Session Abstract – PMWC 2021 Silicon Valley


Sessions:

AI-Based Radiology and Digital Pathology Applications
Sharmila Majumdar, UCSF
Matthew Lungren , Stanford
Ismail Baris Turkbey, NIH
Anant Madabhushi, Case Western Reserve University
Lawrence Schwartz, Columbia University Medical Center
Jayashree Kalpathy-Cramer, Harvard

How Data Science Will Impact and Drive Diagnostics by Combining Radiology with Pathology and Genomics

Developing and Commercializing Clinically Relevant AI-Based Imaging Solutions
Kyung Hyun Sung, UCLA
Luis Pineda, Facebook AI Research

Regulatory Considerations for AI & Machine Learning in Medical Imaging
Matthew Diamond, FDA

How Do We Enable the Next Generation of Medical Imaging for Better Diagnosis and Prognosis

 Session Chair Profile

Ph.D., Vice Chair of Research, Radiology, UCSF

Biography
Sharmila Majumdar’s research work on imaging, particularly magnetic resonance and development of image processing and analysis tools, has been focused in the areas of osteoporosis, osteoarthritis, orthopedic imaging, and lower back pain. Her more recent focus has been on artificial intelligence applied to biomedical imaging. Her research is supported by grants from the NIH and corporate entities, and is diverse – ranging from technical development to clinical trials. She was selected as a fellow of the American Institute of Medical and Biological Engineers in 2004 and a fellow of the International Society of Magnetic Resonance in Medicine in 2008. In 2007, the UCSF Haile T. Debas Academy of Medical Educators at UCSF awarded her the “Excellence in Direct Teaching and/or Excellence in Mentoring and Advising Award”. She was awarded the ISMRM Gold medal in 2016. She has published extensively in highly regarded journals and serves as a reviewer and on the Editorial Board of multiple scientific journals.


 Session Chair Profile

M.D., Associate Director, Stanford Artificial Intelligence in Medicine and Imaging Center, Stanford University

Biography
Assistant Professor of Radiology and Biomedical Informatics (courtesy) at Stanford University and Associate Director of the Stanford Artificial Intelligence in Medicine and Imaging Center (AIMI). He is Principal Investigator on federally funded work focusing on integrating medical imaging data with clinical data to improve the delivery of medical imaging diagnostics on a global scale. His work is among the first to evaluate delivery of machine learning tools for medical imaging in a clinical setting and leads multi-institutional clinical trials for evaluation of new AI medical imaging tools in the clinical practice setting. He leads dozens of industry collaborations on medical imaging AI that feature co-engineering new applications to transform healthcare delivery. He has published over 75 scientific publications and his work is regularly featured in national news outlets such as The Wall Street Journal, VICE News, and NPR.


 Speaker Profile

Ph.D., Professor of Biomedical Engineering, Case Western Reserve University

Biography
Madabhushi’s team at the Center for Computational Imaging and Personalized Diagnostics (CCIPD) is developing and applying novel AI and computational imaging approaches for the diagnosis, prognosis and prediction of therapy response for a variety of diseases including oncology, cardiovascular, kidney and eye disease. Madabhushi has more than 100 patents and authored over 400 journal and conference papers. Madabhushi is a fellow of the American Institute of Medical and Biomedical Engineering and the Institute of Electrical and Electronics Engineers. Madabhushi’s work on “smart computers for identifying lung cancer patients who will benefit from chemotherapy” was ranked in the top 10 medical breakthroughs of 2018 by Prevention Magazine. In 2019, Nature Magazine called him out as one of five scientists pursuing truly offbeat and innovative approaches in cancer research. His work has been awarded >$60 million in grant funding, has co-founded two companies, and has had 15 of his technologies licensed.

Talk
Prognostic And Predictive Radiomics And Pathomics For Precision Oncology
Our group has been pioneering computerized feature analysis methods for extracting subvisual attributes for characterizing disease appearance and behavior on radiographic (radiomics) and digitized pathology images (pathomics). In this talk I will discuss how these radiomic and pathomic approaches can be applied to predicting disease outcome, recurrence, progression and response to therapy in the context of prostate, brain, rectal, oropharyngeal, and lung cancers. Additionally I will also discuss some recent work on looking at use of pathomics in the context of racial health disparity and creation of more precise and tailored prognostic and treatment response prediction models.


 Speaker Profile

M.D., Associate Research Physician, NIH

Biography
Dr. Turkbey obtained his medical degree from Hacettepe University in Ankara, Turkey in 2003. He completed his residency in Diagnostic and Interventional Radiology at Hacettepe University. He joined Molecular Imaging Program, National Cancer Institute, NIH in 2007. His main research areas are imaging of prostate cancer (multiparametric MRI, PET CT), prostate biopsy techniques, focal therapy for prostate cancer and image processing (segmentation, decision support systems).


