database consist 550 normal and 350 abnormal and split to 80% training and 20 testing, the proposed model result achieves the 98.8% accuracy.
The IoT and registration of MRI brain diagnosis based on genetic algorithm an...nooriasukmaningtyas
The document describes a proposed model for MRI brain diagnosis using genetic algorithms, convolutional neural networks, and the Internet of Things. The model has eight steps: loading MRI images, enhancing images, applying discrete wavelet transform, evaluating images using entropy, applying genetic algorithm for registration, subtracting images and using CNN to classify results as normal or abnormal, and sending messages to patients using Arduino and GSM. The model was tested on 550 normal and 350 abnormal MRI images, achieving 98.8% accuracy in classification.
This document describes a study that used deep learning models to diagnose Alzheimer's disease using MRI scans. Specifically, it used convolutional neural networks (CNNs) trained on MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The study achieved an F1-score of 89% for classifying Alzheimer's vs normal cognition. It also used a CycleGAN for data augmentation, which generated additional synthetic MRI images and improved the CNN classification accuracy to 95% F1-score. The document provides background on Alzheimer's diagnosis, CNNs, GANs including CycleGAN, related work applying machine learning to Alzheimer's diagnosis, and the methodology used in this study for data preprocessing, model training, and evaluating the impact of GAN
Classification of MR medical images Based Rough-Fuzzy KMeansIOSRJM
The document summarizes a proposed algorithm for classifying MR medical images using Rough-Fuzzy K-Means (FRKM). It begins with an introduction to the challenges of medical image classification and a literature review of previous techniques. It then provides background on rough set theory, fuzzy set theory, and K-means clustering. The proposed FRKM algorithm is described as using rough set theory for feature selection and dimensionality reduction, followed by a K-means clustering with probabilities assigned based on rough set approximations to classify ambiguous areas. Experimental results show the FRKM approach achieves 94.4% accuracy, higher than other techniques.
The document proposes a semi-supervised learning method called transfer learning with dual-task consistency (TL-DTC) for 3D left atrium segmentation from MRI scans. The method uses a V-Net backbone with a hybrid dilated convolution module. It is trained in two phases: first pre-training on sub-images, then fine-tuning on full images. Dual-task consistency is enforced between segmentation and signed distance map regression tasks to improve predictions. On the left atrium dataset, TL-DTC outperforms other semi-supervised methods with a Dice score of 90.72% using 20% labeled data.
IJCER (www.ijceronline.com) International Journal of computational Engineerin...ijceronline
This document describes a novel approach to automated classification of brain tumors using probabilistic neural networks (PNN). It discusses how principal component analysis (PCA) can be used to reduce the dimensionality of magnetic resonance (MR) brain images, and then a PNN can classify the tumors. The proposed method involves using PCA for feature extraction and a PNN for classification. This is intended to provide faster and more accurate classification of brain tumors in MR images than conventional human-based methods.
An efficient convolutional neural network-based classifier for an imbalanced ...IAESIJAI
Imbalanced datasets pose a major challenge for the researchers while addressing machine learning tasks. In these types of datasets, samples of different classes are not in equal proportion rather the gap between the numbers of individual class samples is significantly large. Classification models perform better for datasets having equal proportion of data tuples in both the classes. But, in reality, the medical image datasets are skewed and hence are not always suitable for a model to achieve improved classification performance. Therefore, various techniques have been suggested in the literature to overcome this challenge. This paper applies oversampling technique on an imbalanced dataset and focuses on a customized convolutional neural network model that classifies the images into two categories: diseased and non-diseased. Outcome of the proposed model can assist the health experts in the detection of oral cancer. The proposed model exhibits 99% accuracy after data augmentation. Performance metrics such as precision, recall and F1-score values are very close to 1. In addition, statistical test is performed to validate the statistical significance of the model. It has been found that the proposed model is an optimised classifier in terms of number of network layers and number of neurons.
Fuzzy k c-means clustering algorithm for medical imageAlexander Decker
This document summarizes and compares several algorithms used for medical image segmentation, including thresholding, classifiers, Markov random field models, artificial neural networks, atlas-guided approaches, deformable models, and clustering analysis methods like k-means and fuzzy c-means. It provides details on the fuzzy c-means and k-means clustering algorithms, including their process and flowcharts. A new fuzzy k-c-means algorithm is proposed that combines fuzzy c-means and k-means clustering to improve segmentation time. The algorithms are tested on MRI brain images and their results are analyzed and compared based on time, iterations, and accuracy.
APPLICATION OF CNN MODEL ON MEDICAL IMAGEIRJET Journal
The document discusses using convolutional neural network (CNN) models to detect diseases from medical images such as chest X-rays. It describes how CNN models can be trained on large labeled datasets of chest X-rays to learn patterns and features that indicate diseases. The document then evaluates several CNN architectures - including VGG-16, ResNet, DenseNet, and InceptionNet - for classifying chest X-rays as normal or infected. It finds these models achieve high accuracy, with metrics like accuracy over 89% and AUC over 0.94. In conclusion, deep learning models show promising results for automated disease detection from medical images.
DIRECTIONAL CLASSIFICATION OF BRAIN TUMOR IMAGES FROM MRI USING CNN-BASED DEE...IRJET Journal
This document presents research on using a convolutional neural network (CNN) model for the detection and classification of brain tumors from MRI images. The CNN model improves the accuracy of tumor detection and can serve as a useful tool for physicians. The researchers trained and tested several CNN architectures, including CNN, ResNet50, MobileNetV2, and VGG19 on an MRI brain image database. Their proposed model uses a modified Residual U-Net architecture with residual blocks and attention gates to better segment tumors and extract local features from MRI images. Evaluation results found their model achieved better accuracy than existing methods like U-Net and CNN for brain tumor segmentation tasks.
This document presents a method for segmenting and detecting tumors in MRI brain images using convolutional neural networks (CNNs) and support vector machine (SVM) classification. The proposed method first performs pre-processing on MRI images, including bias field correction and intensity normalization. CNN is then used to segment the images and identify enhanced tumor (HGG) and edema tumor (LGG) regions. Features are extracted from the images and SVM classification is performed to determine if the tumor is benign or malignant based on calculated parameters like mean, standard deviation, and texture features. Results show the CNN segmentation achieved Dice similarity, positive predictive value, and sensitivity metrics over 98%, demonstrating accurate tumor segmentation. The calculated features and SVM classification then identified a tumor
Brain Tumor Detection and Segmentation using UNETIRJET Journal
This document discusses brain tumor detection and segmentation using the UNET model. It analyzes previous research on brain tumor segmentation techniques and their limitations. The proposed method uses the BraTS 2020 dataset containing 369 MRI images for training and 125 for testing. It develops a 3D UNET model for multimodal brain tumor segmentation. The model generates 3D outputs and achieves 98.5% accuracy in segmenting whole, core and enhancing tumors.
Similar to Generative Adversarial Networks for Robust Medical Image Analysis.pdf (20)
Robustness in Machine Learning Explanations Does It Matter-1.pdfDaniel983829
This document discusses the desirability of robustness in machine learning explanations. It argues that robustness is desirable to the extent we want explanations to reflect real patterns in the data and the world. The importance of explanations capturing real patterns depends on the problem context. In some contexts, non-robust explanations can pose moral hazards. Clarifying how much we want explanations to capture real patterns can help determine whether the "Rashomon effect" is beneficial or problematic.
Robustness and Regularization of Support Vector Machines.pdfDaniel983829
This document summarizes a research paper that establishes an equivalence between robust optimization and regularization as applied to support vector machines (SVMs). It shows that regularized SVMs can be formulated as a robust optimization problem that minimizes error under potential adversarial noise or disturbances in the training data. This provides an alternative explanation for why regularization improves generalization performance of SVMs. The document also discusses implications for algorithm development and analysis, including a new proof of consistency for SVMs based on their robustness interpretation.
Robustness of Machine Learning Models Beyond Adversarial Attacks.pdfDaniel983829
This document discusses assessing the robustness of machine learning models to "real-world perturbations" that occur naturally rather than being crafted by an adversary. It argues that adversarial robustness is not a valid measure of robustness to such natural perturbations. The document proposes a probabilistic approach to compute the likelihood that a real-world perturbation would change a model's prediction, quantifying its real-world robustness. This approach models possible input perturbations individually for each application and works for any "black-box" model. It illustrates the approach on two datasets and analytically solvable cases, and discusses estimating real-world robustness in high-dimensional spaces.
