Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroimaging

2,367 views

Published on

reviewing convolutional neural networks for image processing especially for medical diagnosis and introducing the new CNN architect is following.

Published in: Engineering
  • Hello! I can recommend a site that has helped me. It's called ⇒ www.WritePaper.info ⇐ They helped me for writing my quality research paper.
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here
  • Hi there! I just wanted to share a list of sites that helped me a lot during my studies: .................................................................................................................................... www.EssayWrite.best - Write an essay .................................................................................................................................... www.LitReview.xyz - Summary of books .................................................................................................................................... www.Coursework.best - Online coursework .................................................................................................................................... www.Dissertations.me - proquest dissertations .................................................................................................................................... www.ReMovie.club - Movies reviews .................................................................................................................................... www.WebSlides.vip - Best powerpoint presentations .................................................................................................................................... www.WritePaper.info - Write a research paper .................................................................................................................................... www.EddyHelp.com - Homework help online .................................................................................................................................... www.MyResumeHelp.net - Professional resume writing service .................................................................................................................................. www.HelpWriting.net - Help with writing any papers ......................................................................................................................................... Save so as not to lose
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here
  • Hello! I can recommend a site that has helped me. It's called HelpWriting.net So make sure to check it out!
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here
  • Njce! Thanks for sharing.
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here

