The Cancer Imaging Program
The Quantitative Imaging Network
The National Cancer Institute
Then: 1939
And Now: 2016
Annual Meeting
April 10 – 11, 2017
Abstracts
The 2017 Quantitative Imaging Network
Annual Meeting
Shady Grove Facility
NCI
Joseph F. Fraumeni Jr. Lecture Room
TE 406/408/410
Agenda and Abstracts
April 10 – 11, 2017
The Quantitative Imaging Network Annual Meeting
April 10 – 11, 2017
Agenda
Location: Joseph F. Fraumeni Jr. Lecture Hall (TE 406), Shady Grove Facility
DAY 1: Monday April 10, 2017
8:00 Introduction and Welcome
Paula Jacobs, Ph.D.
Associate Director, DCTD
8:10 Program Introduction
Robert Nordstrom, Ph.D.
Branch Chief, DCTD
Session 1: Translation of QIN tools into clinical settings
-
Theme: Establishing strategic partnerships and pathways to advance QIN tools into a clinical environment
-
Purpose: To incentivize QIN members to begin or continue the clinical translation of QI tools
8:15 Summary of the 2016 QIN-NCTN Planning Meeting
Larry Schwartz, MD
Chair, Prof. of Radiology
Columbia University
With Q/A
8:45 Overview of Pathways to Clinical Trials Project
Hui-Kuo Shu, MD, Ph.D. - Insights into clinical validation
Emory University
John Buatti, MD. - Potential Impact of Proven QIN tools
Chair, Dept. of Rad Oncology
University of Iowa
9:15 Response Assessment in Lymphoma - imaging criteria and guidelines
Bruce Cheson, MD
Georgetown University
9:35 Opportunities for multi-applications of QI tools
Maryellen Giger, Ph.D.
University of Chicago
9:50 ECOG-ACRIN plans for clinical testing of QIN tools
David Mankoff, MD, Ph.D.
ECOG-ACRIN Medical Foundation
**************************************************************************
10:15 BREAK:
Poster Session in Seminar Room 110
Tool Demos in Lecture Hall 406
Clinical Trial Design & Dev. Working group –
meet on 2nd floor West Wing in Room 910 / 912
**************************************************************************
11:20 PANEL SESSION
Purpose: Open forum to ask questions on the above or questions related to the translation of your tool
Moderator; Lori Henderson
Members: Drs. Schwartz, Kelloff, Shankar, Wahl, Shu, Mankoff, Buatti
**************************************************************************
12:00 Lunch
**************************************************************************
1:00 Presentation of the Young Investigator Award
Robert Nordstrom – Dr. Assaf Hoogi, Stanford University Awardee
1:20 CIP involvement in the Interagency Working Group on Medical Imaging
Janet Eary, MD.
Deputy Associate Director, DCTD
Session 2: Pathways to Clinical Utility
-
Theme: Continuation of QIN tools and methods for clinical decision support in oncology
-
Purpose: To incentivize the QIN community to benchmark, optimize and share clinical decision support tools and methods
1:30 New Funding Opportunity Announcements (PAR-17-128, PAR-17-129)
Robert Nordstrom, Ph.D.
Branch Chief, DCTD
1:45 Challenges and Collaborative Projects (CCPs): Platforms and resources
Keyvan Farahani, Ph.D.
Program Director, DCTD
2:00 CCP 1: PET segmentation challenge
Reinhard Beichel, Ph.D.
Prof. of Electrical and Computer Engineering
University of Iowa
**************************************************************************
2:30 BREAK:
Poster Session in Seminar Room 110
Tool Demos in TE 406
PET/CT Working Group meet on 2nd floor East Wing in Room 908
MRI Working Group meet on 2nd floor West Wing in Room 910 / 912
**************************************************************************
3:30 CCP 2: Breast MRI Metrics of Response (BMMR) Challenge
Despina Kontos, Ph.D.
University of Pennsylvania
Zheng Zhang, Ph.D.
