The Cancer Imaging Archive (TCIA) is a service which de-identifies and hosts a large archive of medical images of cancer accessible for public download.
- Update on new data sets
- New features
- New publications
- Other news
Radiomics: Novel Paradigm of Deep Learning for Clinical Decision Support towa...Wookjin Choi
‘Radiomics’ is a novel process to identify ‘radiome’ in the field of imaging informatics when long-term clinical outcomes such as mortality are not immediately available, relying on first acquiring paired gene expression data and medical images at diagnosis from a study cohort, and then leveraging the public gene expression data containing clinical outcomes from a closely matched population into a personalized medicine (Stanford and Harvard University).
Professor Harrison Bai, Artificial Intelligence Applications in Radiology_mHe...Levi Shapiro
The document discusses several active areas of work in artificial intelligence applications in radiology at Brown University's AI radiology lab, including COVID-19 detection from chest x-rays, tumor assessment, stroke diagnosis, and more. It provides details on techniques like contrast dropout to deal with missing data, human-in-the-loop approaches, automatic quality estimation, treatment response evaluation, and federated learning to share models without sharing patient data. Performance results and example visualizations from various models are also included.
Slides presented at the Molecular Med Tri-Con 2018 Precision Medicine, "Emerging Role of Radiomics in Precision Medicine" (http://www.triconference.com/Precision-Medicine/)
Abstract
The goal of this talk is to discuss the role of data standards, and specifically the Digital Imaging and Communication in Medicine (DICOM) standard, in supporting radiomics research. From the clinical images, to the storage of image annotations and results of radiomics analysis, standardization can potentially have transformative effect by enabling discovery, reuse and mining of the data, and integration of the radiomics workflows into the healthcare enterprise.
This document provides an overview of a radiogenomic imaging prototype that utilizes data from The Cancer Imaging Archive (TCIA). It discusses how DICOM images contain valuable metadata and how radiomics aims to extract higher dimensional data from images for improved decision support. The prototype would allow segmentation and feature extraction of images from TCIA and correlate these with genomic and pathology data from The Cancer Genome Atlas. Within 6 months, the goal is to create a standalone Python application that demonstrates key imaging analysis capabilities and is compatible with TCIA data standards.
University of Toronto - Radiomics for Oncology - 2017Andre Dekker
This document contains the slides from a lecture on radiomics for oncology given by Andre Dekker. The lecture covers the rationale for radiomics, which is to use quantitative features extracted from medical images to help predict outcomes like tumor behavior, survival, and response to treatment using machine learning. The major workflow steps of radiomics are discussed, from image acquisition and feature extraction to modeling and validation. Key challenges like robust segmentation and feature reproducibility are also addressed. New directions for radiomics research include applications in preclinical studies, other modalities like PET and MRI, and linking radiomic features to genomic data. Overall, radiomics holds promise to help personalized medicine but large amounts of standardized data are still needed for proper validation of models.
Radiomics: Novel Paradigm of Deep Learning for Clinical Decision Support towa...Wookjin Choi
‘Radiomics’ is a novel process to identify ‘radiome’ in the field of imaging informatics when long-term clinical outcomes such as mortality are not immediately available, relying on first acquiring paired gene expression data and medical images at diagnosis from a study cohort, and then leveraging the public gene expression data containing clinical outcomes from a closely matched population into a personalized medicine (Stanford and Harvard University).
Professor Harrison Bai, Artificial Intelligence Applications in Radiology_mHe...Levi Shapiro
The document discusses several active areas of work in artificial intelligence applications in radiology at Brown University's AI radiology lab, including COVID-19 detection from chest x-rays, tumor assessment, stroke diagnosis, and more. It provides details on techniques like contrast dropout to deal with missing data, human-in-the-loop approaches, automatic quality estimation, treatment response evaluation, and federated learning to share models without sharing patient data. Performance results and example visualizations from various models are also included.
Slides presented at the Molecular Med Tri-Con 2018 Precision Medicine, "Emerging Role of Radiomics in Precision Medicine" (http://www.triconference.com/Precision-Medicine/)
Abstract
The goal of this talk is to discuss the role of data standards, and specifically the Digital Imaging and Communication in Medicine (DICOM) standard, in supporting radiomics research. From the clinical images, to the storage of image annotations and results of radiomics analysis, standardization can potentially have transformative effect by enabling discovery, reuse and mining of the data, and integration of the radiomics workflows into the healthcare enterprise.
This document provides an overview of a radiogenomic imaging prototype that utilizes data from The Cancer Imaging Archive (TCIA). It discusses how DICOM images contain valuable metadata and how radiomics aims to extract higher dimensional data from images for improved decision support. The prototype would allow segmentation and feature extraction of images from TCIA and correlate these with genomic and pathology data from The Cancer Genome Atlas. Within 6 months, the goal is to create a standalone Python application that demonstrates key imaging analysis capabilities and is compatible with TCIA data standards.
University of Toronto - Radiomics for Oncology - 2017Andre Dekker
This document contains the slides from a lecture on radiomics for oncology given by Andre Dekker. The lecture covers the rationale for radiomics, which is to use quantitative features extracted from medical images to help predict outcomes like tumor behavior, survival, and response to treatment using machine learning. The major workflow steps of radiomics are discussed, from image acquisition and feature extraction to modeling and validation. Key challenges like robust segmentation and feature reproducibility are also addressed. New directions for radiomics research include applications in preclinical studies, other modalities like PET and MRI, and linking radiomic features to genomic data. Overall, radiomics holds promise to help personalized medicine but large amounts of standardized data are still needed for proper validation of models.
Twenty Years of Whole Slide Imaging - the Coming Phase ChangeJoel Saltz
I surveyed the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins (PMC2233368) to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data. I will describe the capabilities of current methods, describe how these methods are likely to evolve and how they will be likely to impact Pathology research and practice.
Detection of Lung Cancer using SVM ClassificationIRJET Journal
This document presents a method for detecting lung cancer using support vector machine (SVM) classification of sputum cell images. The authors first extract features from sputum cell images such as nucleus-cytoplasm ratio, perimeter, density, curvature, and circularity. They then use these extracted features to train an SVM classifier to classify sputum cells as cancerous or normal. The authors test their proposed method on 100 sputum cell images and evaluate the technique's performance using metrics like sensitivity, precision, specificity, and accuracy. Their results indicate the SVM classification approach shows potential for early detection of lung cancer from sputum cell analysis.
This chapter discusses rapid learning health care as an approach to enable customized radiotherapy. It describes a 4-phase methodology: 1) collecting diverse patient, treatment and outcome data, 2) developing prediction models using machine learning to analyze the data, 3) applying the models in clinical practice via decision support systems, and 4) evaluating predicted vs actual outcomes. The goal is to improve treatment predictability and ensure patients receive optimal therapy while efficiently using resources. Next steps involve including patient preferences in decision making for personalized cancer care.