Robustness in Deep Learning - Single Image Denoising using Untrained Networks...Daniel983829
This document is a thesis submitted by Esha Singh to the University of Minnesota for the degree of Master of Science in May 2021. The thesis explores single image denoising using untrained neural networks. It first provides background on deep learning, inverse problems, image denoising and neural networks. It then reviews existing image denoising algorithms including spatial/transform domain and neural network methods. The thesis also discusses recent work on deep image priors and rethinking single image denoising using over-parameterization and low-rank matrix recovery. Preliminary experiments on denoising images with salt and pepper noise are presented to demonstrate the proposed methodology.
Data preparation for artificial intelligence in medical imaging - A comprehen...Daniel983829
This document provides a comprehensive guide to tools and platforms for preparing medical image data for artificial intelligence applications. It discusses key steps in a medical image preparation pipeline including image acquisition, de-identification, data curation, storage, and annotation. A variety of open-access tools are reviewed that can perform image de-identification, data curation, storage, and annotation. Examples of medical imaging datasets covering different organs and diseases are also provided. The guide aims to enable standardized and large-scale data preparation and AI development in medical imaging.
Application of generative adversarial networks (GAN) for ophthalmology image ...Daniel983829
This document reviews literature on the application of generative adversarial networks (GANs) for ophthalmology image domains. GANs have been used for tasks like segmentation, data augmentation, denoising, domain transfer, and super-resolution of ophthalmic images. The review identified 48 relevant papers and found that GANs have benefited analysis of fundus photographs, optical coherence tomography scans, and other eye images. However, GANs also have limitations such as mode collapse and need clinical validation before practical use in ophthalmology. Further development could improve GAN performance for ocular image analysis and disease diagnosis.
Auditing AI models for verified deployment under semantic specifications.pdfDaniel983829
The document proposes a framework called AuditAI for auditing deep learning models prior to deployment. It does this by creating a bridge between the deep learning model and a generative model, allowing them to share the same semantically-aligned latent space. This enables the use of unit tests to verify that predefined specifications are satisfied for controlled variations in the latent space, like accuracy over 95% for different angles of faces. The framework applies interval bound propagation to provide certifications for specifications involving latent space perturbations, providing interpretable and scalable auditing of deep learning models.
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfChart Kalyan
A Mix Chart displays historical data of numbers in a graphical or tabular form. The Kalyan Rajdhani Mix Chart specifically shows the results of a sequence of numbers over different periods.
Have you ever been confused by the myriad of choices offered by AWS for hosting a website or an API?
Lambda, Elastic Beanstalk, Lightsail, Amplify, S3 (and more!) can each host websites + APIs. But which one should we choose?
Which one is cheapest? Which one is fastest? Which one will scale to meet our needs?
Join me in this session as we dive into each AWS hosting service to determine which one is best for your scenario and explain why!
Taking AI to the Next Level in Manufacturing.pdfssuserfac0301
Read Taking AI to the Next Level in Manufacturing to gain insights on AI adoption in the manufacturing industry, such as:
1. How quickly AI is being implemented in manufacturing.
2. Which barriers stand in the way of AI adoption.
3. How data quality and governance form the backbone of AI.
4. Organizational processes and structures that may inhibit effective AI adoption.
6. Ideas and approaches to help build your organization's AI strategy.
This presentation provides valuable insights into effective cost-saving techniques on AWS. Learn how to optimize your AWS resources by rightsizing, increasing elasticity, picking the right storage class, and choosing the best pricing model. Additionally, discover essential governance mechanisms to ensure continuous cost efficiency. Whether you are new to AWS or an experienced user, this presentation provides clear and practical tips to help you reduce your cloud costs and get the most out of your budget.
GraphRAG for Life Science to increase LLM accuracyTomaz Bratanic
GraphRAG for life science domain, where you retriever information from biomedical knowledge graphs using LLMs to increase the accuracy and performance of generated answers
Introduction of Cybersecurity with OSS at Code Europe 2024Hiroshi SHIBATA
I develop the Ruby programming language, RubyGems, and Bundler, which are package managers for Ruby. Today, I will introduce how to enhance the security of your application using open-source software (OSS) examples from Ruby and RubyGems.
The first topic is CVE (Common Vulnerabilities and Exposures). I have published CVEs many times. But what exactly is a CVE? I'll provide a basic understanding of CVEs and explain how to detect and handle vulnerabilities in OSS.
Next, let's discuss package managers. Package managers play a critical role in the OSS ecosystem. I'll explain how to manage library dependencies in your application.
I'll share insights into how the Ruby and RubyGems core team works to keep our ecosystem safe. By the end of this talk, you'll have a better understanding of how to safeguard your code.
Programming Foundation Models with DSPy - Meetup SlidesZilliz
Prompting language models is hard, while programming language models is easy. In this talk, I will discuss the state-of-the-art framework DSPy for programming foundation models with its powerful optimizers and runtime constraint system.
Driving Business Innovation: Latest Generative AI Advancements & Success StorySafe Software
Are you ready to revolutionize how you handle data? Join us for a webinar where we’ll bring you up to speed with the latest advancements in Generative AI technology and discover how leveraging FME with tools from giants like Google Gemini, Amazon, and Microsoft OpenAI can supercharge your workflow efficiency.
During the hour, we’ll take you through:
Guest Speaker Segment with Hannah Barrington: Dive into the world of dynamic real estate marketing with Hannah, the Marketing Manager at Workspace Group. Hear firsthand how their team generates engaging descriptions for thousands of office units by integrating diverse data sources—from PDF floorplans to web pages—using FME transformers, like OpenAIVisionConnector and AnthropicVisionConnector. This use case will show you how GenAI can streamline content creation for marketing across the board.
Ollama Use Case: Learn how Scenario Specialist Dmitri Bagh has utilized Ollama within FME to input data, create custom models, and enhance security protocols. This segment will include demos to illustrate the full capabilities of FME in AI-driven processes.
Custom AI Models: Discover how to leverage FME to build personalized AI models using your data. Whether it’s populating a model with local data for added security or integrating public AI tools, find out how FME facilitates a versatile and secure approach to AI.
We’ll wrap up with a live Q&A session where you can engage with our experts on your specific use cases, and learn more about optimizing your data workflows with AI.
This webinar is ideal for professionals seeking to harness the power of AI within their data management systems while ensuring high levels of customization and security. Whether you're a novice or an expert, gain actionable insights and strategies to elevate your data processes. Join us to see how FME and AI can revolutionize how you work with data!
Digital Marketing Trends in 2024 | Guide for Staying AheadWask
https://www.wask.co/ebooks/digital-marketing-trends-in-2024
Feeling lost in the digital marketing whirlwind of 2024? Technology is changing, consumer habits are evolving, and staying ahead of the curve feels like a never-ending pursuit. This e-book is your compass. Dive into actionable insights to handle the complexities of modern marketing. From hyper-personalization to the power of user-generated content, learn how to build long-term relationships with your audience and unlock the secrets to success in the ever-shifting digital landscape.
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...alexjohnson7307
Predictive maintenance is a proactive approach that anticipates equipment failures before they happen. At the forefront of this innovative strategy is Artificial Intelligence (AI), which brings unprecedented precision and efficiency. AI in predictive maintenance is transforming industries by reducing downtime, minimizing costs, and enhancing productivity.
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUpanagenda
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-und-domino-lizenzkostenreduzierung-in-der-welt-von-dlau/
DLAU und die Lizenzen nach dem CCB- und CCX-Modell sind für viele in der HCL-Community seit letztem Jahr ein heißes Thema. Als Notes- oder Domino-Kunde haben Sie vielleicht mit unerwartet hohen Benutzerzahlen und Lizenzgebühren zu kämpfen. Sie fragen sich vielleicht, wie diese neue Art der Lizenzierung funktioniert und welchen Nutzen sie Ihnen bringt. Vor allem wollen Sie sicherlich Ihr Budget einhalten und Kosten sparen, wo immer möglich. Das verstehen wir und wir möchten Ihnen dabei helfen!
