In This Section

Program

Please Note: All session times for the AACR Virtual Special Conference: Artificial Intelligence, Diagnosis, and Imaging are U.S. Eastern Standard Time (EST).

WEDNESDAY, JANUARY 13, 2021

THURSDAY, JANUARY 14, 2021

WEDNESDAY, JANUARY 13, 2021  

Welcome and Opening Keynote 
9:30-10:15 A.M.


Welcome and Opening Remarks
Trevor J. Pugh, Princess Margaret Cancer Centre, Toronto, ON, Canada

Introduction of Keynote
Benjamin Haibe-Kains, Princess Margaret Cancer Centre, Toronto, ON, Canada

Keynote Address 
Artificial Intelligence in medicine and biomedical research
John Quackenbush, Harvard School of Public Health, Boston, Massachusetts

Break 
10:15-10:30 A.M.

Plenary Session 1: Learning from Images: Pathology 
Moderator: Thomas J. Fuchs, Icahn School of Medicine at Mount Sinai, New York, New York
10:30 A.M.-12 P.M. 

Interpretable prediction of molecular phenotypes in cancer with dense, high-resolution cell and tissue maps
Andrew H. Beck, PathAI, Cambridge, Massachusetts
(Not eligible for CME credit)

Unsupervised resolution of intra- and inter-tumoral heterogeneity using deep learning 
Phedias Diamandis, University of Toronto – University Health Network, Toronto, ON, Canada 

Title to be announced 
Thomas J. Fuchs, Icahn School of Medicine at Mount Sinai, New York, New York 

Real-time, point-of-care pathology diagnosis via embedded deep learning*
Bowen Chen, Harvard University, Cambridge, Massachusetts

Machine learning models to quantify lineage plasticity and neuroendocrine differentiation in high-grade prostate cancer*
Beatrice Knudsen, University of Utah and ARUP laboratories, Salt Lake City, Utah

BREAK 
12-12:15 P.M.
Plenary Session 2: Learning from Images: Radiomics 
Moderator: Hugo Aerts, Brigham and Women’s Hospital, Boston, Massachusetts
12:15-1:45 P.M. 

Deep learning radiomics in cancer imaging
Ahmed Hosny, Dana-Farber Cancer Institute, Boston, Massachusetts

Artificial intelligence in cancer imaging
Hugo Aerts, Brigham and Women’s Hospital, Boston, Massachusetts  

Radiomics: Transforming standard imaging into mineable data for diagnostic and theragnostic applications
Philippe Lambin, Maastricht University, Maastricht, The Netherlands

Radiomics and AI-based treatment decision support for non-small cell lung cancer*
Wei Mu, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida

Effect of breast cancer chemoprevention on a convolutional neural network-based mammographic evaluation using a mammographic dataset of women with atypical hyperplasia, lobular or ductal carcinoma in situ*
Julia E. McGuinness, Columbia University Irving Medical Center, New York, NY

Break
1:45-2 P.M.
Plenary Session 3: Learning from Images: Multiplex Imaging and Small Molecule Design
Moderator: Garry P. Nolan, Stanford University School of Medicine, Stanford, California
2-3:30 P.M.


High-parameter single-cell analysis has driven deep understanding of immune processes
Garry P. Nolan, Stanford University School of Medicine, Stanford, California

Mapping cell structure across scales by fusing protein images and interactions
Trey Ideker, UC San Diego School of Medicine, La Jolla, California 

Machine learning–enabled analysis of high-content imaging dataset: Progress and prospects
Mohammad Muneeb Sultan, insitro, South San Francisco, California

Leveraging graphs to do novel hypothesis and data-driven research using multiplex immunofluorescence images*
Christopher Innocenti, AstraZeneca, Gaithersburg, Maryland

Utilizing biological domain knowledge and machine learning methods to improve cellular segmentation on multiplex fluorescence and imaging mass cytometry datasets improves the quality of single-cell data obtained*
Trevor D. McKee, University Health Network, Toronto, ON, Canada

Break 
3:30-3:45 P.M.
Plenary Session 4: Learning from Genome Biology
Moderator: Trey Ideker, UC San Diego School of Medicine, La Jolla, California
3:45-5:25 PM

Combining multiplexed assays of variant effect and modeling to drive variant interpretation
Douglas M. Fowler, University of Washington, Seattle, Washington