Warren Kibbe discusses challenges and opportunities in cancer research and precision medicine. Cancer is a grand challenge that requires deep biological understanding, advances in scientific methods and technology, and leveraging large amounts of detailed data. While genomics sequencing has become cheaper, analyzing and making sense of the vast amounts of multi-omic, clinical and other data generated poses new challenges. Emerging technologies like cryo-EM and single cell techniques are providing new insights. Collaborative team science bringing together experimentalists and computational/data scientists is critical to make progress on problems like understanding RAS activation. Precision medicine aims to understand health and disease at the population, individual and clinical levels by leveraging diverse clinical, molecular and other data, but connecting
Presentation that gives an overview of the impact of IT on radiology, including the growing role of biomarkers and artificial intelligence and deep learning on the (future) radiology profession. The shift to precision medicine and personalized care are explained, the reasons for a re-definition of radiology are addressed.
Public Databases for Radiomics Research: Current Status and Future DirectionsCancerImagingInforma
This document discusses radiomics research and public databases. It describes what radiomics is and why data sharing is important. Several public databases are mentioned, with an in-depth look at The Cancer Imaging Archive (TCIA). TCIA hosts radiology data like CT, MR, PET images along with associated data. It provides services to upload and access data and enables data citation. Future directions discussed include standardization initiatives and using cloud computing.
SAMSI Precision Medicine Keynote, August 2018: Data: where Precision Oncology...Warren Kibbe
The promise of precision medicine in oncology is predicated on the availability of accurate, high quality data from the clinic and the laboratory. Likewise, a Learning Health System is one in which we use data to monitor that we are following guidelines and care pathways to deliver the best care and not revert to prior practices (regression testing for care!) and also provide real world evidence to determine effectiveness and identify populations that would benefit from novel therapies. Into this mix of clinical drivers are the rapidly changing capabilities in instrumentation, computing, computation, and the pervasive use of sensors and smart devices. I will highlight a few of the obvious and perhaps not as obvious opportunities in leveraging the increasingly digital landscape in healthcare and biomedical research as we move toward a national learning health system for cancer.
Digital Pathology, FDA Approval and Precision MedicineJoel Saltz
Digital pathology platforms combined with machine learning can improve the consistency and quality of clinical decision making by precisely scoring known criteria from pathology images and predicting treatment outcomes and cancer types. Researchers are developing tools to extract features from pathology images, link these features to molecular data and clinical outcomes, and use these integrated datasets to gain new insights into cancer and select the best interventions. The SEER Virtual Tissue Repository aims to enable population-level cancer research by creating a linked collection of de-identified clinical data and whole slide images from pathology samples that can be analyzed using computational methods.
This document provides an overview of the development of a white paper on teleradiology by the European Society of Radiology (ESR). It discusses the purpose and objectives of the white paper, which is to establish standards for teleradiology across Europe. A task force was assembled consisting of radiologists with relevant expertise. They reviewed existing literature and standards and aimed to create an online document that could be easily updated. The white paper would address topics like quality, legal issues, and technical standards for teleradiology.
Twenty Years of Whole Slide Imaging - the Coming Phase ChangeJoel Saltz
Presentation at Pathology Visions 2017 - https://digitalpathologyassociation.org/2017-pathology-visions-agenda
I will survey the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins (PMC2233368) to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data. I will describe the capabilities of current methods, describe how these methods are likely to evolve and how they will be likely to impact Pathology research and practice.
BDW16 London - Mishal Patel, NHS - Modernising Routine Breast Cancer Using Bi...Big Data Week
Radiological imaging is fundamental within the healthcare industry and has become routinely adopted for diagnosis, disease monitoring and treatment planning. With the advent of digital imaging modalities and the rapid growth in both diagnostic and therapeutic imaging, the ability to able to harness this large influx of data is of paramount. Traditionally, the systematic collection of medical images for research from heterogeneous sites has not been commonplace within the NHS and is fraught with challenges including; data acquisition, storage, secure transfer and correct anonymisation. Here we describe the development and implementation of a national centralised oncology image database and discuss the central issues associated with large-scale image acquisition from heterogeneous sites.
The ability to collect fully annotated sets of images for research opens to door to a multitude of potential research opportunities that utilise the legacy images, such as quantitative image informatics. Medical imaging provides the ability to detect and localise many changes that are important to determine whether a disease is present or a therapy is effective by depicting alterations in the anatomic, physiologic, biochemical or molecular process. Calculating quantitative imaging features from acquired images and using these to build computational models to investigate detection, prognosis, and classification.
IRJET- Lung Cancer Detection using Digital Image Processing and Artificia...IRJET Journal
This document discusses a proposed system to detect lung cancer at early stages using digital image processing and artificial neural networks. The system consists of several steps: image acquisition, preprocessing using histogram equalization, segmentation using thresholding, dilation, image filling, feature extraction from CT images, and classification of images using an artificial neural network. The goal is to develop an automated diagnostic system that can maximize the detection of true positive lung cancer cases while minimizing false negatives to improve early detection rates and patient outcomes.
This document discusses digital pathology, which focuses on managing pathology data from digitized glass slides. Key points include:
- Glass slides are converted into high-resolution digital slides that can be viewed and analyzed on computer monitors.
- Digital pathology offers advantages like telepathology, improved accuracy and speed, and potential roles in clinical research.
- While the global digital pathology market is growing, limitations include high costs, lack of standards, and need for stable technology.
- Digital pathology could offer significant benefits in developing countries by reducing costs and improving patient care, but high equipment and software costs present challenges.
- As technology advances, digital pathology may become mainstream, but pathologists will still need microscope skills and issues around
TexRAD is software that analyzes textures in existing medical scans to provide prognostic information and risk stratification to clinicians. It does this by measuring fine, medium, and coarse textures in scans of tumors like those in the liver, lungs, and other organs. This additional texture information can help predict factors like cancer stage, metastasis risk, and prognosis. TexRAD requires no new scanning procedures and can analyze routine clinical images, providing more information to clinicians to guide patient care decisions.
Initial Lessons From Implementing a Telecolposcopy Program on a High Risk Pop...MobileODT
Initial findings from a study on implementing a telecolposcopy program on a high-risk population in California showed that:
1) Experts were able to assist junior providers remotely and provide guidance in real-time during colposcopy procedures through a mobile telecolposcopy system.
2) Both patients and providers reacted positively to the use of live remote expert supervision during telecolposcopy exams.
3) Preliminary results suggest telecolposcopy is a feasible approach when integrated into a mobile colposcopy system and may help address lack of in-person colposcopy services, especially for underserved populations.