Wir erklären Ihnen, wie Sie häufige Konfigurationsprobleme lösen können, die dazu führen können, dass mehr Benutzer gezählt werden als nötig, und wie Sie überflüssige oder ungenutzte Konten identifizieren und entfernen können, um Geld zu sparen. Es gibt auch einige Ansätze, die zu unnötigen Ausgaben führen können, z. B. wenn ein Personendokument anstelle eines Mail-Ins für geteilte Mailboxen verwendet wird. Wir zeigen Ihnen solche Fälle und deren Lösungen. Und natürlich erklären wir Ihnen das neue Lizenzmodell.
Nehmen Sie an diesem Webinar teil, bei dem HCL-Ambassador Marc Thomas und Gastredner Franz Walder Ihnen diese neue Welt näherbringen. Es vermittelt Ihnen die Tools und das Know-how, um den Überblick zu bewahren. Sie werden in der Lage sein, Ihre Kosten durch eine optimierte Domino-Konfiguration zu reduzieren und auch in Zukunft gering zu halten.
Diese Themen werden behandelt
- Reduzierung der Lizenzkosten durch Auffinden und Beheben von Fehlkonfigurationen und überflüssigen Konten
- Wie funktionieren CCB- und CCX-Lizenzen wirklich?
- Verstehen des DLAU-Tools und wie man es am besten nutzt
- Tipps für häufige Problembereiche, wie z. B. Team-Postfächer, Funktions-/Testbenutzer usw.
- Praxisbeispiele und Best Practices zum sofortigen Umsetzen
5th LF Energy Power Grid Model Meet-up SlidesDanBrown980551
5th Power Grid Model Meet-up
It is with great pleasure that we extend to you an invitation to the 5th Power Grid Model Meet-up, scheduled for 6th June 2024. This event will adopt a hybrid format, allowing participants to join us either through an online Mircosoft Teams session or in person at TU/e located at Den Dolech 2, Eindhoven, Netherlands. The meet-up will be hosted by Eindhoven University of Technology (TU/e), a research university specializing in engineering science & technology.
Power Grid Model
The global energy transition is placing new and unprecedented demands on Distribution System Operators (DSOs). Alongside upgrades to grid capacity, processes such as digitization, capacity optimization, and congestion management are becoming vital for delivering reliable services.
Power Grid Model is an open source project from Linux Foundation Energy and provides a calculation engine that is increasingly essential for DSOs. It offers a standards-based foundation enabling real-time power systems analysis, simulations of electrical power grids, and sophisticated what-if analysis. In addition, it enables in-depth studies and analysis of the electrical power grid’s behavior and performance. This comprehensive model incorporates essential factors such as power generation capacity, electrical losses, voltage levels, power flows, and system stability.
Power Grid Model is currently being applied in a wide variety of use cases, including grid planning, expansion, reliability, and congestion studies. It can also help in analyzing the impact of renewable energy integration, assessing the effects of disturbances or faults, and developing strategies for grid control and optimization.
What to expect
For the upcoming meetup we are organizing, we have an exciting lineup of activities planned:
-Insightful presentations covering two practical applications of the Power Grid Model.
-An update on the latest advancements in Power Grid -Model technology during the first and second quarters of 2024.
-An interactive brainstorming session to discuss and propose new feature requests.
-An opportunity to connect with fellow Power Grid Model enthusiasts and users.
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc
How does your privacy program stack up against your peers? What challenges are privacy teams tackling and prioritizing in 2024?
In the fifth annual Global Privacy Benchmarks Survey, we asked over 1,800 global privacy professionals and business executives to share their perspectives on the current state of privacy inside and outside of their organizations. This year’s report focused on emerging areas of importance for privacy and compliance professionals, including considerations and implications of Artificial Intelligence (AI) technologies, building brand trust, and different approaches for achieving higher privacy competence scores.
See how organizational priorities and strategic approaches to data security and privacy are evolving around the globe.
This webinar will review:
- The top 10 privacy insights from the fifth annual Global Privacy Benchmarks Survey
- The top challenges for privacy leaders, practitioners, and organizations in 2024
- Key themes to consider in developing and maintaining your privacy program
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdfflufftailshop
When it comes to unit testing in the .NET ecosystem, developers have a wide range of options available. Among the most popular choices are NUnit, XUnit, and MSTest. These unit testing frameworks provide essential tools and features to help ensure the quality and reliability of code. However, understanding the differences between these frameworks is crucial for selecting the most suitable one for your projects.
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Generative Adversarial Networks for Robust Medical Image Analysis.pdf
1. UNIVERSIDAD DE LOS ANDES
DEPARTMENT OF BIOMEDICAL ENGINEERING
Generative Adversarial Networks for Robust Medical
Image Analysis
A THESIS PRESENTED FOR THE DEGREE OF MASTER OF SCIENCE
by
Maria Camila ESCOBAR PALOMEQUE
Under the supervision of
Dr. Pablo Andrés ARBELÁEZ
Members of the Qualifying Examination Committee
Dr. Marcela HERNÁNDEZ, Universidad de Los Andes
&
Dr. Mario Andrés VALDERRAMA, Universidad de Los Andes
December 8, 2020
2. Generative Adversarial Networks for Medical Image
Analysis
Maria Camila Escobar
M.Sc. Student
Bogotá, Colombia
mc.escobar11@uniandes.edu.co
Abstract—Deep Learning models have been widely used for
medical imaging tasks such as segmentation. However, these
models tend to have low performances when applied to images
that do not resemble the training dataset distribution. Thus,
the robustness of medical segmentation models can be affected
by external factors such as the quality of the input image, or
by synthetic modifications such as adversarial attacks. In this
work we present two novel approaches to increase robustness
in medical segmentation by using Generative Adversarial Net-
works. First, we present UltraGAN, a method to improve the
robustness to quality of ultrasound segmentation. Second, we
present MedRobGAN, a method to generate adversarial examples
that can later be used in improving the adversarial robustness
for various 3D segmentation tasks. We validate the effectiveness
of our methods through extensive experiments and make a
comprehensive analysis on how Generative Adversarial Networks
can improve medical segmentation tasks.
Index Terms—Deep Learning, Medical segmentation, Genera-
tive Adversarial Networks, Robustness, Image quality, Adversar-
ial Attacks.
I. INTRODUCTION
The analysis and processing of medical images has been
one of the greatest technological advances in medical practice.
Nowadays there are different image acquisition techniques
such as magnetic resonance imaging (MRI), computed axial
tomography (CT), X-rays, ultrasonography, among others.
These techniques are used for various applications, from the
diagnosis of a specific pathology to the planning of surgeries
with a high level of complexity. With the increasing use of
Deep Learning (DL) methods in all types of computer vision
applications, there has been a surge in using these methods for
medical imaging [1]. The biomedical community in general
is accepting the use of these new techniques thanks to the
potential they have to interpret medical images and create
relevant representations in problems such as classification,
detection or segmentation.
Even though DL models are increasingly becoming more
accurate in achieving the task they are trained for, most
of the time they fail when applied to images with slightly
different characteristics. The model’s capability of having a
good performance on images with diverse characteristics is
known as robustness. Because medical datasets usually have
standardized protocols for the acquisition of images, these tend
to only include images taken by a few expert physicians and
most likely with the same acquisition device. DL medical
models are then trained using this data and tend to have a
low performance when evaluated on real-life data from any
physician or a different brand of acquisition device. Thus,
current DL medical models may not be robust to variations
in the quality of the data.
Recently, a new type of robustness assessment, known as ad-
versarial attacks [46], has been studied by the computer vision
community. This assessment is based on adversarial examples,
which are almost imperceptible intensity perturbations to the
original image. However, these perturbations are specifically
designed to trick the model into failure cases. For the task
of medical semantic segmentation, recent studies [6] support
that adversarial examples greatly hurt state-of-the-art models.
These results highlight the importance of developing methods
that are robust to any type of perturbation.
Generative Adversarial Networks (GANs) [21] are a type
of generative models that learn the statistical representation
of the training data. GANs have successfully tackled image-
to-image translation problems [14], [22], [36], including but
not limited to: image colorization [18], super resolution [34],
multi-domain and multimodal mappings [32], and image en-
hancement [17]. In the medical field, several works have
introduced GANs into their approach for tasks that include
data augmentation [15] and image synthesis [7], [8], [35].
GANs are able to learn feature representations from training
images. Thus, the training process of a GAN can be optimized
to learn robust features from the images and generate new
examples than can help for robustness to adversarial attacks
[9] or to classical perturbations in the images [25], [26], [28].