Brown University
4:00 Panel discussion on Challenges
Purpose: Discussion on Challenges and their role in translation
Moderator: Keyvan Farahani
Members: ME Giger, W Huang, D Newitt, L Hadjiyski, D Goldgof, R Beichel
4:30 QIN Announcement of 2017 Executive Committee and Working Group Leaders
5:00 Adjourn for the Day
DAY 2: APRIL 11, 2017
8:00 Opening Remarks
Robert Nordstrom, Ph.D.
Branch Chief, DCTD
Session 3: Role of Informatics Technology in QIN
Theme: Informatics pipelines in quantitative imaging
Purpose: To introduce and discuss the role of informatics pipelines in quantitative imaging analysis and as a way to share software algorithms and tools
8:05 QIN applications of Pipelines in Bioinformatics
Bradley J. Erickson, MD, Ph.D.
Prof. of Radiology
Mayo Clinic, Rochester, MN
8:20 Quantitative Imaging feature pipeline
Sandy Napel, Ph.D.
Prof. of Radiology
Stanford University
8:35 BioInformatics and Data Sharing (BIDS) Working Group Demonstrations of a Quantitative Imaging Pipeline
9:15 Informatics Panel discussion
Purpose: Discuss the emerging role of informatics pipelines in QIN translational research
Moderator: Keyvan Farahani
Members: B Erickson, S Napel, J Kalpathy-Cramer, A Sharma, D Goldgof
**************************************************************************
10:00 Morning break
Poster Session in TE410
Tool Demos in TE 406
BIDS Working Group meet on 2nd floor West Wing in Room 910 / 912
**************************************************************************
10:45 Update on QIN/ITCR activities
Juli Klemm, Ph.D.
NCI / CBIIT
11:05 Open Session with a few ITCR members (Brief 5 Mins. Presentation for each speaker)
Moderator: Yantian Zhang
Speakers: Joel Saltz, Hugo Aerts, Andriy Fedorov, Christos Davatzikos,
John Flavin, Gordon Harris, Anant Madabhushi
11:45 Open Microphone Discussion
12:00 Lunch
Session 4: Joint CBIIT / QIN Collaborations
Theme: Meaningful ways to connect clinical data to imaging collections
Purpose: Present existing solutions to harmonize disparate clinical data sets
1:00 NCI CBIIT Update: Ongoing activities of interest to QIN
Ed Helton, Ph.D.
NCI / CBIIT
1:15 TCIA Update: Support for QIN collaborative projects, challenges and data sharing
John Freymann
CIP/Frederick National Lab
Justin Kirby
CIP/Frederick National Lab
1:45 Genomic Data Common (GDC) model for harmonizing diverse clinical data sets
Mark Jensen, Ph.D.
Leidos / Frederick National Lab
2:15 Coffee Break
2:30 Assessing gaps in the GDC model to support QIN clinical data sharing
David Clunie, Ph.D.
Pixelmed Publishing LLC
3:00 Implementing a clinical data sharing strategy for QIN/TCIA
Fred Prior, Ph.D.
Univ. of Arkansas
Ashish Sharma, Ph.D.
Emory University
3:30 Open Discussion: Preliminary thoughts/feedback on this path forward from QIN investigators
Moderators: Justin Kirby, John Freymann and Edward Helton
4:00 Program wrap-up and closing remarks
Table of Contents
Presentation Abstracts Section
Session 1: Translation of QIN tools into clinical settings
Summary of the 2016 QIN-NCTN Planning Meeting 2
Larry Schwartz, MD
Columbia University
Overview of Pathways to Clinical Trials Project 3
Insights into clinical validation
Hui-Kuo Shu, MD, Ph.D.
Emory University
Potential Impact of Proven QIN tools
John Buatti, MD.
University of Iowa
Response Assessment in Lymphoma - imaging criteria and guidelines 4
Bruce Cheson, MD
Georgetown University
Opportunities for Multi-applications of Quantitative Image Analysis 5
Methods and Tools across Modalities and Clinical Tasks
Maryellen Giger, Ph.D.