Calypso Medical's Prostate Cancer Treatment: Imaging Technology NewsCalypso Medical
A thorough explanation of image guided radiation therapy for prostate cancer, prostate cancer side effects associated with prostate radiation treatment, and how Calypso GPS for the Body technology greatly reduces the risk of side effects.
Performance of automated visual evaluation as a triage test for HPV+ patients...MobileODT
1) Automated visual evaluation (AVE) uses machine learning to predict cervical pathology by analyzing images, providing a low-cost alternative in low-resource settings.
2) The study integrated an existing AVE classifier into the Enhanced Visual Assessment imaging system to evaluate patients at a cervical cancer screening camp in rural China.
3) Results found AVE to have a very low failure rate of 1.3% compared to 11.6% for colposcopy. AVE performance was comparable to existing triage methods and favorable for use in low-resource settings.
2016 Data Commons and Data Science Workshop June 7th and June 8th 2016. Genomic Data Commons, FAIR, NCI and making data more findable, publicly accessible, interoperable (machine readable), reusable and support recognition and attribution
US Federal Cancer Moonshot- One Year LaterJerry Lee
Presentation from former Cancer Moonshot Data and Technology Track Co-chairs Jerry S.H. Lee, PhD (NCI, former OVP) and Dimitri Kusnezov, PhD (DOE) to update on efforts that will help realize the Data/Tech Track's vision of a national learning healthcare system for cancer. These include NCI/DOE pilots, DOE/VA pilot, NCI GDC, DoD/VA/NCI APOLLO, NCI/GSK ATOM, and BloodPAC.
Twenty Years of Whole Slide Imaging - the Coming Phase ChangeJoel Saltz
I surveyed the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins (PMC2233368) to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data. I will describe the capabilities of current methods, describe how these methods are likely to evolve and how they will be likely to impact Pathology research and practice.
Detection of Lung Cancer using SVM ClassificationIRJET Journal
This document presents a method for detecting lung cancer using support vector machine (SVM) classification of sputum cell images. The authors first extract features from sputum cell images such as nucleus-cytoplasm ratio, perimeter, density, curvature, and circularity. They then use these extracted features to train an SVM classifier to classify sputum cells as cancerous or normal. The authors test their proposed method on 100 sputum cell images and evaluate the technique's performance using metrics like sensitivity, precision, specificity, and accuracy. Their results indicate the SVM classification approach shows potential for early detection of lung cancer from sputum cell analysis.
This chapter discusses rapid learning health care as an approach to enable customized radiotherapy. It describes a 4-phase methodology: 1) collecting diverse patient, treatment and outcome data, 2) developing prediction models using machine learning to analyze the data, 3) applying the models in clinical practice via decision support systems, and 4) evaluating predicted vs actual outcomes. The goal is to improve treatment predictability and ensure patients receive optimal therapy while efficiently using resources. Next steps involve including patient preferences in decision making for personalized cancer care.
Warren Kibbe discusses challenges and opportunities in cancer research and precision medicine. Cancer is a grand challenge that requires deep biological understanding, advances in scientific methods and technology, and leveraging large amounts of detailed data. While genomics sequencing has become cheaper, analyzing and making sense of the vast amounts of multi-omic, clinical and other data generated poses new challenges. Emerging technologies like cryo-EM and single cell techniques are providing new insights. Collaborative team science bringing together experimentalists and computational/data scientists is critical to make progress on problems like understanding RAS activation. Precision medicine aims to understand health and disease at the population, individual and clinical levels by leveraging diverse clinical, molecular and other data, but connecting
Presentation that gives an overview of the impact of IT on radiology, including the growing role of biomarkers and artificial intelligence and deep learning on the (future) radiology profession. The shift to precision medicine and personalized care are explained, the reasons for a re-definition of radiology are addressed.
Public Databases for Radiomics Research: Current Status and Future DirectionsCancerImagingInforma
This document discusses radiomics research and public databases. It describes what radiomics is and why data sharing is important. Several public databases are mentioned, with an in-depth look at The Cancer Imaging Archive (TCIA). TCIA hosts radiology data like CT, MR, PET images along with associated data. It provides services to upload and access data and enables data citation. Future directions discussed include standardization initiatives and using cloud computing.
SAMSI Precision Medicine Keynote, August 2018: Data: where Precision Oncology...Warren Kibbe
The promise of precision medicine in oncology is predicated on the availability of accurate, high quality data from the clinic and the laboratory. Likewise, a Learning Health System is one in which we use data to monitor that we are following guidelines and care pathways to deliver the best care and not revert to prior practices (regression testing for care!) and also provide real world evidence to determine effectiveness and identify populations that would benefit from novel therapies. Into this mix of clinical drivers are the rapidly changing capabilities in instrumentation, computing, computation, and the pervasive use of sensors and smart devices. I will highlight a few of the obvious and perhaps not as obvious opportunities in leveraging the increasingly digital landscape in healthcare and biomedical research as we move toward a national learning health system for cancer.
Digital Pathology, FDA Approval and Precision MedicineJoel Saltz
Digital pathology platforms combined with machine learning can improve the consistency and quality of clinical decision making by precisely scoring known criteria from pathology images and predicting treatment outcomes and cancer types. Researchers are developing tools to extract features from pathology images, link these features to molecular data and clinical outcomes, and use these integrated datasets to gain new insights into cancer and select the best interventions. The SEER Virtual Tissue Repository aims to enable population-level cancer research by creating a linked collection of de-identified clinical data and whole slide images from pathology samples that can be analyzed using computational methods.
This document provides an overview of the development of a white paper on teleradiology by the European Society of Radiology (ESR). It discusses the purpose and objectives of the white paper, which is to establish standards for teleradiology across Europe. A task force was assembled consisting of radiologists with relevant expertise. They reviewed existing literature and standards and aimed to create an online document that could be easily updated. The white paper would address topics like quality, legal issues, and technical standards for teleradiology.
Twenty Years of Whole Slide Imaging - the Coming Phase ChangeJoel Saltz
Presentation at Pathology Visions 2017 - https://digitalpathologyassociation.org/2017-pathology-visions-agenda
I will survey the development of Digital Pathology methodology beginning with the 1997 virtual microscope prototype at Hopkins (PMC2233368) to current tools, methods and algorithms designed to display, analyze and classify whole slide imaging data. I will describe the capabilities of current methods, describe how these methods are likely to evolve and how they will be likely to impact Pathology research and practice.