In this work we present two different approaches to increas-
ing robustness in medical segmentation by using GANs. First,
we present UltraGAN [2], a novel framework for ultrasound
image enhancement through adversarial training. Our method
receives as input a low-quality image and performs high-
quality enhancement without compromising the underlying
anatomical structures of the input. The use of the images
generated by UltraGAN improves the robustness to quality
in a state-of-the-art medical segmentation model. Second, we
create a Medical Robust GAN (MedRobGAN) that generates
3D adversarial examples by optimizing the change in appear-
ance of different anatomical structures. Using the volumes
generated by MedRobGAN as additional data for medical
segmentation models can improve the adversarial robustness
3. in some datasets.
II. RELATED WORK
A. Neural Networks
Artificial Neural Networks (ANN) are computational sys-
tems partially inspired by biological neural networks [3]. Their
goal is to receive inputs and find the nonlinear relationship
between them in order to predict the corresponding outputs.
ANN have processing units, called neurons, that receive an
input and multiply it by the neuron weight. Afterwards, these
neurons are connected in different layers that sum up the
output given by each neuron and pass it through a non-
linear activation function to obtain a final output. ANNs have
a different amount of neurons and layers according to the
problem that they are trying to solve. The learning process of
a ANN consists on finding the right weights for each neuron
that will transform the input into the desired output. Eq. 1
describes the output of a neuron, where xi is the activation of
the previous neuron, wi is the weight that the current neuron
gives to each of the xi, b is an additional bias given to the
entire output of the current neuron and f(z) = is a non-linear
activation function. The final output of the current neuron is
y.
y = f
X
i
xiwi + b
(1)
For the task of medical image segmentation, the input of
the ANN is usually a 2D or 3D matrix with the information
of the image or volume and the output is a segmentation of a
region of interest from the input. The learning process of the
network consists on comparing the output with the groundtruth
information and modifying the individual weights and biases
of the neurons in order to get closer to the desired output. This
process is done iteratively and the final results depends heavily
on choosing the appropriate loss function for comparing the
ANN’s output with the groundtruth.
B. Adversarial attacks
The result given by an ANN can be extremely sensitive
to small modifications in the input image. These changes,
known as adversarial perturbations [50], are imperceptible by
the human eye but are able to fool top-performing systems
by dropping their performance virtually to 0 [39]. There is an
increasing amount of works regarding adversarial attacks and
defenses for diverse tasks [4], [5], [37], [42], [46], [47], [50],
[52].
Due to their direct impact in human health, medical image
systems are of special importance to research in adversarial
robustness. There are several works studying robustness in the
medical domain for tasks such as image classification [45]
and image segmentation [38], [41], [43], [44], [48]. Recently,
Daza et al. [6] developed a comprehensive framework for
adversarial robustness in the task of 3D medical segmentation.
Their approach includes a set of possible attacks that can be
done to reduce the performance of a 3D segmentation model
as well as a new model for general medical segmentation that
is robust to adversarial perturbations. For our Medical Robust
GAN we use the implementation of the attacks and the 3D
segmentation model from [6].
C. Generative Adversarial Networks
GANs consist of a generator, that is in charge of produc-
ing new images, and a discriminator, that is in charge of
discerning between real data from the existing database and
new data created by the generator. The learning process of
a GAN consists on a min-max game between the generator
and the discriminator, where the generator tries to fool the
discriminator by producing realistic-looking images and the
discriminator tries to identify the synthetic images created by
the generator.
For the task of ultrasound quality robustness, some au-
tomated methods have been developed for image enhance-
ment [19], [23], [24], [31]. Liao et al. [28] proposed a quality
transfer network to enhance ultrasound images. The algorithm
was tested in echo view classification, showing that quality
transfer improves the performance. Additionally, Lartaud et
al. [26] trained a convolutional network for data augmentation
by changing the quality of the images to create contrast
and non-contrast images for segmentation. The augmented
data improved their segmentation method. On the same note,
Jafari et al. [25] trained a model to transform quality between
ultrasound images. The approach introduced a segmentation
network in the training of the GAN to provide an anatomi-
cal constraint added by the segmentation task. Nevertheless,
these methods were developed and evaluated on private data,
complicating the possibility of a direct comparison.
Finally, for the task of medical segmentation adversarial
robustness, Chen et al. [16] combined a GAN with a Varia-
tional Autoencoder to generate images with deformations and
appearance changes that can be used to attack medical segmen-
tation models. The generated adversarial examples included
geometrical deformations as well as intensity variations. They
were able to attack a 2D medical segmentation network.
However, they did not use the generated images to improve
the robustness of their segmentation model. In contrast, our
Medical Robust GAN is able to generate 3D adversarial attacks
and then use the generated data to increase the robustness of
the segmentation models.
III. METHOD
In this section we explain our two approaches for gen-
erating images that can increase the robustness of medical
segmentation methods. First we explain UltraGAN, a method
for improving quality robustness, and then MedRobGAN, a
method for improving adversarial robustness.
A. UltraGAN
Our method named UltraGAN consists of a Generative
Adversarial Network designed to enhance the quality of ul-
trasound images without compromising underlying anatomical
information.
2
4. Generator
Enhanced
Original Reconstruction
real/fake
Enhanced
Segmentation
channel-wise
concatenation
Discriminator
Fig. 1. Overview of our generation scheme for UltraGAN. We add a frequency consistency loss to preserve fine details and coarse structures. We concatenate
the segmentation map along with the input image for the discriminator to classify as real or enhanced. This particular case corresponds to an enhanced input.
1) Problem formulation: We have a set of low-quality
ultrasounds {li}
N
i=1 ∈ L with a data distribution l ∼ pdata(l)
and a set of high-quality ultrasounds {hi}
N
i=1 ∈ H with a
data distribution h ∼ pdata(h). Our main objective is to learn
mapping functions that translate from low to high-quality
domain and vice versa. Thus, we have a generator for each
domain translation GH : L → H and GL : H → L. We also
have two discriminators: DH distinguishes between real high-
quality images hi and generated high-quality images GH(li),
and DL distinguishes between real low-quality images li and
generated low-quality images GL(hi).
We want to preserve the structural information from the
original image. Therefore, we include the segmentation of
the anatomical regions of interest for the high-quality sh or
for the low-quality sl ultrasound as additional input for the
discriminators.
2) Model: Our generator (G) builds upon the CycleGAN
architecture [36] which is the most common used frame-
work for Image-to-Image translation. CycleGAN consists of
down-sampling layers, followed by residual blocks and up-
sampling layers. For the discriminator (D), we build upon
PatchGAN [22], [36] that breaks down the image into different
patches and then learns to predict if those patches are real or
generated. Our discriminator has two inputs: the ultrasound
image (whether real or generated) and the corresponding
segmentation of the anatomical regions of interest.
3) Loss functions: Finding the appropriate loss function
is a critical task for image generation because the problem
must have enough constraints to create images similar to the
desired domain. For UltraGAN, we use an identity loss and we
alter the traditional adversarial and cycle consistency losses to
create an anatomically coherent adversarial loss and frequency
cycle consistency losses.
Anatomically Coherent Adversarial Loss: The goal of
the adversarial loss is to make the generated images resemble
the distribution of the real dataset. Inspired by the idea of
conditional GANs [29] and pix2pix [22], we modify the
adversarial loss to include as input the segmentation of the
anatomical regions of interest. For the high-quality translation
networks GH and DH our anatomically coherent adversarial
loss is defined as:
Ladv (GH, DH) = Eh∼pdata(h) [log DH(h, sh)]
+ El∼pdata(l) [log (1 − DH(GH(l), sl)]
(2)
This loss helps the networks to learn the underlying relation-
ship between the anatomical regions of interest and the struc-
tures in the generated image. Furthermore, the segmentation
is not necessary at test time, since we only use the generator.
In our training process we also consider the adversarial loss
for low-quality translation GL and DL.
Frequency Cycle Consistency: The cycle consistency
loss [36] is one of the most important losses in image-to-image
translation because it allows training without paired images.
However, the cycle consistency constraint is a pixel-wise L1-
norm between the original image (l) and the reconstruction
(GL(GH(l))), which enforces the output to have exactly the
same intensities. Yet, during the process of ultrasound quality
enhancement, it is more useful to think of the image in terms
of frequency rather than intensity [20]. As it can be seen
in Fig. 2, low frequencies contain the coarse information of
an image, while high frequencies contain the fine details.
With this concept in mind, we create two types of frequency
consistency losses to improve quality enhancement.