University of Chicago
ECOG-ACRIN plans for clinical testing of QIN tools 6
David Mankoff, MD, Ph.D.
ECOG-ACRIN Medical Foundation
Young Investigator presentation: 8
“Automated and adaptive segmentation of diverse cancer lesions
for treatment evaluation”
Assaf Hoogi, Ph.D.
Stanford University
CIP involvement in the Interagency Working Group on Medical Imaging
Janet Eary, MD.
NIH/NCI/DCTD
Session 2: Pathways to Clinical Utility
New Funding Opportunity Announcements:
PAR-17-128, PAR-17-129
Robert Nordstrom, Ph.D.
NIH/NCI/DCTD
Challenges and Collaborative Projects (CCPs): 10
Platforms and resources
Keyvan Farahani, Ph.D.
NIH/NCI/DCTD
PET segmentation challenge 11
Reinhard Beichel, Ph.D.
University of Iowa
Breast MRI Metrics of Response (BMMR) Challenge 12
Despina Kontos, Ph.D.
University of Pennsylvania
Zheng Zhang, Ph.D.
Brown University
Session 3: Role of Informatics Technology in QIN
QIN applications of Pipelines in Bioinformatics
Bradley J. Erickson, MD, Ph.D.
Mayo Clinic, Rochester, MN
Quantitative Imaging feature pipeline 14
Sandy Napel, Ph.D.
Stanford University
BioInformatics and Data Sharing (BIDS) Working Group
Demonstrations of a Quantitative Imaging Pipeline
Bradley J. Erickson, MD, Ph.D.
Mayo Clinic, Rochester, MN
Update on QIN/ITCR activities 16
Juli Klemm, Ph.D.
NIH/NCI/CBIIT
Session 4: Joint CBIT / QIN Collaborations
NCI CBIIT Update: Ongoing activities of interest to QIN 17
Ed Helton, Ph.D.
NCI / CBIIT
TCIA Update: Support for QIN collaborative projects, challenges
and data sharing 18
John Freymann
CIP/Frederick National Lab
Justin Kirby
CIP/Frederick National Lab
The Genomic Data Common (GDC) model for harmonizing diverse
clinical data sets 19
Mark Jensen, Ph.D
Leidos / Frederick National Lab
Assessing gaps in the GDC model to support QIN clinical data sharing 20
David Clunie
Pixelmed Publishing LLC
Implementing a clinical data sharing strategy for QIN/TCIA
Fred Prior, Ph.D.
Univ. of Arkansas
Ashish Sharma, Ph.D.
Emory University
Poster Session & Abstracts
Poster #
-
Somatic mutations drive distinct imaging phenotypes 22
in lung cancer: Dana Farber Cancer Institute
-
Highly accurate model for prediction of lung nodule malignancy 25
with CT scans: Arkansas State University
-
Radiomics of Non-Small Cell Lung Cancer (NSCLC): 27
H. Lee Moffitt Cancer Center & Research Institute
-
Baseline and delta radiomic features improve prediction 29
of lung cancer incidence from size-stratified nodules in
The National Lung Screening Trial (NLST): Univ. of South Florida
-
Quantitative CT Imaging for Response Assessment 31
when using Dose Reduction Methods: UCLA
-
Quantitative Volume and Density Response Assessment: 33
Sarcoma and HCC as a Model: Columbia University
-
Lesion volume Estimation from PET without Requiring 35
Segmentation: Univ. of British Columbia
-
Correcting PET images of hypoxia for tissue transport properties: 37
Princess Margaret Cancer Centre, Toronto, Canada
-
Impact of Experimental Settings on the Performance of PET 39
radiomics in Predicting EGFR Mutation Status: Dana Farber Cancer Inst.