BDW16 London - Mishal Patel, NHS - Modernising Routine Breast Cancer Using Bi...Big Data Week
Radiological imaging is fundamental within the healthcare industry and has become routinely adopted for diagnosis, disease monitoring and treatment planning. With the advent of digital imaging modalities and the rapid growth in both diagnostic and therapeutic imaging, the ability to able to harness this large influx of data is of paramount. Traditionally, the systematic collection of medical images for research from heterogeneous sites has not been commonplace within the NHS and is fraught with challenges including; data acquisition, storage, secure transfer and correct anonymisation. Here we describe the development and implementation of a national centralised oncology image database and discuss the central issues associated with large-scale image acquisition from heterogeneous sites.
The ability to collect fully annotated sets of images for research opens to door to a multitude of potential research opportunities that utilise the legacy images, such as quantitative image informatics. Medical imaging provides the ability to detect and localise many changes that are important to determine whether a disease is present or a therapy is effective by depicting alterations in the anatomic, physiologic, biochemical or molecular process. Calculating quantitative imaging features from acquired images and using these to build computational models to investigate detection, prognosis, and classification.
IRJET- Lung Cancer Detection using Digital Image Processing and Artificia...IRJET Journal
This document discusses a proposed system to detect lung cancer at early stages using digital image processing and artificial neural networks. The system consists of several steps: image acquisition, preprocessing using histogram equalization, segmentation using thresholding, dilation, image filling, feature extraction from CT images, and classification of images using an artificial neural network. The goal is to develop an automated diagnostic system that can maximize the detection of true positive lung cancer cases while minimizing false negatives to improve early detection rates and patient outcomes.
This document discusses digital pathology, which focuses on managing pathology data from digitized glass slides. Key points include:
- Glass slides are converted into high-resolution digital slides that can be viewed and analyzed on computer monitors.
- Digital pathology offers advantages like telepathology, improved accuracy and speed, and potential roles in clinical research.
- While the global digital pathology market is growing, limitations include high costs, lack of standards, and need for stable technology.
- Digital pathology could offer significant benefits in developing countries by reducing costs and improving patient care, but high equipment and software costs present challenges.
- As technology advances, digital pathology may become mainstream, but pathologists will still need microscope skills and issues around
TexRAD is software that analyzes textures in existing medical scans to provide prognostic information and risk stratification to clinicians. It does this by measuring fine, medium, and coarse textures in scans of tumors like those in the liver, lungs, and other organs. This additional texture information can help predict factors like cancer stage, metastasis risk, and prognosis. TexRAD requires no new scanning procedures and can analyze routine clinical images, providing more information to clinicians to guide patient care decisions.
Initial Lessons From Implementing a Telecolposcopy Program on a High Risk Pop...MobileODT
Initial findings from a study on implementing a telecolposcopy program on a high-risk population in California showed that:
1) Experts were able to assist junior providers remotely and provide guidance in real-time during colposcopy procedures through a mobile telecolposcopy system.
2) Both patients and providers reacted positively to the use of live remote expert supervision during telecolposcopy exams.
3) Preliminary results suggest telecolposcopy is a feasible approach when integrated into a mobile colposcopy system and may help address lack of in-person colposcopy services, especially for underserved populations.
Calypso Medical's Prostate Cancer Treatment: Imaging Technology NewsCalypso Medical
A thorough explanation of image guided radiation therapy for prostate cancer, prostate cancer side effects associated with prostate radiation treatment, and how Calypso GPS for the Body technology greatly reduces the risk of side effects.
Performance of automated visual evaluation as a triage test for HPV+ patients...MobileODT
1) Automated visual evaluation (AVE) uses machine learning to predict cervical pathology by analyzing images, providing a low-cost alternative in low-resource settings.
2) The study integrated an existing AVE classifier into the Enhanced Visual Assessment imaging system to evaluate patients at a cervical cancer screening camp in rural China.
3) Results found AVE to have a very low failure rate of 1.3% compared to 11.6% for colposcopy. AVE performance was comparable to existing triage methods and favorable for use in low-resource settings.
2016 Data Commons and Data Science Workshop June 7th and June 8th 2016. Genomic Data Commons, FAIR, NCI and making data more findable, publicly accessible, interoperable (machine readable), reusable and support recognition and attribution
US Federal Cancer Moonshot- One Year LaterJerry Lee
Presentation from former Cancer Moonshot Data and Technology Track Co-chairs Jerry S.H. Lee, PhD (NCI, former OVP) and Dimitri Kusnezov, PhD (DOE) to update on efforts that will help realize the Data/Tech Track's vision of a national learning healthcare system for cancer. These include NCI/DOE pilots, DOE/VA pilot, NCI GDC, DoD/VA/NCI APOLLO, NCI/GSK ATOM, and BloodPAC.
Advancing Innovation and Convergence in Cancer Research: US Federal Cancer Mo...Jerry Lee
Special Seminar at the 8th Taiwan Biosignatures Workshop to share overall work of NCI's Center for Strategic Scientific Initiatives since 2003 as well as CSSI's influence on select projects initiated by the 2016 WH Cancer Moonshot Task Force that include Applied Proteogenomics Organizational Learning and Outcomes (APOLLO) network, International Cancer Proteogenome Consortium, and the Blood Profiling Atlas in Cancer (BloodPAC) commons.
NCI Cancer Genomics, Open Science and PMI: FAIR Warren Kibbe
Talk given to the NLM Fellows on July 8, 2016. Touches on Cancer Genomics, Open Science and PMI: FAIR in NCI genomics thinking and projects. Includes discussion of the Genomic Data Commons (GDC), Cancer Data Ecosystem, Data sharing, and the NCI cancer clinical trials open API.
This document outlines a research proposal on medical image fusion. It discusses radiotherapy treatment planning which involves target volume delineation using fused images from modalities like PET, CT and MRI. The proposal discusses techniques for image decomposition, fusion and reconstruction. It reviews literature on various fusion methods like multi-resolution analysis, multi-scale geometric analysis and color based methods. It identifies research gaps in appropriate decomposition levels and contouring. The proposal discusses implementing a fusion method using soft computing techniques to differentiate between edge and non-edge regions.
tranSMART Community Meeting 5-7 Nov 13 - Session 3: The TraIT user stories fo...David Peyruc
This document provides an overview of the TraIT project and existing demonstrators using tranSMART. It discusses the TraIT roadmap and user stories being implemented at the Netherlands Cancer Institute. Key points include:
- TraIT aims to support translational research through integrated data and tools across clinical, imaging, biobanking and experimental domains.
- Existing demonstrators using tranSMART include DeCoDe (colorectal cancer) and PCMM (prostate cancer).
- The roadmap involves enhancing tranSMART functionality based on user needs and integrating additional data sources.
- At NKI, tranSMART will provide an integrated research data warehouse with clinical and research data from various sources and departments.
- National challenges in cancer research include lowering barriers to data access and analysis, and integrating clinical and basic research data to enable improved outcomes.