Decoding the genome: Regulatory mutations in cancer
Olga Troyanskaya, Princeton University, Princeton, New Jersey  

Machine learning for improved management of patients with pancreatic cysts
Rachel Karchin, Johns Hopkins University, Baltimore, Maryland

Automatic tumor typing based on patterns of somatic passenger mutations
Gurnit Atwal, University of Toronto, Toronto, ON, Canada
Quaid Morris, Sloan Kettering Institute, New York, New York

Thursday, January 14, 2021

Panel 1: Development of Data Resources, Data Standards, Access Policy, Reproducibility, Benchmarking  
Moderator: Lincoln D. Stein, Ontario Institute for Cancer Research, Toronto, ON, Canada
9:30-11 A.M. 

Platforms to improve reproducibility in artificial intelligence research
Benjamin Haibe-Kains, University Health Network Princess Margaret Hospital, Toronto, ON, Canada 

The winding path to reproducibility in AI
Jeffrey Tullis Leek, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland

Plumbing the depths of the non-coding cancer genome
Lincoln D. Stein, Ontario Institute for Cancer Research, Toronto, ON, Canada  

ORCESTRA: A platform for orchestrating and sharing high-throughput multimodal data analyses*
Anthony Mammoliti, University Health Network, Toronto, ON, Canada

 

Break 
11–11:15 A.M.
Plenary Session 5: Learning from Clinical Genomics 
Moderator: Dana Pe’er, Memorial Sloan Kettering Cancer Center, New York, New York
11:15 A.M.–12:45 P.M.

Big pediatric cancer genomic data: Discovery, precision medicine, and data sharing
Jinghui Zhang, St. Jude Children’s Research Hospital, Memphis, Tennessee

Machine learning and AI in molecular pathology diagnostics and clinical management of cancer
Matija Snuderl, New York University Langone Medical Center, New York, New York
 
A dynamic view of tumor ecosystems
Dana Pe’er

Accurate quantification of tumor DNA in liquid biopsies using deep learning*
O. Alejandro Balbin, Novartis Institutes for Biomedical Research, Inc, Cambridge, Massachusetts

Genetic risk scores for breast cancer based on machine learning analysis of chromosomal-scale length variation*
James P. Brody, University of California, Irvine, Irvine, California

Break
12:45-1 P.M.
Plenary Session 6: Clinical Implementation of Machine Learning Models in Oncology 
Moderator: Constance Lehman, Massachusetts General Hospital, Boston, Massachusetts
1-2:30 P.M. 


AI in an imaging center: Challenges and opportunities
Constance Lehman, Massachusetts General Hospital, Boston, Massachusetts

Automated treatment planning and quality assurance in radiation oncology
Thomas Purdie, Techna Institute for the Advancement of Technology for Health, Toronto, ON, Canada  

Multi-scale modeling of cancer patients 
Olivier Gevaert, Stanford University, Stanford, California

Identifying new risk factors for early-onset CRC in population under 50 years old using EHR-based machine learning*
Taylor M. Parker, University of Florida, Gainesville, Florida
Michael B. Quillen, University of Florida, Gainesville, Florida

Developing an agnostic risk prediction model for Acute Kidney Injury in cancer patients using a machine learning algorithm from blood results data*
Lauren Scanlon, The Christie NHS Foundation Trust, Manchester, United Kingdom

Break 
2:30-2:45 P.M. 
Panel 2: Challenges and Opportunities in Machine Learning Algorithms for Cancer Research 
Moderator:Benjamin Haibe-Kains, University Health Network Princess Margaret Hospital, Toronto, ON, Canada
2:45-4:20 P.M. 


Towards robust image based models for cancer risk assessment
Regina Barzilay, Massachusetts Institute of Technology, Cambridge, Massachusetts

An interpretable deep learning system for automatic medical image segmentation
Bo Wang, University of Toronto, Toronto, ON, Canada

AI for regulatory science research at FDA 
Weida Tong, Food and Drug Administration-National Center for Toxicological Research, Jefferson, Arkansas

Towards verifying results from biomedical deep learning models using the UMLS: Cases of primary tumor site classification and cancer named entity recognition*
Theodore Gaelejwe, IBM Research, Johannesburg, South Africa

Closing Remarks 

*Short talk from proffered abstract