Fig. 2. Frequency extraction of ultrasound image. The low frequency image
contains the coarse anatomical structures while the high frequency image
contains detailed information of the division between the organs.
During high-quality translation, we aim to preserve the
anatomical information present in the low frequencies of the
original image. To extract low frequencies, we pass the images
through a Gaussian pyramid [30] φ at K = 3 scales, then
3
5. Fig. 3. Overview of the adversarial optimization process in MedRobGAN. Both the original image and the groundtruth are inputs to the GAN.
compute the L1-norm between the structural information of
the original and the generated image (Eq. 3). Our generators
transfer image details of the high-quality domain in the form
of high frequencies. Therefore, we obtain those frequencies
through a Laplacian pyramid [30] γ at K = 3 scales and
calculate the L1-norm between the high frequencies of the
original image and the high frequencies of the reconstruction
(Eq. 4). The loss concept is better illustrated in Fig. 1.
Llf (GH) =
K
X
k=1
kφk(l) − φk (GH(l))k1 (3)
Lhf (GH, GL) =
K
X
k=1
kγk(l) − γk (GL(GH(l)))k1 (4)
Identity Loss: The identity loss is particularly useful for
the application of quality enhancement in real-life clinical
scenarios because it ensures that the generator does not modify
images from the same domain. In real-life applications we
will not have a quality label for each ultrasound image but
we would still want to perform quality enhancement without
damaging the images that already have a high-quality. We
achieve this by using a L1-norm between the original high-
quality image and the same image after going through the
quality enhancement process.
Lidt = kh − GH(h)k1 (5)
Overall Loss: Our overall loss is defined as the weighted
sum of the losses in both pathways H → L and L → H, where
each λ represents the relative importance of each loss function
in the system. Even though we train two generators and two
discriminators, at inference time we only use the generator
GH since our goal is to improve the quality of all ultrasound
images.
LUltraGAN = λadvLadv + λlf Llf + λhf Lhf + λidtLidt. (6)
B. Medical Robust GAN
With our Medical Robust GAN (MedRobGAN) we aim to
generate adversarial examples that are particularly challenging
for the segmentation network. These hard examples can be
later used for finetuning the segmentation network with the
expectation of improving the overall robustness. Our method
is divided into two main parts: generation and adversarial
optimization.
1) Generation: In this stage we adapt the state-of-the-art
GAN for 2D image generation: SEAN [10], in order to make
it suitable for 3D volume generation. Because 3D volumes
take more memory space than 2D images, we have to reduce
the amount of parameters in SEAN for it to be feasible to
train. We keep the same training scheme and loss functions as
the original SEAN model with the exception of the perceptual
loss that we do not implement. The principal advantage of
using SEAN as our baseline is that it allows us to control the
style of different parts of the volume if there is a segmentation
mask to go along with it. Thus, for medical applications we
are able to modify only the part of the volume that includes
a certain organ or a tumor and we can copy the styles from
one volume to another. This style manipulation is achieved
through modulation parameters that modify the mean and the
variance of each pixel by using the segmentation information
after batch normalization [13]. The entire normalization layer
[10] can be seen in Eq. 7 where x is the activation of
the previous convolutional layer, η is an additional noise to
increase variability, γ and β are the modulation parameters,
and µc and σc are the channel-wise mean and variance used
for batch normalization.
γ
(x + η) + µc
σc
+ β (7)
2) Adversarial optimization: For the adversarial optimiza-
tion stage we use the generator of our Robust Medical GAN
with the already trained weights (U) and a pretrained seg-
mentation model (V). As we mention before, a critical step
for volume generation based on styles are the modulation
parameters in the normalization block. Thus, we aim to find,
through adversarial optimization, the value of η, γ and β for
U that will generate a volume that is hard to segment by V.
The main advantage of optimizing modulation parameters is
that we can modify an object’s appearance while keeping the
original pose. For example, we can modify a liver by changing
the style to something less identifiable by V, but we retain the
spatial and geometrical information so that the generated organ
does not deviate from the original class. Fig. 3 illustrates the
adversarial optimization process.
4
6. To find the optimal η, γ and β we use Projected Gradient
Descent (PGD) [46] with the steepest descent under the L∞-
norm. The process is shown in Eq. 9, we start from a noise
δ that is added to each of the three parameters, and we pass
the original volume (j) through the generator U. The output
of U is a new volume (z) with a different style given by
γ + δ, β + δ and η + δ. Then, we calculate the loss function
between the groundtruth segmentation (s) and the output of
V(z). Since our goal is to generate the volume that confuses
V the most, we move δ towards the direction that maximizes
the loss, which is equivalent to moving it in the direction
of the sign, and increase it by a factor of α. Additionally,
to control the effect of δ we include the standard constraint
= 8/255, meaning that δ cannot be higher than or lower
than −. This optimization process is done iteratively for k
steps to find the hardest example possible. The more steps we
add to the adversarial optimization, the harder it is for V to
segment z but there is also a higher probability of generating
a volume with an unrelated style that would no longer be
useful for training. This problem happens when the adversarial
optimization finds modulation parameters that result in a hard
example but are visually unrealistic or very different from
the original dataset. Thus, when we use these images for
finetuning, it would confuse the network rather than help with
the adversarial robustness. We have to find a trade-off between
how hard the example is and how real it looks.
z = U(j, s, δ) (8)
δ = δ + α × sign(Loss(V(z), s)) (9)
IV. EXPERIMENTS
A. UltraGAN
1) Dataset: To validate UltraGAN, we use the publicly
available “Cardiac Acquisitions for Multi-structure Ultrasound
Segmentation” (CAMUS) dataset [27]. The CAMUS dataset
contains 2D Ultrasound images and multi-structure segmenta-
tions of 450 patients. Each of the ultrasound images in the CA-
MUS dataset comes with a quality-assessment given by expert
physicians. Besides, the CAMUS dataset includes pathological
patients that have different left ventricle ejection fractions,
making it a realistic problem in which not all the anatomical
structures are perfect. The task in the CAMUS dataset is
to segment the left ventricular endocardium (LVEndo), left
ventricular epicardium (LVEpi) and left atrium (LA) in two
chamber (2CH) and four chamber (4CH) views for End of
Diastole (ED) and End of Systole (ES).
2) Experimental Setup: We train UltraGAN with 80% of
the images and evaluate on the remaining 20%. In the dataset,
each image can be labeled as high-quality, medium-quality
or low-quality. However, for our experiments we consider
medium-quality images in the same group as low-quality im-
ages. Thus, allowing us to be more strict during the ultrasound
enhancement process. To ensure that every component of our
networks has a relevant contribution, we enhance low-quality
ultrasound images using three variants of our system for the
ablation experiments:
TABLE I
CHARACTERISTICS OF THE CAMUS DATASET
Characteristic Number of patients
High-quality 198
Medium/Low-quality 252
EF within standard range 141
EF lower than 45% 222
EF higher than 55% 87
• Without anatomically coherent adversarial loss.
• Without frequency cycle consistency losses.
• Without anatomically coherent or frequency cycle con-
sistency losses (CycleGAN).
Nevertheless, the evaluation of image quality in an unpaired
setup is a subjective process and performing perceptual stud-
ies would require expert physicians spending their time in
analyzing which ultrasound images were correctly enhanced.
However, we make the assumption that, as in real-life, it is
easier to identify anatomical structures in high-quality images
than in low-quality images. Therefore, we use multi-structure
segmentation as a down-stream quantitative metric.
We train an U-Net model [33] for segmentation and evaluate
using 10 fold cross-validation splits of the CAMUS dataset as
done in [27]. Then, we use UltraGAN to enhance the quality
of all the training images and train the same U-Net with the
original images as well as the enhanced augmentation. We
compare the segmentation results by using the Dice score
between the groundtruth (s) and the predicted segmentation
(p) for each anatomical structure.
Dice =
2|s ∩ p|
|s| + |p|
× 100 (10)
B. Medical Robust GAN
1) Dataset: Since our goal is to generate adversarial exam-
ples that can increase the robustness of a medical segmentation
model, we evaluate our framework on the most challenging di-
agnostic problems. This includes seven tasks from the Medical
Segmentation Decathlon (MSD) [49], which is the standard
framework for medical image segmentation, and the Kidney
and Kidney Tumor Segmentation dataset (KiTS) [11]. Each
dataset includes 3D volumes (MRI or CT) and a segmentation
with the desired organs and lesions.