- Disruptive technologies like high-throughput biology and ubiquitous computing are generating large amounts of molecular and clinical cancer data.
- The NCI is working to build infrastructure like the Genomics Data Commons and Cloud Pilots to make these data widely accessible and support data analysis.
- The goal is to develop a national "learning health system" that applies insights from real-world cancer data to research and clinical practice to continuously improve patient care and outcomes.
Cancer Moonshot, Data sharing and the Genomic Data CommonsWarren Kibbe
Gave the inaugural Informatics Grand Rounds at City of Hope on September 8th. NIH Commons, Genomic Data Commons, NCI Cloud Pilots, Cancer Moonshot and rationale for changing incentives around data sharing all discussed.
Advancing Convergence and Innovation in Cancer Research: Seminar at Universit...Jerry Lee
Since 2003, the National Cancer Institute’s Center for Strategic Scientific Initiatives (CSSI) has worked to develop the resources and infrastructures investigators need to surmount roadblocks in cancer research. CSSI manages programs that promote technology development and cross-disciplinary collaboration and provide support for investigators in nascent and challenging research fields. This support includes funding opportunities, shared reagent and database resources, and assistance in the development of standards and protocols. CSSI also provides a network of partners in industry and government that can help NCI-funded researchers advance their technologies toward commercialization and translation. This presentation will highlight technologies including single-cell isolation and analysis techniques that have been supported through various CSSI mechanisms from proof-of-concept to translation into the clinic.
A Vision for a Cancer Research Knowledge SystemWarren Kibbe
The document discusses a vision for a cancer research knowledge system that utilizes data commons and cloud platforms. It describes how data commons co-locate data, storage, computing and tools to create interoperable resources for researchers. The Genomic Data Commons aims to make over 30,000 cancer cases FAIR (Findable, Accessible, Interoperable, Reusable) and provide attribution. This will help identify rare cancer drivers and factors influencing therapy response. The system incorporates multiple data types from studies and clinical trials to enable precision medicine approaches.
The document outlines various resources and programs available through the National Institutes of Health (NIH) to support research and development efforts, from early stage screening and validation to late stage clinical trials. It describes screening programs, technology characterization services, preclinical and clinical development resources across multiple NIH institutes focused on areas like cancer, neurodegeneration, infectious diseases, and more. The document encourages collaborations between NIH researchers and outside entities through licensing agreements, cooperative research agreements, and material transfers to help move technologies toward public health benefits.
This document provides an overview of clinical trial accrual challenges and discusses how social media could potentially help address some of these challenges. It summarizes the National Clinical Trials Network (NCTN) and reviews major accrual barriers experienced by institutions, investigators, and patients. These include a lack of trial awareness, preference for standard care over trials, and concerns about side effects. The document then describes NCI's use of Twitter to promote NCTN trials and poses questions about how social media could enhance awareness of cancer clinical trials.
National Cancer Data Ecosystem and Data SharingWarren Kibbe
Grand Rounds at the Siteman Cancer Center at Washington University. Highlighting the Genomic Data Commons and the National Cancer Data Ecosystem defined by the Cancer Moonshot Blue Ribbon Panel
Cancer Research Data Ecosystem - Dr. Warren Kibbeimgcommcall
The document discusses the Cancer Research Data Ecosystem and the National Cancer Data Ecosystem being developed through the Beau Biden Cancer Moonshot initiative. It notes that cancer research and care generate large amounts of detailed data that is critical to create a learning health system for cancer. It highlights efforts like the NIH Genomic Data Commons and the need for data standards to make cancer-related data more accessible, interoperable, and reusable to researchers. The goal is to maximize data sharing and reuse to advance the understanding of cancer and improve prevention and treatment outcomes.
NCI Cancer Imaging Program - Cancer Research Data EcosystemWarren Kibbe
Given to the NCI Cancer Imaging Program monthly telecon on January 9th, 2017. NCI Genomic Data Commons, Beau Biden Cancer Moonshot Blue Ribbon Panel, Cancer Research Data Ecosystem and the role of imaging in precision medicine
Converged IT Summit - NCI Data SharingWarren Kibbe
Cancer Moonshot, Data Sharing, Genomic Data Commons, NCI Cloud Pilots, Cancer Research Data Ecosystem, technology advances, chemotherapy advances, MATCH, NCI Cancer Moonshot Blue Ribbon Panel Recommendations
Keynote at NVIDIA GPU Technology Conference in D.C.Jerry Lee
Presentation at NVIDIA GPU Technology Conference in D.C. on how the Cancer Moonshot Task Force under Vice President Biden is using AI to help end cancer as we know it. Dr. Lee will discuss global efforts to empower A.I. and deep learning for oncology with larger and more accessible datasets.
Making Radiology AI Models more robust: Federated Learning and other Approachesimgcommcall
Daniel Rubin discusses approaches for making AI models more robust by accessing larger amounts of medical image data. Centralized data pooling is challenging due to data sharing barriers. Federated learning, which trains models across sites without sharing patient data, is presented as an alternative. However, federated learning requires common data standards for image annotations. The talk explores existing annotation standards and tools that could enable federated learning to leverage multi-institutional medical image data for developing more generalizable AI models.
This document provides an agenda for the NCI Imaging Informatics Webinar held on July 6, 2020. The agenda included presentations on distributed learning of deep learning in medical imaging, an update on the MedICI website, an update on The Cancer Imaging Archive, and announcements about future community calls, the community call wiki page, and where recordings could be accessed. The next scheduled community calls were listed as August 3, 2020 and September 14, 2020.
The document discusses the American College of Radiology's (ACR) efforts to advance the appropriate use of data science and artificial intelligence in radiology. It provides details on ACR's Data Science Institute (DSI) programs and initiatives to help define, validate, and monitor AI algorithms. These include ACR Define-AI, ACR Assess-AI, and ACR Certify-AI. The DSI aims to establish ACR as a leader in the radiology AI ecosystem and ensure the safe, effective integration of AI into clinical practice and medical education. The rest of the document discusses ACR's AI-LAB program to pilot AI algorithms and collect clinical feedback at partner sites.
The document summarizes the agenda for an NCI Imaging Informatics Webinar on April 6, 2020. The webinar included presentations on PathPresenter, a web-based digital pathology and image viewer, and an update on The Cancer Imaging Archive. It was announced that the webinar recordings and slides would be made available online on the NCI Imaging Community Call Wiki page and SlideShare account. The next webinars were scheduled for May 4 and June 1, 2020.