 Speaker Profile

Ph.D., Associate Professor, UCLA

Biography
Dr. Sung received the M.S and Ph.D. degrees in Electrical Engineering from University of Southern California, Los Angeles, in 2005 and 2008, respectively. From 2008 to 2012, he finished his postdoctoral training at Stanford in the Departments of Radiology and joined the University of California, Los Angeles (UCLA) Department of Radiological Sciences in 2012 as an Assistant Professor. His research interest is to develop fast and reliable MRI methods that can provide improved diagnostic contrast and useful information. In particular, his group is currently focused on developing advanced quantitative MRI techniques for early diagnosis, treatment guidance, and therapeutic response assessment for oncologic applications.


 Speaker Profile

M.D., Radiology Department Chair, Columbia University Medical Center

Biography
Dr. Lawrence Schwartz is the James Picker Professor and Chairman for the Department of Radiology at Columbia University Medical Center. He also is the Chief of the Radiology Service and Attending Physician at New York-Presbyterian Hospital. Dr. Schwartz earned his medical degree at Boston University School of Medicine, completed an internship at Winthrop University Hospital, a residency at the New York Hospital - Cornell University Medical College and a fellowship specializing in Cross Sectional Imaging (MRI/US/CT) at Brigham and Women's Hospital and Harvard Medical School. He is a diplomate of the American Board of Radiology and a member of the American Roentgen Ray Society, Radiological Society of North America, International Society for Magnetic Resonance in Medicine, New York Roentgen Ray Society, Society for Computer Applications in Radiology and a Fellow at the International Cancer Imaging Society.


 Speaker Profile

Ph.D., Scientific Director, CCDS, Harvard

Biography
Jayashree Kalpathy-Cramer is the Director of the QTIM lab and the Center for Machine Learning at the Athinoula A. Martinos Center for Biomedical Imaging and an Associate Professor of Radiology at MGH/Harvard Medical School. Dr. Kalpathy-Cramer is also Scientific Director at MGH & BWH Center for Clinical Data Science. An electrical engineer by training, she worked in the semiconductor industry for a number of years. After returning to academia, she is now focused on the applications of machine learning and modeling in healthcare. Her research interests include medical image analysis, machine learning and artificial intelligence for applications in radiology, oncology and ophthalmology. The work in her lab spans the spectrum from novel algorithm development to clinical deployment. She is passionate about the potential that these techniques have to improve access to healthcare in the US and worldwide. Dr. Kalpathy-Cramer has authored over 100 peer-reviewed publications and has written over 10 book chapters.


 Speaker Profile

M.D., Ph.D., Medical Officer, Digital Health, FDA’s Center for Devices and Radiological Health

Biography
Matthew Diamond, MD, PhD serves as Medical Officer for Digital Health at FDA’s Center for Devices and Radiologic Health. In this role, Dr. Diamond leads a multi-disciplinary team of physicians, scientists, and engineers developing FDA policy on emerging technologies. He regularly provides consultation within and outside of the agency on digital health products, and he serves on center, agency, and international working groups, including on medical software standards and artificial intelligence. Dr. Diamond brings experience from his work at large and small technology companies, including as Chief Medical Officer at Nokia, and as Medical Director at Fossil Group and the startup Misfit Wearables. As Vice Chair of the Consumer Technology Association (CTA) Health & Fitness Technology Board, Dr. Diamond promoted public health applications of mobile technology, and he established an ANSI-accredited standardization committee to develop standards in digital health for wellness-related devices and apps. Dr. Diamond has served on numerous advisory boards including for the Center for Personalized Health Monitoring at UMass Amherst and for the venture firm NGP Capital. As a wearables expert, he was Chair of the USA Technical Advisory Group to the IEC Wearables Standards Committee TC124. Dr. Diamond earned his MD and PhD (biophysics) from the Mount Sinai School of Medicine, and he is board certified in rehabilitation medicine and sports medicine, with certification in medical acupuncture. A faculty member at NYU, Dr. Diamond is passionate about helping people improve their mobility and performance through a holistic approach to rehabilitation and technology that promotes wellness.


 Speaker Profile

Ph.D., Research Engineer, Facebook AI Research

Biography
Dr. Pineda's research involves the design and application of learning-based algorithms for sequential decision making under uncertainty. He is one of the first proponents of the use of deep reinforcement learning for active MRI acquisition, a data-driven approach to optimize acquisition trajectories on a per-patient basis. His goal is to eventually deploy adaptive MRI systems that can continuously select the best frequencies to scan as new information arrives, leading to lower scan times without loss in diagnostic quality. Prior to his current position at Facebook AI Research, he completed his Ph.D. at University of Massachusetts, Amherst in 2018.