TABLE II
CHARACTERISTICS OF THE 8 CHOSEN DATASETS TO ASSESS
ADVERSARIAL ROBUSTNESS.
Dataset Modality Target Training volumes Validation volumes
Heart MRI Left Atrium 16 4
Liver CT Liver and tumor 94 37
Hippocampus MRI Hippocampus head and body 208 52
Pancreas CT Pancreas and tumor 225 57
Hepatic Vessel CT Hepatic vessels and tumor 212 91
Spleen CT Spleen 33 8
Colon CT Colon cancer primaties 88 38
KiTS CT Kidney and tumor 168 42
5
7. Low Quality
Images
Enhanced
Images
Fig. 4. Qualitative comparison of the low-quality and enhanced images using UltraGAN. Our method is able to enhance ultrasound images, improving the
interpretability of the heart structures regardless of the view.
2) Experimental Setup: The adversarial examples that our
Medical Robust GAN generates are used as additional data for
finetuning ROG [6], a state-of-the-art medical segmentation
network. The motivation for doing this finetuning is that it
should help the segmentation network to learn more discrim-
inative features and therefore be more robust to adversarial
perturbations. Afterwards, we assess the robustness of ROG
with and without the additional finetuning stage. For a better
benchmarking, we also compare our method with the Free
Adversarial Training (FreeAT) defense for ROG as shown in
[6]. For the adversarial attack we use AutoPGD-CE [6] that
operates by maximizing the Cross Entropy loss [12] averaged
across all spatial locations. The concept behind this attack
is the same as shown in section III-B2 and we perform
experiments for 5, 10 and 20 iterations. We also evaluate
the performance of the standard and robust methods under
no attack (0 iterations) to obtain a complete framework. The
metric for evaluating the performance of each method is the
Dice Score.
Having 8 different datasets allows us to explore the potential
of our Medical Robust GAN under different circumstances.
For each dataset we train a GAN, perform adversarial opti-
mization to generate hard examples and finetune ROG. We
keep the original train and validation division and use the
pretrained weights from [6].
V. RESULTS
A. UltraGAN
1) Image Enhancement: UltraGAN provides an image
quality enhancement that is noticeable even for untrained eyes.
Fig. 4 shows the comparison between low-quality images and
the enhanced images we generate. In the enhanced images,
the heart’s chambers are easier to recognize because they have
sharper boundaries. These results are consistent for both 2CH
and 4CH views.
Furthermore, in Fig. 5 we demonstrate that UltraGAN
generates better high-quality images than the traditional Cy-
cleGAN. For our ablation experiment in Fig. 6 we see the
effect that removing one of our components has on quality
enhancement. The images enhanced without the anatomically
coherent adversarial loss maintain finer details, yet the system
tends to hallucinate high frequencies in the left part of the
image. Conversely, if we do not use the frequency cycle
consistency losses, the structure is preserved but there is not
a well definition of heart regions. Overall, with UltraGAN we
are able to create an image quality enhancement that takes into
account frequency and structural information.
CycleGAN
results
UltraGAN
results
Low Quality
Images
Fig. 5. Qualitative comparison between CycleGAN results and UltraGAN.
The images generated by CycleGAN are perceptually similar to the original
low-quality images. In contrast, images enhanced by UltraGAN show a clear
difference between anatomical structures.
No Frequency
consistency
Enhanced Training
No Anatomical
coherence
No Anatomical
coherence and
No Frequency
consistency
Original
Poor Quality
Fig. 6. Ablation examples of UltraGAN. We show the results obtained for
every stage of the generation.
2) Multi-structure segmentation: In Fig. 7 we show that
some of the segmentations obtained by using the standard data
have artifacts, while training with UltraGAN-enhanced images
improves the resulting segmentation. Also, Table III shows the
Dice Scores for this experiment. Here we confirm that for each
of the structures present in the ultrasound image, augmenting
the training data with UltraGAN improves the segmentation
results. This improvement is also consistent across all of the
image qualities, suggesting that the baseline with enhanced
training data preserves correctly the anatomical structures
6
8. TABLE III
SEGMENTATION RESULTS FOR 10-FOLD CROSS-VALIDATION SET COMPARING STANDARD TRAINING VS TRAINING WITH ULTRAGAN.
Method
High (%) Medium (%) Low (%)
LVEndo LVEpi LA LVEndo LVEpi LA LVEndo LVEpi LA
Baseline 93.07 86.61 88.99 92.02 85.32 88.13 90.76 83.10 87.52
Our method 93.78 87.38 89.48 92.66 86.20 88.38 91.55 83.75 87.84
Groundtruth Baseline Training Enhanced Training Groundtruth Baseline Training Enhanced Training
Fig. 7. Qualitative results for heart segmentation in the CAMUS dataset by using our enhanced images as data augmentation in the training stage. We present
two different test examples showing the groundtruth (columns 1 and 4), the baseline results (columns 2 and 5) and the improved segmentation (columns 3
and 6).
TABLE IV
SEGMENTATION RESULTS FOR 10-FOLD CROSS-VALIDATION COMPARING
THE STATE-OF-THE-ART VS. OUR QUALITY ENHANCED TRAINING.
Image quality Method
ED (%) ES (%)
LVEndo LVEpi LVEndo LVEpi
High Ours 94.40±0.7 86.54±1.2 92.04±1.1 87.05±1.4
+ Medium Leclerc et al. 93.90±4.3 95.40 ±2.3 91.60±6.1 94.50±3.9
Low
Ours 93.00±1.1 83.57±1.9 90.10±1.3 83.93±2.7
Leclerc et al. 92.10±3.7 94.70±2.3 89.80±5.7 93.67±3.2
present in the ultrasound images. We evaluate separately
the segmentation of our enhanced images in a subset of the
CAMUS dataset consisting of patients at pathological risk with
a left ventricle ejection fraction lower than 45%. We find that,
for pathological cases, the average Dice score (89.5%) is as
good as for healthy patients (89.7%).
Table IV shows the comparison between the state-of-the-
art method in the CAMUS dataset and our quality enhanced
method for the High+Medium and Low-qualities in the 10-fold
cross-validation sets. We do not include the comparison for
Left atrium segmentation since the authors do not report their
performance on that class. [27] uses a modified U-Net network
that has more parameters than the U-Net we used. Here we
demonstrate that enhancing the quality of training images
we are able to improve the robustness of the segmentation
model towards different quality ultrasounds. Also, even with
a simpler network with less amount of parameters, our robust
model is able to outperform state-of-the-art approaches in left
ventricular endocardium segmentation, and obtain competitive
results in left ventricular epicardium segmentation. Thus,
demonstrating that the inclusion of quality enhanced images
during training can benefit a model’s generalization.
B. Medical Robust GAN
Fig. 8 shows the performance under adversarial attack of
different variants of the medical segmentation model for each
task of the 8 datasets. Each graph includes the performance
of the normal segmentation model (blue line) and three
lines corresponding to the performance of the same model
finetuned with different adversarial examples generated by
MedRobGAN. The three versions of adversarial examples
were generated through the optimization explained in section
III-B2 by setting the amount of iterations k to 5 (orange line),
10 (green line) and 20 (red line). The x axis of the graphs in
Fig. 8 denotes the number of iterations done in the adversarial
attacks. Analogous to the optimization stage, a higher number
of attack iterations represent a stronger attack to the network.
Thus, the performance of the normal segmentation network
drops when the attack iterations increase. The goal of using
adversarial examples during the finetuning is to increase the
adversarial robustness of the model which can be understood
in the graph as retaining a high Dice score throughout the
attack iterations, i.e. the dashed lines should be higher than
the solid blue line.
We observe that the effectiveness of finetuning with ad-
versarial examples varies greatly depending on the dataset.
For hippocampus, pancreas, hepatic vessel and colon there is
no advantage in using our adversarial examples. However, for
liver, spleen, KiTs and heart there is a significant increase
in robustness when finetuning with adversarial examples. An-
other observation we find is that there is a lack of consistency
in the ranking of the numbers of iterations for the adversarial
optimization. For example, for the liver dataset, the best
performing model was finetuned with 10 iterations while the
best performing model for the spleen dataset is finetuned with
5 iterations.