The Medical Segmentation Decathlon provides a benchmark for evaluating the generalizability of semantic segmentation algorithms across a variety of anatomical structures and imaging modalities. The Decathlon includes 10 segmentation tasks with over 2,600 unique patient datasets. In Phase 1 of the challenge, participants developed algorithms to segment the structures and submitted results for evaluation. The top performing methods for each task are identified based on Dice scores and boundary accuracy metrics. Phase 2 will involve applying the previously developed algorithms to new datasets without modifications, to further evaluate generalizability.
The January 6, 2020 Imaging Community Call featured presentations on the Medical Segmentation Decathlon, Imaging Data Commons updates, NBIA updates, and TCIA updates. Announcements were made about recording the presentations, the community call wiki page with recordings and slides, and the next scheduled community calls in February and March 2020.
NCI Cancer Research Data Commons - Overviewimgcommcall
The NCI Cancer Research Data Commons aims to enable sharing of diverse cancer research data across institutions by providing easy access to data stored in domain-specific repositories through a common authentication and authorization mechanism. It utilizes a framework of reusable components including data nodes, a cancer data aggregator, and cloud resources to integrate genomic, imaging, proteomic, and other data types while controlling access. The goals are to facilitate discovery and analysis tools as well as sustainably sharing data publicly to advance cancer research.
Imaging Data Commons (IDC) - Introduction and intital approachimgcommcall
The document introduces the Imaging Data Commons (IDC) which will connect researchers to cancer image collections, metadata, and tools for searching, viewing, and analyzing imaging data and related data types. The IDC will build on existing technologies and collaborations, with an initial focus on radiology and pathology images stored in DICOM format. It will utilize public cancer image collections from the Cancer Imaging Archive and integrate with other nodes in the Cancer Research Data Commons. The team has experience with open-source imaging tools, cloud infrastructure, and standards development. The initial implementation phases will focus on defining the data model and use cases, evaluating existing tools, and developing a minimal viable product hosted on the Google Cloud platform.
The document outlines the agenda for an Imaging Community Call on July 1, 2019. The agenda included welcome remarks, overviews of the Clinical Proteomic Tumor Analysis Consortium project and how its image, proteomic, and genomic data can be accessed through various data portals. It concluded with announcements about joining a community call group, an imaging community call wiki, and details on the next call in August 2019 focusing on tissue cytometry presentations.
The document discusses the Office of Cancer Clinical Proteomics Research (OCCPR) and its tumor characterization programs, including the Clinical Proteomic Tumor Analysis Consortium (CPTAC). CPTAC applies proteogenomics to characterize tumors and generate public resources of proteomic and genomic data. It builds on data from The Cancer Genome Atlas (TCGA) by characterizing proteins and genes to understand cancer. CPTAC data, along with clinical and genomic data, can be found on the Genomic Data Commons (GDC) portal. The document provides information on accessing, exploring, and analyzing CPTAC and other proteomic data deposited on the GDC.
CPTAC Data Portal and Proteomics Data Commonsimgcommcall
The CPTAC Data Coordinating Center houses proteomic datasets from CPTAC studies in its public data portal and assay portal. It analyzes data through a common pipeline and enables high-speed access. The Proteomic Data Commons is being developed to provide unified access to mass spectrometry data from multiple sources and allow analysis tools to access data in the cloud. It currently hosts data from CPTAC studies and is working to integrate with other cancer research data clouds. The goal is to improve data sharing, reuse and reproducibility across proteomic studies.
The National Cancer Institute’s Clinical Proteomic Tumor Analysis Consortium (CPTAC) is a national effort to accelerate the understanding of the molecular basis of cancer through the application of large-scale proteome and genome analysis, or proteogenomics.
The PRISM semantic integration approach aims to integrate diverse datasets from The Cancer Imaging Archive by representing data using shared ontologies. This removes obstacles to combining data about the same individuals from different sources. The Arkansas Image Enterprise System (ARIES) is an instance of PRISM that integrates imaging, clinical, and cognitive data from three Parkinson's disease cohorts. Semantic representation allows linking image volumes to cognitive assessments across cohorts. Ongoing work expands data integration and develops semantic query tools.
New manual contours for evaluating lung segmentation algorithms, additional MRI sequences for prostate data, and three new pathology datasets were added to TCIA. Diffusion and dynamic contrast MRI were added to the QIN-Prostate-Repeatability collection. 2018 Crowds Cure Cancer data was also released. The CPTAC lung adenocarcinoma proteomics/clinical discovery cohort data is now available. An upcoming Community Call will discuss the CPTAC program and data access policies. Multiple TCIA datasets were used in an AI cancer detection paper covered by major media outlets. A paper also discussed vulnerabilities in radiomic signature development using the NSCLC dataset. The NBIA data portal was updated with species selection and automatic inclusion of annotation files.
The document summarizes the agenda for an Imaging Community Call on June 3, 2019. The agenda included welcome remarks, updates on the PRISM project and TCIA, and announcements. The announcements section provided information on joining the community call mailing list, the Imaging Community Call Wiki page, and the next scheduled call on July 1, 2019.
This document summarizes the new features and improvements in the NBIA 7.0 GA Community Version release, including a new search interface, support for fielded text search, an improved data retriever application, upgrades for better Java support, and testing of load balancing capabilities. It also provides information on how to obtain the community version release and where to find additional documentation and support resources.
The document summarizes the agenda for an Imaging Community Call on May 6, 2019. The agenda included welcome remarks, updates on ITCR, TCIA, CPTAC SIG, and NBIA 7.0GA, and announcements. Under announcements, it invites the community to future calls, topics for discussion, and links to the community call wiki and SlideShare page for presentation materials. The next scheduled calls were for June 3rd with a PRISM update and July 1st.
Nano-gold for Cancer Therapy chemistry investigatory projectSIVAVINAYAKPK
chemistry investigatory project
The development of nanogold-based cancer therapy could revolutionize oncology by providing a more targeted, less invasive treatment option. This project contributes to the growing body of research aimed at harnessing nanotechnology for medical applications, paving the way for future clinical trials and potential commercial applications.
Cancer remains one of the leading causes of death worldwide, prompting the need for innovative treatment methods. Nanotechnology offers promising new approaches, including the use of gold nanoparticles (nanogold) for targeted cancer therapy. Nanogold particles possess unique physical and chemical properties that make them suitable for drug delivery, imaging, and photothermal therapy.
Breast cancer: Post menopausal endocrine therapyDr. Sumit KUMAR
Breast cancer in postmenopausal women with hormone receptor-positive (HR+) status is a common and complex condition that necessitates a multifaceted approach to management. HR+ breast cancer means that the cancer cells grow in response to hormones such as estrogen and progesterone. This subtype is prevalent among postmenopausal women and typically exhibits a more indolent course compared to other forms of breast cancer, which allows for a variety of treatment options.