Convolutional Neural Network for Alzheimer’s disease diagnosis with Neuroimaging

  1. 1. 1 / 42 Diagnosis of alzheimer's disease with deep learning 2016. 7. 4 Seonho Park
  2. 2. 2 / 42 Outline Introduction to Machine Learning Convolutional Neural Network Diagnosing of Alzheimer’s disease
  3. 3. 3 / 42 Introduction to Machine Learning Convolutional Neural Network Diagnosing of Alzheimer’s disease
  4. 4. 4 / 42 Introduction to Machine Learning x1 x2 x1 y x1 x2 <Supervised Learning> <Unsupervised Learning> classification regression clustering Category of Machine Learning 문제 + 정답 문제 + 정답 문제 + 정답 데이터 + 레이블 머신러닝 학습 머신러닝 모델 정답 예측새로운 데이터 문제 + 정답 문제 + ??? 분류 회귀 Cat Computer Lion Pencil Pig 레이블 없는 데이터 머신러닝 학습 군집화
  5. 5. 5 / 42 Introduction to Machine Learning Scikit-Learn • Machine Learning Library in Python • http://scikit-learn.org/ • Classification: Decision trees, SVM, NN • Regression: GP, Ordinary LS, Ridge Regression, SVR • Clustering: k-Means, Spectral Clustering
  6. 6. 6 / 42 Introduction to Machine Learning Why Deep Learning? • Deep Learning = Deep Neural Network • Data and Machine Learning † http://cs229.stanford.edu/materials/CS229-DeepLearning.pdf
  7. 7. 7 / 42 Introduction to Machine Learning Artificial neural networks Training = Find weights (parameters) Inference = get output by specific input and trained weights
  8. 8. 8 / 42 Introduction to Machine Learning Convolutional Neural Network (CNN) • Image Processing (Computer Vision)
  9. 9. 9 / 42 Introduction to Machine Learning Recurrent Neural Network (RNN) • Time Series Data • Natural Language Processing • Translation, Speech Recognition, Auto Caption • 자동번역, 음성인식, 이미지 캡션 생성 등에 활용 † Towards End-to-End Speech Recognition with Recurrent Neural Networks, Alex Graves et al (2014)
  10. 10. 10 / 42 Introduction to Machine Learning Why GPU? • CuDNN: GPU-accelerated library of primitives for deep neural networks • VRAM limitation, Double/Single/Half Precision • Linear Algebra: CuBLAS, MAGMA
  11. 11. 11 / 42 Introduction to Machine Learning Frameworks Cuda-ConvNetPylearn2 Lasagne
  12. 12. 12 / 42 Introduction to Machine Learning Open Sources for Deep Learning † Comparative Study of Deep Learning Software Frameworks, Soheil Bahrampour et al (2015)
  13. 13. 13 / 42 Introduction to Machine Learning Pioneers • Yann Lecun • Geoffrey Hinton • Yoshua Bengio • Andrew Ng • Jürgen Schmidhuber
  14. 14. 14 / 42 Image Recognition Speech Recognition Auto Caption Self Driving Car Natural Language Processing Recommendation System Introduction to Machine Learning Applications
  15. 15. 15 / 42 Introduction to Machine Learning Convolutional Neural Network Diagnosing of Alzheimer’s disease
  16. 16. 16 / 42 Convolutional Neural Network Overview • Classification • Convolution Operation + MLP • Architecture • Convolutional Layer (Convolution Operator, Activation) • Subsampling (Downsampling, Pooling) • Fully Connected Layer • Classifier
  17. 17. 17 / 42 Convolutional Neural Network LeNet5† Convolutional Operation † Gradient Based Learning Applied to Document Recognition , Yann LeCun et al (1998) • Digit Recognition • Weight matrix (filter): 4D tensor [# of feature at layer m, # of features at layer m-1, height, width]
  18. 18. 18 / 42 Convolutional Neural Network Activation function (nonlinearity) † Systematic evaluation of CNN advances on the ImageNet, Dmytro Mishkin, et al (2016)
  19. 19. 19 / 42 Convolutional Neural Network Pooling Layer • Erase Noise • Reduce Feature Map Size (Memory Save) † Systematic evaluation of CNN advances on the ImageNet, Dmytro Mishkin, et al (2016)
  20. 20. 20 / 42 Convolutional Neural Network Training • Error(Loss) Function: Categorical Cross Entropy • Design Variable: weights(W), bias(b) • Backpropagation conjunction with an optimization method such as gradient descent • Vanishing gradient
  21. 21. 21 / 42 Convolutional Neural Network Mini-Batch Method • Computational Efficiency • Memory Use • Iteration & Epoch Vanilla Gradient Descent Stochastic Gradient Descent • Parameter update for each training example x(i) and label y(i) • Step size(η) is typically set to 10-3
  22. 22. 22 / 42 Convolutional Neural Network Training (Optimization) • Update Functions • Second-order Method (L-BFGS) is not common in practice • NAG is more standard
  23. 23. 23 / 42 Convolutional Neural Network Overfitting and Regularization • Dropout • Relaxation: Add Regularization Term to Loss Function • Remove Layer (Reduce Parameters), Add Feature † Dropout: A Simple Way to Prevent Neural Networks from Overfitting, Nitish Srivastava et al (2014)
  24. 24. 24 / 42 Convolutional Neural Network Local Optimum? † Identifying and attacking the saddle point problem in high-dimensional non-convex optimization, Yann N. Dauphin et al (2014) • Non-convex optimization problem • deeper and more profound difficulty originates from the proliferation of saddle points, not local minima, especially in high dimensional problems of practical interest
  25. 25. 25 / 42 Convolutional Neural Network Parallel Computation • Architectural Parallel: Divide Channel • Data Parallel: Divide Batch