-
Advanced PET/CT Imaging for Improving Clinical Trials: 40
Univ. of Washington at Seattle
-
Development of advanced whole brain 3D spectroscopic 42
MRI for the management of GBM patients: Emory Univ./Johns Hopkins
-
DSC-MRI in Brain Tumors: Distinction of Tumor from 44
Treatment Effect & Fractional Tumor Burden: Medical College of Wisconsin
Poster #
-
Quantitative MRI of Glioblastoma Response: Massachusetts General Hospital 46
-
Early Tumour Perfusion and Diffusion Evaluated in Multi-modal 47
Imaging following Radiosurgery for Metastatic Brain Cancer:
Princess Margaret Cancer Centre, UHN, Toronto, Canada
-
Predicting Response of Low Grade Gliomas to Therapy from 48
MRI Images using Convolutional Neural Networks (CNNs):
Mayo Clinic, Rochester, Minnesota
-
Determination of MGMT Methylation status of GBMs from MRI 49
using machine learning: Mayo Clinic, Rochester, Minnesota
-
Multi-Imaging Risk Biomarkers in Poor Prognostic 51
Head and Neck Cancer: Univ. of Michigan (team#3)
-
Quantitative Radiomics of Breast MRI: image analysis and machine 53
learning for imaging-genomic association discovery studies and
precision medicine: Univ. of Chicago, Illinois
-
Quantitative Image Analysis and Deep Learning in Breast Cancer 55
Diagnosis and Response to Therapy: Univ. of Chicago, Illinois
Quantitative Imaging for Assessing Breast Cancer Response to Treatment 57
NCI Quantitative Imaging Network: UCSF (Abstract only)
-
Shutter-Speed Model DCE-MRI for Assessment of Response to 59
Cancer Therapy: Oregon Health & Science Univ., Portland, Oregon
-
Quantification of hepatocellular carcinoma heterogeneity with 61
multi-parametric magnetic resonance imaging: Mount Sinai, NY, NY
-
Staging and monitoring of treatment response of bladder cancer 63
by using CDSS-S and CDSS-T decision support systems:
Univ. of Michigan (team#2)
-
Advancing Quantification of Diffusion MRI for Oncologic Imaging: 65
Univ. of Michigan (team#1)
Poster #
-
Predictive Radiomics, Pathomics, and Radiology-Pathology Fusion Tools: Applications to predicting treatment response in Brain, Rectal, and 67
Oropharyngeal Cancers: Case Western Reserve Univ.
-
Eureka! Clinical Analytics 69
Univ. of Arkansas at Little Rock
-
No-gold-standard evaluation of quantitative imaging biomarker quantification methods: Johns Hopkins University 71
-
Quantitative Imaging to Assess Response in Cancer Therapy Trials 73
The University of Iowa
-
Multi-parametric and Multimodality Quantitative Imaging for Evaluation of 75 Response to Cancer Therapy: Johns Hopkins Univ. & Washington University
-
Computing, Optimizing, and Evaluating Quantitative Cancer Imaging Biomarkers: The Stanford Quantitative Imaging Feature Pipeline (QIFP): 76 Stanford Univ.
-
Qualification and Deployment of Imaging Biomarkers of Cancer 78
Treatment Response: Stanford Univ.