Diagnosis and Staging
The diagnosis of HR+ breast cancer begins with clinical evaluation, imaging, and biopsy. Imaging modalities such as mammography, ultrasound, and MRI help in assessing the extent of the disease. Histopathological examination and immunohistochemical staining of the biopsy sample confirm the diagnosis and hormone receptor status by identifying the presence of estrogen receptors (ER) and progesterone receptors (PR) on the tumor cells.
Staging involves determining the size of the tumor (T), the involvement of regional lymph nodes (N), and the presence of distant metastasis (M). The American Joint Committee on Cancer (AJCC) staging system is commonly used. Accurate staging is critical as it guides treatment decisions.
Treatment Options
Endocrine Therapy
Endocrine therapy is the cornerstone of treatment for HR+ breast cancer in postmenopausal women. The primary goal is to reduce the levels of estrogen or block its effects on cancer cells. Commonly used agents include:
Selective Estrogen Receptor Modulators (SERMs): Tamoxifen is a SERM that binds to estrogen receptors, blocking estrogen from stimulating breast cancer cells. It is effective but may have side effects such as increased risk of endometrial cancer and thromboembolic events.
Aromatase Inhibitors (AIs): These drugs, including anastrozole, letrozole, and exemestane, lower estrogen levels by inhibiting the aromatase enzyme, which converts androgens to estrogen in peripheral tissues. AIs are generally preferred in postmenopausal women due to their efficacy and safety profile compared to tamoxifen.
Selective Estrogen Receptor Downregulators (SERDs): Fulvestrant is a SERD that degrades estrogen receptors and is used in cases where resistance to other endocrine therapies develops.
Combination Therapies
Combining endocrine therapy with other treatments enhances efficacy. Examples include:
Endocrine Therapy with CDK4/6 Inhibitors: Palbociclib, ribociclib, and abemaciclib are CDK4/6 inhibitors that, when combined with endocrine therapy, significantly improve progression-free survival in advanced HR+ breast cancer.
Endocrine Therapy with mTOR Inhibitors: Everolimus, an mTOR inhibitor, can be added to endocrine therapy for patients who have developed resistance to aromatase inhibitors.
Chemotherapy
Chemotherapy is generally reserved for patients with high-risk features, such as large tumor size, high-grade histology, or extensive lymph node involvement. Regimens often include anthracyclines and taxanes.
5-hydroxytryptamine or 5-HT or Serotonin is a neurotransmitter that serves a range of roles in the human body. It is sometimes referred to as the happy chemical since it promotes overall well-being and happiness.
It is mostly found in the brain, intestines, and blood platelets.
5-HT is utilised to transport messages between nerve cells, is known to be involved in smooth muscle contraction, and adds to overall well-being and pleasure, among other benefits. 5-HT regulates the body's sleep-wake cycles and internal clock by acting as a precursor to melatonin.
It is hypothesised to regulate hunger, emotions, motor, cognitive, and autonomic processes.
NAVIGATING THE HORIZONS OF TIME LAPSE EMBRYO MONITORING.pdfRahul Sen
Time-lapse embryo monitoring is an advanced imaging technique used in IVF to continuously observe embryo development. It captures high-resolution images at regular intervals, allowing embryologists to select the most viable embryos for transfer based on detailed growth patterns. This technology enhances embryo selection, potentially increasing pregnancy success rates.
These lecture slides, by Dr Sidra Arshad, offer a simplified look into the mechanisms involved in the regulation of respiration:
Learning objectives:
1. Describe the organisation of respiratory center
2. Describe the nervous control of inspiration and respiratory rhythm
3. Describe the functions of the dorsal and respiratory groups of neurons
4. Describe the influences of the Pneumotaxic and Apneustic centers
5. Explain the role of Hering-Breur inflation reflex in regulation of inspiration
6. Explain the role of central chemoreceptors in regulation of respiration
7. Explain the role of peripheral chemoreceptors in regulation of respiration
8. Explain the regulation of respiration during exercise
9. Integrate the respiratory regulatory mechanisms
10. Describe the Cheyne-Stokes breathing
Study Resources:
1. Chapter 42, Guyton and Hall Textbook of Medical Physiology, 14th edition
2. Chapter 36, Ganong’s Review of Medical Physiology, 26th edition
3. Chapter 13, Human Physiology by Lauralee Sherwood, 9th edition
Discover the benefits of homeopathic medicine for irregular periods with our guide on 5 common remedies. Learn how these natural treatments can help regulate menstrual cycles and improve overall menstrual health.
Visit Us: https://drdeepikashomeopathy.com/service/irregular-periods-treatment/
- Video recording of this lecture in English language: https://youtu.be/Pt1nA32sdHQ
- Video recording of this lecture in Arabic language: https://youtu.be/uFdc9F0rlP0
- Link to download the book free: https://nephrotube.blogspot.com/p/nephrotube-nephrology-books.html
- Link to NephroTube website: www.NephroTube.com
- Link to NephroTube social media accounts: https://nephrotube.blogspot.com/p/join-nephrotube-on-social-media.html
3. 3
New Data: SPIE-AAPM ProstateX Challenge
PROSTATEx Classification Challenge
• Release date of training set cases with truth: 21 Nov 2016
• Release date of test set cases without truth: 12 Dec 2016
• Submission date for participants’ test set classification output: 15 Jan 2017
• Challenge results released to participants: 20 Jan 2017
• SPIE Medical Imaging Symposium: 13-16 Feb 2017
142 participants registered already!
8. 8
New Features: NBIA 6.3 Additional API features
Alpha implementation of REST API for “restricted” collections
• Looking for potential testers and use cases
• https://wiki.nci.nih.gov/display/NBIA/NBIA+REST+API+User's+Guide
9. 9
New Features: TCIA Data Analysis Centers (DACs)
DACs are tools or websites which
provide advanced capabilities for
downloading, visualizing, or
analyzing TCIA data
DACs are not funded by TCIA, but serve
as a construct to enable the research
community to build upon TCIA’s existing
infrastructure (e.g. through ITCR grant
applications)
TCIA maintains a registry of DACs
to make them discoverable to users
under the “Data Access” menu
DACs may provide access to TCIA data
using the API or by mirroring their own
local copy of TCIA data
10. 10
New Features: BitTorious DAC
BitTorious is a holistic solution to
collaborative, private data transfer for
organizations needing to share epic
payloads across the Internet in a cost-
scalable, manageable, automated, and
easy-to-use platform.
Select TCIA collections are being
mirrored on BitTorious at
https://tcia.bittorious.com/.
• 4d-Lung
• Breast-Diagnosis
• Breast-MRI-NACT-Pilot
• TCGA-GBM
12. 12
1. Ahmadvand P, Duggan N, Bénard F, Hamarneh G, editors. Tumor Lesion Segmentation from 3D PET Using
a Machine Learning Driven Active Surface. International Workshop on Machine Learning in Medical Imaging;
2016: Springer.