  26. 26. 26 / 42 ILSVRC • Evaluate algorithms for object detection and image classification at large scale • Training: 1.3M/ Test: 100k, 1000 categories Convolutional Neural Network
  27. 27. 27 / 42 AlexNet • ILSVRC12 1st Place • 15.3% error rate (2nd place achieved 26.5% error rate) • Architecture Parallel (2GPU used) † ImageNet Classification with Deep Convolutional Neural Networks, Alex Krizhevsky et al. (2012) Convolutional Neural Network
  28. 28. 28 / 42 VGG Net • DeepMind • ILSVRC14 2nd Place • 6.8% error rate † VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION, Karen Simonyan et al. (2014) Convolutional Neural Network
  29. 29. 29 / 42 GoogLeNet • Google • Inception module • ILSVRC14 1st Place • 6.67% error rate † Going Deeper with Convolutions, Christian Szegedy et al. (2014) Convolutional Neural Network
  30. 30. 30 / 42 MSRA • MicroSoft • PReLU activation • Weight initialization • 4.94% error rate (Surpass Human Level, 5.1%) † Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, Kaiming He et al. (2015) Convolutional Neural Network
  31. 31. 31 / 42 Inception-v3 • Google • Inception Module Upgrade • 50 GPUs • 3.46% error rate • Public Use with TensorFlow † Going Deeper with Convolutions, Christian Szegedy et al. (2015) Convolutional Neural Network
  32. 32. 32 / 42 Convolutional Neural Network Deep Neural Networks are Easily Fooled† † Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images, A Nguyen et al (2014) • It is possible to produce images totally unrecognizable to human eyes • interesting differences between human vision and current DNNs • raise questions about the generality of DNN computer vision
  33. 33. 33 / 42 Convolutional Neural Network Neural Style † A Neural Algorithm of Artistic Style, Leon A. Gatys et al (2014) • Style + Contents reconstruction • Caffe framework • https://github.com/jcjohnson/neural-style
  34. 34. 34 / 42 Introduction to Machine Learning Convolutional Neural Network Diagnosing of Alzheimer’s disease
  35. 35. 35 / 42 Diagnosing of Alzheimer’s disease Traditional Diagnosis of Alzheimer’s disease • Review medical history • Mini Mental Status Exam • Physical Exam • Neurological Exam • Brain Image: Structural(MRI,CT), Functional(fMRI) • NC(Normal Condition), MCI(Mild Cognitive Impairment), AD • AD: Vascular/Non-Vascular
  36. 36. 36 / 42 Diagnosing of Alzheimer’s disease AD Patients’ MRI Features • Temporal Lobe: Hippocampus • Ventricle
  37. 37. 37 / 42 Diagnosing of Alzheimer’s disease Case Study: Machine Learning for diagnosing of AD • PET, MRI images • Patch Extraction • Restrict Bolzmann Machine • Accuracy: 92.4%(MRI), 95.35%(MRI+PET) † Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis, Heung-Il Suk et al (2014)
  38. 38. 38 / 42 Diagnosing of Alzheimer’s disease Case Study: Machine Learning for diagnosing of AD • Feature: Cortex Thickness • FreeSurfer • Linear discriminant analysis (LDA) • Accuracy: Sensitivity: 82%, Specificity: 93% † Individual subject classification for Alzheimer’s disease based on incremental learning using a spatial frequency representation of cortical thickness data, Young-Sang Cho et al (2012)
  39. 39. 39 / 42 Diagnosing of Alzheimer’s disease Preprocessing • Data Set: about 1400 of T1 MRI from SMC • FreeSurfer: Skull Stripping: reduce size [256,256,256][190,190,190] / 67MB27MB • Pixel Value Normalization [0,255]  [-1,1] • Mirrored cropping
  40. 40. 40 / 42 Diagnosing of Alzheimer’s disease Architecture • CNN • Lasagne (Theano) Framework • Inception Module, Batch Normalization • 3D Convolution + CuDNN v3 (Github) • 2 TITAN X GPU: Data Parallel (PyCUDA) • Batch Size: 80 • Training Set #Healthy Condition(HC): 761 #Alzheimer’s Disease (AD): 389 • Test Set #Healthy Condition(HC): 105 #Alzheimer’s Disease (AD): 84 Data
  41. 41. 41 / 42 Diagnosing of Alzheimer’s disease Architecture input 24*Conv11/5 MaxPool7/2 288*Conv3/2 FC120 DropOut SoftMax input 36*Conv16/6 MaxPool3/2 120*Conv4/1 BatchNorm MaxPool3/2 60*Conv1/1 96*Conv3/1 12*Conv1/1 24*Conv5/124*Conv1/1 MaxPool3/1 48*Conv1/1 Concatenate MaxPool3/2 FC150 128*Conv1/1 192*Conv3/1 32*Conv1/1 96*Conv5/164*Conv1/1 MaxPool3/1 128*Conv1/1 Concatenate 96*Conv1/1 208*Conv3/1 16*Conv1/1 48*Conv5/164*Conv1/1 MaxPool3/1 192*Conv1/1 Concatenate SoftMax input 60*Conv10/2 MaxPool2/2 144*Conv3/1 BatchNorm MaxPool3/2 48*Conv1/1 72*Conv3/1 18*Conv1/1 36*Conv5/148*Conv1/1 MaxPool3/1 48*Conv1/1 Concatenate MaxPool3/2 FC500 96*Conv1/1 208*Conv3/1 16*Conv1/1 48*Conv5/164*Conv1/1 MaxPool3/1 192*Conv1/1 Concatenate 160*Conv1/1 320*Conv3/1 32*Conv1/1 128*Conv5/1128*Conv1/1 MaxPool3/1 256*Conv1/1 Concatenate SoftMax 280*Conv1/1 340*Conv3/1 32*Conv1/1 128*Conv5/1128*Conv1/1 MaxPool3/1 228*Conv1/1 Concatenate AvgPool3/1 MidasNet1 MidasNet2 MidasNet3
  42. 42. 42 / 42 Convergence History Model Accuracy MidasNet1 167/189 (88.4%) MidasNet2 169/189 (89.4%) MidasNet3 169/189 (89.4%) 0.01 0.1 1 10 0 10 20 30 40 50 60 70 80 90 100 110 120 130 140 150 160 170 180 190 Cost Epoch Diagnosing of Alzheimer’s disease Result
  43. 43. Thank You

×