-
ECOG-ACRIN QIN Resource for Advancing 79
Quantitative Cancer Imaging in Clinical Trials:
ECOG-ACRIN, Philadelphia, PA
Working Groups Posters
-
Clinical Trial Design and Development Working Group Update 2017 83
-
Bioinformatics / IT and Data Sharing Working Group Report 85
-
QIN PET-CT Subgroup – Overview of Activities 87
-
Standardizing Radiomic Feature Descriptions for Quantitative Imaging: 89
A Preliminary Report of the Cooperative Efforts of the NCI’s QIN
PET-CT Subgroup
-
MRI data acquisition CCPs on accuracy of T1 mapping and validation of 91
DWI bias correction
-
DSC & DCE Challenges and Collaborative Project Updates 93
-
DWI-Related Challenges and Collaborative Projects: 95
Apparent Diffusion Coefficient (ADC) Mapping and Parametric
ADC Map DICOM implementation
Demonstrations
Station #
-
Quantitative image analysis tools for assessing response 99
in cancer therapy trials: University of Iowa
-
Spectroscopic MRI Clinical Interface: Emory University 100
-
Observer Performance Evaluation of Bladder Cancer Treatment Response Assessment on CT scans using computerized decision support tool (CDSS-T): University of Michigan, Ann Arbor 101
-
Quantitative MRI of Glioblastoma response: The QTIM suite of image analysis tools: Mass. General Hospital 102
-
A Streamlined Workflow for Quantitative Assessment of Brain Tumor Burden Using FTB: Medical College of Wisconsin 103
-
Quantitative Volume and Density Response Assessment: Sarcoma and HCC as a Model: Columbia University Medical Ctr. 106
-
Computational Radiomics System to Decode the Radiographic Phenotype: Dana Farber & Brigham and Women’s Hospital 107
-
ePAD: Enabling imaging assessment of imaging biomarkers in the workflow of clinical trials: Stanford University 109
-
Open source tools for standardized communication of quantitative image analysis results: Brigham and Women’s Hospital 111
-
Data Visualization of QIN PET/CT working group challenges 113
QIN Tools involved in Prospective Clinical Trials 115
Appendix 1: Report on the December, 2016 QIN-NCTN Planning Meeting 119
Appendix 2: Agenda for the National Photonics Initiative Workshop: 143
Strategies for Improving Early Detection of Cancer and Response to Therapies
through Imaging Technologies
QIN and JMI to honor Dr. Larry Clarke in an upcoming special issue
The special issue will focus on quantitative imaging methods and translational developments.
The call for papers will be posted online by March 1st and will be open to submissions immediately. In addition, JMI invites papers based on presentations from the QIN annual meeting in April 2017.
Questions about the journal can be sent to JMI@spie.org.
Check the journal website http://spie.org/JMICalls for details.
Dr. Larry Clarke’s QIN Young Investigator Award Recipient:
Dr. Assaf Hoogi, Stanford University
Assaf Hoogi is currently a Postdoc fellow in the Quantitative Imaging Lab, school of Medicine at Stanford. Assaf received his MSc and PhD degrees in biomedical engineering from the Technion (Israel) in 2008 and 2013 respectively with specialization in image processing and computer vision. His research interests are in the areas of image understanding and characterization. In particular, Assaf focuses on developing new methods for adaptive lesion segmentation, disease prediction and treatment evaluation by exploring new directions of machine learning and computer vision techniques such as deep learning, sparse coding, deformable models, variational approaches and other cutting edge techniques.
During his PhD research, Assaf developed a semi-automatic algorithm to quantify intra-plaque neovasculature for evaluating plaque vulnerability, and assessed the risk of stroke by using Contrast Enhanced Ultrasound images of Carotid artery plaques. Assaf detected, segmented and tracked contrast spots over time on ultrasound images using segmentation and multidimensional dynamic programming techniques. Classification of contrast paths into blood vessels and artifacts was performed according to spatial criteria. His PhD was awarded among the five novel researches in the Technion during 2013. During his PhD, Assaf was also an intern fellow in the image processing group in Thorax center, Rotterdam, Netherlands.
During his postdoc fellowship, under the supervision of prof. Daniel Rubin, Assaf focuses on developing an adaptive segmentation framework for automated lesion annotation. An adaptive framework that can handle substantial diversity of image characteristics that will be highly desirable, and will supply far more general, fast, accurate and robust segmentation solution, than any ad-hoc designed platforms that are currently available. Such a technique requires a minimal user interaction and will be used as a tool to assess treatment efficacy. Except for lesion segmentation, Assaf also deals with disease prediction and survival analysis by using text and image longitudinal data. Assaf published his research in leading journals and conferences, including the MedIA, IEEE-TMI, MICCAI and NIPS.
Dostları ilə paylaş: |