7
9. 0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Spleen
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Pancreas Organ
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Pancreas Lesion
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Liver Organ
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Liver Lesion
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
KiTS Organ
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
KiTS Lesion
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Heart
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Colon
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Hippocampus Body
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Hippocampus Head
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Hepatic Vessel Organ
Normal
Adv5
Adv10
Adv20
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Hepatic Vessel Lesion
Normal
Adv5
Adv10
Adv20
Fig. 8. Adversarial robustness for each task of the 8 datasets. We compare the pretrained ROG [6] that only has clean images (blue line) with the finetuned
ROG with 5 (orange line), 10 (green line) and 20 (red line) iterations. We show the results across different attack iterations of APGD-CE.
8
10. Goundtruth
Prediction - clean image Prediction - adversarial image
ROG + MedRobGAN
ROG ROG + MedRobGAN
ROG
Fig. 9. Qualitative results of adversarial robustness for Spleen (top row) and heart (bottom row). Using MedRobGAN for data augmentation significantly
increases the accuracy of the prediction in adversarial images.
We report qualitative results in Fig. 9, the top row corre-
sponds to spleen and the bottom row corresponds to heart (left
atrium). Overall, we observe that the segmentation generated
by ROG in the adversarial image is completely inaccurate.
However, using MedRobGAN as data augmentation has a
significant improvement in the segmentation of the attacked
image. Additionally, for the clean image, both ROG and
ROG+MedRobGAN have comparable results.
We also perform a comparison between the segmentation
model trained with a standard adversarial defense known as
Free Adversarial training (+FreeAT) [6] and our best adver-
sarial examples (+MedRobGAN). Fig. 10 shows the results
of the comparison for our best-performing datasets. We find
that the adversarial examples created by our MedRobGAN
improve the robustness of the model for liver segmentation
in a greater extent than FreeAT. However, for the remaining
3 datasets, using FreeAT gives a better performance than
using our MedRobGAN. These results suggest that there is
still room for improvement in finding the adequate training
hyperparameters for the GAN and the ideal strength and
number of iterations for the adversarial optimization. However,
this work is the first time that a GAN framework is used
for increasing the robustness of generic medical segmentation
and our results so far prove that it is possible to achieve an
improvement.
VI. CONCLUSION
In this work we present two novel methods that use GANs
to tackle the robustness of medical segmentation models:
• First, we present UltraGAN, a method designed for
quality enhancement of ultrasound images. We achieve
enhancement of 2D echocardiography images without
compromising the anatomical structures. By using multi-
structure segmentation as a downstream task we demon-
strate that augmenting the training data with enhanced
images improves the robustness. We expect UltraGAN to
be useful in other ultrasound problems to push forward
automated ultrasound analysis.
• Second, we present MedRobGAN, a method that inte-
grates adversarial optimization into the GAN framework
to create adversarial examples that are semantically hard
for a medical segmentation network. We evaluate our
framework in 8 diverse datasets for medical segmentation.
Using the adversarial examples for training achieves
competitive results in adversarial robustness for half
of the datasets. This results are promising in order to
keep exploring the potential of GAN augmentation in
adversarial robustness.
ACKNOWLEDGMENTS
This thesis is done as part of an ongoing project with Angela
Castillo, I am deeply thankful for her immense contributions.
I would also like to thank professor Pablo Arbeláez for his
guidance during this project and throughout my development
as a researcher. Finally, I thank the Biomedical Computer
Vision group for their advice and support.
REFERENCES
[1] Litjens, G. , Kooi, T. , Bejnordi, B.E. , Setio, A.A.A , Ciompi, F. ,
Ghafoorian, M. , Van Der Laak, J.A. , Van Ginneken, B. , Sánchez,
C.I.: A survey on deep learning in medical image analysis. In: Medical
image analysis vol 42, pp 60-88. Elsevier (2017)
[2] Escobar, M., Castillo, A., Romero, A., Arbeláez, P.: UltraGAN: Ul-
trasound Enhancement Through Adversarial Generation. In International
Workshop on Simulation and Synthesis in Medical Imaging (pp. 120-
130). Springer, Cham. (2020)
[3] LeCun et al., ”Backpropagation Applied to Handwritten Zip Code
Recognition,” Neural Computation, 1, pp. 541–551, 1989.
9
11. 0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Spleen
Normal
+MedRobGAN
+FreeAT
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Liver Organ
Normal
+MedRobGAN
+FreeAT
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Liver Lesion
Normal
+MedRobGAN
+FreeAT
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
KiTS Organ
Normal
+MedRobGAN
+FreeAT
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
KiTS Lesion
Normal
+MedRobGAN
+FreeAT
0 5 10 20
Attack iterations
0.0
0.2
0.4
0.6
0.8
1.0
Dice
Score
Heart
Normal
+MedRobGAN
+FreeAT
Fig. 10. Comparison of adversarial robustness for our best-performing datasets. We compare the pretrained ROG model that only has clean images with two
different defense versions of ROG: finetuned with the adversarial examples generated by MedRobGAN (red line) and the FreeAT presented in [6].
[4] Pérez, J. C., Alfarra, M., Jeanneret, G., Bibi, A., Thabet, A., Ghanem, B.,
Arbeláez, P.: Gabor Layers Enhance Network Robustness. In European
Conference on Computer Vision (pp. 450-466). Springer, Cham.(2020)
[5] Alfarra, M., Pérez, J. C., Bibi, A., Thabet, A., Arbeláez, P., Ghanem,
B.: ClustTR: Clustering Training for Robustness. arXiv preprint
arXiv:2006.07682.(2020)
[6] Daza, L. , Pérez, J.C, Gómez C., Arbeláez P.: Towards Robust General
Medical Image Segmentation. Submitted to CVPR2021
[7] Abdi, A.H., Jafari, M.H., Fels, S., Tsang, T., Abolmaesumi, P.: A
study into echocardiography view conversion. In: Workshop of Medical
Imaging Meets NeurIPS (2019)
[8] Abdi, A.H., Tsang, T., Abolmaesumi, P.: Gan-enhanced conditional
echocardiogram generation. In: Workshop of Medical Imaging Meets
NeurIPS (2019)
[9] Shetty, R. , Fritz, M. , Schiele, B.: Towards automated testing and
robustification by semantic adversarial data generation. In: European
Conference on Computer Vision (ECCV) (2020)
[10] Zhu, P., Abdal, R., Qin, Y., Wonka, P.: SEAN: Image Synthesis
with Semantic Region-Adaptive Normalization. : Proceedings of the
IEEE/CVF Conference on Computer Vision and Pattern Recognition
(pp. 5104-5113) (2020).
[11] Heller, N., Isensee, F., Maier-Hein, K. H., Hou, X., Xie, C., Li, F., ...
Yao, G.: The state of the art in kidney and kidney tumor segmentation
in contrast-enhanced CT imaging: Results of the KiTS19 Challenge.
Medical Image Analysis, 67, 101821 (2019)
[12] Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training
deep neural networks with noisy labels. Advances in neural information
processing systems, 31, 8778-8788 (2018)
[13] Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep
network training by reducing internal covariate shift. arXiv preprint
arXiv:1502.03167 (2015)
[14] Translation, M. I.: StarGAN: Unified Generative Adversarial Networks
for Multi-Domain Image-to-Image Translation. (2017)
[15] Abhishek, K., Hamarneh, G.: Mask2lesion: Mask-constrained adversar-
ial skin lesion image synthesis. In: Burgos, N., Gooya, A., Svoboda, D.
(eds.) Simulation and Synthesis in Medical Imaging. pp. 71–80. Springer
International Publishing, Cham (2019)
[16] Chen, L., Bentley, P., Mori, K., Misawa, K., Fujiwara, M., Rueckert, D.:
Intelligent image synthesis to attack a segmentation cnn using adversarial
learning. In: Burgos, N., Gooya, A., Svoboda, D. (eds.) Simulation
and Synthesis in Medical Imaging. pp. 90–99. Springer International
Publishing, Cham (2019)
[17] Chen, Y.S., Wang, Y.C., Kao, M.H., Chuang, Y.Y.: Deep photo enhancer:
Unpaired learning for image enhancement from photographs with gans.
In: Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition. pp. 6306–6314 (2018)
[18] Deshpande, A., Lu, J., Yeh, M.C., Jin Chong, M., Forsyth, D.: Learning
diverse image colorization. In: Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition. pp. 6837–6845 (2017)
[19] Duarte-Salazar, C.A., Castro-Ospina, A.E., Becerra, M.A., Delgado-
Trejos, E.: Speckle noise reduction in ultrasound images for improving
the metrological evaluation of biomedical applications: An overview.