2. Prasanna P, Patel J, Partovi S, Madabhushi A, Tiwari P. Radiomic features from the peritumoral brain
parenchyma on treatment-naïve multi-parametric MR imaging predict long versus short-term
survival in glioblastoma multiforme: Preliminary findings. European Radiology. 2016:1-10.
3. Jeanquartier F, Jean-Quartier C, Schreck T, Cemernek D, Holzinger A, editors. Integrating Open Data on
Cancer in Support to Tumor Growth Analysis. International Conference on Information Technology in Bio-
and Medical Informatics; 2016: Springer.
4. Song SE, Bae MS, Chang JM, Cho N, Ryu HS, Moon WK. MR and mammographic imaging features of HER2-
positive breast cancers according to hormone receptor status: a retrospective comparative study.
Acta Radiologica. 016:0284185116673119.
5. Chaddad A, Desrosiers C, Toews M, editors. Radiomic analysis of multi-contrast brain MRI for the
prediction of survival in patients with glioblastoma multiforme. Engineering in Medicine and Biology
Society (EMBC), 2016 IEEE 38th Annual International Conference; 2016.
6. Kotrotsou A, Zinn PO, Colen RR. Radiomics in Brain Tumors: An Emerging Technique for
Characterization of Tumor Environment. Magnetic Resonance Imaging Clinics of North America.
2016;24(4):719-29.
7. Zheng C, Wang X, Feng D, editors. Topology guided demons registration with local rigidity preservation.
Engineering in Medicine and Biology Society (EMBC), 2016 IEEE 38th Annual International Conference; 2016:
IEEE.
14. 14
TCIA-Sponsored Sessions
Imaging Integration with Cancer
Genomics/Proteomics: Methodologies Leveraging the
Cancer Imaging Archive
The Cancer Imaging Archive: Using 'Big Data' for the
study of Cancer Radiomics, Proteomics, Genetics and
Pathology (Hands-on)
15. 15
User Community Sessions
Posters/Exhibits
The Quantitative Image Feature Pipeline (QIFP) for Discovery, Validation, and
Translation of Cancer Imaging Biomarkers
Thursday 12:15-12:45 PM | IN251-SD-THA2 | IN Community, Learning Center
Station #2
Reproducibility of CT Texture Parameters by Leveraging Publically Available Patient
Imaging Datasets
Thursday 12:15-12:45 PM | IN255-SD-THA6 | IN Community, Learning Center
Station #6
Interoperable Communication of Quantitative Image Analysis Results Using the
DICOM Standard
All Day | QRR003 | QIRR, Learning Center
Early Implementation of Radiomics into Clinical Use: How Radiomic Data Can
Change Clinical Care of Patients
All Day | IN109-ED-X
Radiogenomic Analysis of The Cancer Genome Atlas (TCGA)/The Cancer
Imaging Archive (TCIA) Head and Neck Squamous Cell Cancer (HNSCC)
Cohort: Correlations between Genomic Features and Quantitative Imaging
Features
Monday 10:30-10:40 AM | SSC08-01 | Room: S402AB
Radiogenomics Mapping of Non-small Cell Lung Cancer Shows Strong
Correlations between Semantic Image Features and Metagenes
Monday 11:20-11:30 AM | SSC08-06 | Room: S402AB
Targeting Glucose Metabolism in Brain Tumor Initiating Cells: An Novel
Therapeutic Approach for Radiosensitization
Monday 11:50-12:00 PM | MSRO25-09 | Room: S103CD
Practical Radiogenomics: Lessons Learned from the Cancer Genome Atlas
Tuesday 9:40-10:10 AM | RC305-06 | Room: S102AB
Comparison of Novel Multi-level Otsu and Conventional PET Segmentation
Methods for Measuring FDG Metabolic Tumor Volume in Patients with Soft
Tissue Sarcoma
Tuesday 11:20-11:30 AM | RC311-12 | Room: S505AB
16. http://cancerimagingarchive.net
John Freymann
Informatics Manager, Applied/Developmental Research Directorate
Frederick National Laboratory for Cancer Research
Leidos Biomedical Research, Inc.
Support to: Cancer Imaging Program/DCTD/NCI
Imaging Integration with Cancer Genomics/Proteomics:
Methodologies Leveraging The Cancer Imaging Archive
RSNA 2016, Thursday 8:30-10:00 AM | RCC51 | Room: S501ABC
17. 17
Welcome
• This meeting is a continuation of NCI-
AAPM off-site imaging genomics meetings
2011-2015.
• NCI Cancer Imaging
Program
• Paula Jacobs PhD
• Consultant
• C. Carl Jaffe MD
• FNLCR Informatics
• John Freymann
• Justin Kirby
• Brenda Fevrier-
Sullivan
• UAMS
• PI – Fred Prior
• ..And countless
voluntary researchers
from around the globe
18. 18
Premise of the TCIA-TCGA project:
Imaging can improve the
pace and accuracy of
genomic discoveries:
Temporal context
Spatial context
Additional biomarkers
Non invasive alternatives
Genomic Features
Clinical
Features
Pathology Features
Imaging
Features
Needed: Big Data and Open Science
19. 19
Prerequisite 3: Open Science
• Voluntary, Opt-in, Multi-
institutional Groups from data-
supply sites
• Multi-disciplinary:
• Radiology, Oncology Informatics
Statistics Genomics
• Incentives:
• First opportunity to publish
• Chance to become a thought leader
20. 20
10 minute presentations
1. Qualitative Process
2. Quantitative Analysis
3. Statistics
4. Proteomics
5. Deep Learning
•Juan Ibarra,
MD
Baylor College of
Medicine
TCGA Imaging Bladder Research
Group Progress Update
•Sandy
Napel, PhD
Stanford
University
Stanford’s Quantitative Image
Feature Pipeline for Radiomics
Research and Translation
•Erich Huang,
PhD
National
Cancer
Institute
Statistical Methodology for
Analyzing TCIA Imaging Data
•Evis Sala,
MD, PhD
Memorial Sloan
Kettering
Ovarian cancer: the role of
imaging in interrogating tumor
biology and genomics/proteomics
•Maryellen
Giger, PhD
University of
Chicago
Imaging-Genomics Research in
Breast Cancer: Past & Future
Analyses
21. 21
Using Big Data for the study of Cancer Radiomics,
Proteomics, Genetics, and Pathology (HandsOn
Intro – overview of scope and intent of archive
Publishing data
Browsing for data
What kinds of 'omics/path data do we have?
Searching/filtering data
Other ways to access the data
Q&A