IEEE Access 8, 15983–15999 (2020)
[20] Fritsche, M., Gu, S., Timofte, R.: Frequency separation for real-world
super-resolution. ICCV Workshop (2019)
[21] Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley,
D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets.
In: Advances in neural information processing systems. pp. 2672–2680
(2014)
[22] Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation
with conditional adversarial networks. In: Computer Vision and Pattern
Recognition (CVPR), 2017 IEEE Conference on (2017)
[23] Jafari, M.H., Girgis, H., Abdi, A.H., Liao, Z., Pesteie, M., Rohling,
R., Gin, K., Tsang, T., Abolmaesumi, P.: Semi-supervised learning for
cardiac left ventricle segmentation using conditional deep generative
models as prior. In: 2019 IEEE 16th International Symposium on
Biomedical Imaging (ISBI 2019). pp. 649–652. IEEE (2019)
[24] Jafari, M.H., Girgis, H., Van Woudenberg, N., Moulson, N., Luong, C.,
Fung, A., Balthazaar, S., Jue, J., Tsang, M., Nair, P., et al.: Cardiac point-
of-care to cart-based ultrasound translation using constrained cyclegan.
International Journal of Computer Assisted Radiology and Surgery pp.
1–10 (2020)
[25] Jafari, M.H., Liao, Z., Girgis, H., Pesteie, M., Rohling, R., Gin, K.,
Tsang, T., Abolmaesumi, P.: Echocardiography segmentation by quality
translation using anatomically constrained cyclegan. In: Medical Image
Computing and Computer Assisted Intervention – MICCAI 2019. pp.
655–663. Springer International Publishing, Cham (2019)
[26] Lartaud, P.J., Rouchaud, A., Rouet, J.M., Nempont, O., Boussel, L.:
10
12. Spectral ct based training dataset generation and augmentation for
conventional ct vascular segmentation. In: International Conference on
Medical Image Computing and Computer-Assisted Intervention. pp.
768–775. Springer (2019)
[27] Leclerc, S., Smistad, E., Pedrosa, J., Østvik, A., Cervenansky, F.,
Espinosa, F., Espeland, T., Berg, E.A.R., Jodoin, P.M., Grenier, T., et al.:
Deep learning for segmentation using an open large-scale dataset in 2d
echocardiography. IEEE transactions on medical imaging 38(9), 2198–
2210 (2019)
[28] Liao, Z., Jafari, M.H., Girgis, H., Gin, K., Rohling, R., Abolmaesumi,
P., Tsang, T.: Echocardiography view classification using quality transfer
star generative adversarial networks. In: International Conference on
Medical Image Computing and Computer-Assisted Intervention. pp.
687–695. Springer (2019)
[29] Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv
preprint arXiv:1411.1784 (2014)
[30] Oliva, A., Torralba, A., Schyns, P.G.: Hybrid images. ACM Transactions
on Graphics (TOG) 25(3), 527–532 (2006)
[31] Ortiz, S.H.C., Chiu, T., Fox, M.D.: Ultrasound image enhancement: A
review. Biomedical Signal Processing and Control 7(5), 419–428 (2012)
[32] Romero, A., Arbeláez, P., Van Gool, L., Timofte, R.: Smit: Stochastic
multi-label image-to-image translation. In Proceedings of the IEEE
International Conference on Computer Vision Workshops (2019)
[33] Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks
for biomedical image segmentation. In: International Conference on
Medical image computing and computer-assisted intervention. pp. 234–
241. Springer (2015)
[34] Wang, X., Chan, K.C., Yu, K., Dong, C., Loy, C.C.: Edvr: Video
restoration with enhanced deformable convolutional networks. In: The
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Workshops (June 2019)
[35] Yang, H., Sun, J., Carass, A., Zhao, C., Lee, J., Xu, Z., Prince, J.:
Unpaired brain mr-to-ct synthesis using a structure-constrained cyclegan.
In: Deep Learning in Medical Image Analysis and Multimodal Learning
for Clinical Decision Support. pp. 174–182. Springer International
Publishing, Cham (2018)
[36] Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image
translation using cycle-consistent adversarial networkss. In: Computer
Vision (ICCV), 2017 IEEE International Conference on (2017)
[37] Anurag Arnab, Ondrej Miksik, and Philip HS Torr. On the robustness
of semantic segmentation models to adversarial attacks. In CVPR, 2018.
[38] Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel,
Jonas Rauber, Dimitris Tsipras, Ian Goodfellow, Aleksander Madry, and
Alexey Kurakin. On evaluating adversarial robustness. arXiv preprint
arXiv:1902.06705, 2019.
[39] Nicholas Carlini and David Wagner. Towards evaluating the robustness
of neural networks. In 2017 IEEE Symposium on Security and Privacy
(SP), 2017.
[40] Francesco Croce and Matthias Hein. Reliable evaluation of adversarial
robustness with an ensemble of diverse parameter-free attacks. In
International Conference on Machine Learning (ICML), 2020.
[41] Yinpeng Dong, Qi-An Fu, Xiao Yang, Tianyu Pang, Hang Su, Zihao
Xiao, and Jun Zhu. Benchmarking adversarial robustness on image
classification. In CVPR, 2020.
[42] Jan Hendrik Metzen, Mummadi Chaithanya Kumar, Thomas Brox, and
Volker Fischer. Universal adversarial perturbations against semantic
image segmentation. In ICCV, 2017.
[43] Yingwei Li, Zhuotun Zhu, Yuyin Zhou, Yingda Xia, Wei Shen, Elliot K
Fishman, and Alan L Yuille. Volumetric medical image segmentation: A
3d deep coarse-to-fine framework and its adversarial examples. In Deep
Learning and Convolutional Neural Networks for Medical Imaging and
Clinical Informatics. 2019.
[44] Qi Liu, Han Jiang, Tao Liu, Zihao Liu, Sicheng Li, Wujie Wen, and Yiyu
Shi. Defending deep learning-based biomedical image segmentation
from adversarial attacks: A low-cost frequency refinement approach. In
Medical Image Computing and Computer-Assisted Intervention (MIC-
CAI), 2020.
[45] Xingjun Ma, Yuhao Niu, Lin Gu, Yisen Wang, Yitian Zhao, James
Bailey, and Feng Lu. Understanding adversarial attacks on deep learning
based medical image analysis systems. Pattern Recognition, 2020.
[46] Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris
Tsipras, and Adrian Vladu. Towards deep learning models resistant
to adversarial attacks. In ICLR, 2018.
[47] Chaithanya Kumar Mummadi, Thomas Brox, and Jan Hendrik Metzen.
Defending against universal perturbations with shared adversarial train-
ing. In ICCV, 2019.
[48] Utku Ozbulak, Arnout Van Messem, and Wesley De Neve. Impact of
adversarial examples on deep learning models for biomedical image
segmentation. In Medical Image Computing and Computer-Assisted
Intervention (MICCAI), 2019.
[49] Amber L. Simpson, Michela Antonelli, Spyridon Bakas, Michel Bilello,
Keyvan Farahani, Bram van Ginneken, Annette Kopp-Schneider, Ben-
nett A. Landman, Geert J. S. Litjens, Bjoern H. Menze, Olaf Ron-
neberger, Ronald M. Summers, Patrick Bilic, Patrick Ferdinand Christ,
Richard K. G. Do, Marc Gollub, Jennifer Golia-Pernicka, Stephan
Heckers, William R. Jarnagin, Maureen McHugo, Sandy Napel, Eugene
Vorontsov, Lena Maier-Hein, and M. Jorge Cardoso. A large annotated
medical image dataset for the development and evaluation of segmen-
tation algorithms. CoRR, abs/1902.09063, 2019.
[50] Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna,
Dumitru Erhan, Ian Goodfellow, and Rob Fergus. Intriguing properties
of neural networks. In ICLR, 2014.
[51] Cihang Xie, Mingxing Tan, Boqing Gong, Alan L. Yuille, and Quoc V.
Le. Smooth adversarial training. CoRR, abs/2006.14536, 2020.
[52] Cihang Xie, Jianyu Wang, Zhishuai Zhang, Yuyin Zhou, Lingxi Xie,
and Alan Yuille. Adversarial examples for semantic segmentation and
object detection. In ICCV, 2017.
11