- THIS EVENT HAS BEEN CANCELED -

Artificial Intelligence / deep learning is a modern machine learning approach that has seen tremendous innovation in the last few years. Specifically, it has revolutionized the field of computer vision—making practical technologies out of what seemed like science fiction just a few years ago. There is a general sense of optimism that these same technologies may be fruitfully applied in medical imagine to improve accuracy and efficiency of reading services.

10:15 AM
Introduction from the Chair

Kyle Myers Senior Advisor, Division of Imaging, Diagnostics, and Software Reliability Office of Science and Engineering Laboratories, Center for Devices and Radiological Health FDA (United States)

10:30 AM
Impact of Artificial Intelligence and Analytics to Ophthalmology

Supriyo Sinha Dir. of Applied Research and Head of Optical Engineering & Mechanical Engineering Twenty/Twenty Therapeutics (United States)

Impact of Artificial Intelligence and Analytics to Ophthalmology
Great strides have been made in the last decade in applying digital health and machine learning to ophthalmology; however, the field is in its infancy in demonstrating real world impact on the visual health of patients. The continually improving quality of image sensors and other hardware coupled with the availability of ever-increasing computational power at low cost promise a tipping point in delivering significant improvements to eyecare. The outputs of these software algorithms can increase our understanding of ophthalmic disease progression, determine the most effective course of treatment and allow for democratization of these technologies across the world. We will discuss how companies such as Twenty/Twenty Therapeutics plan to combine hardware and software to be able to maximize the impact of artificial intelligence on eye health.

Bio: Supriyo Sinha is a Director and founding member of Twenty/Twenty Therapeutics where he applies software, electronics, mechanical engineering and optics to create ophthalmic medical devices. Before joining Twenty/Twenty, Dr. Sinha was a founding member of Verily Life Sciences, where he worked on microscopy discovering platforms and robotic surgical systems. Prior to Verily, Dr. Sinha held positions at Synaptics and Raydiance. He received his PhD from Stanford University (2007) developing high power laser and nonlinear optical systems. Dr. Sinha has over 20 patents (issued and pending) and has published over 50 journal articles and conference abstracts.

10:45 AM
Graphs and AI for Healthcare

Ana Areias Data Scientist Kineviz (Portugal)

Graphs and AI for Healthcare
In this talk, we will survey applications of graph technology to leverage high-dimensional and connected data in the medical space. We’ll review examples of graph-powered deep learning, ML, visualization, analytics, and some of the open source and commercially available tools used for this work.

Bio: As Data Scientist for Kineviz, Ana Areias works with merging deep learning and graph technologies in GraphXR to better understand high dimensional and interconnected data. A Harvard MPA-ID grad, she has worked on poverty prediction and big data for labor at the World Bank, has been a fellow at Data Incubator, was part of DataCorps with DataKind and Program Manager at Data-Pop Alliance.

11:00 AM
University of Chicago, MIDRC, Qlarity Imaging

Maryellen Giger Dept. Radiology, Com Medical Physics, The University of Chicago PI at MIDRC Advisor at Qlarity Imaging (United States)

AI in Medical Imaging of COVID-19 and Role of MIDRC
MIDRC is a multi-institutional collaborative initiative driven by the medical imaging community and is aimed at accelerating the transfer of knowledge and innovation in the current COVID-19 pandemic and beyond. MIDRC, funded by NIBIB is co-led by the American College of Radiology® (ACR®), the Radiological Society of North America (RSNA), and the American Association of Physicists in Medicine (AAPM). The aim of MIDRC is to foster machine learning innovation through data sharing for rapid and flexible collection, analysis, and dissemination of imaging and associated clinical data by providing researchers with unparalleled resources in the fight against COVID-19. Beyond its public Open Commons, one of the unique attributes of MIDRC is that it has a Sequestered Commons consisting of sequestered MIDRC data for use in testing, and which will provide a valuable resource for translation of AI algorithms through regulatory, leading to clinical use for improved public health.

Bio: Maryellen Giger, Ph.D. is the A.N. Pritzker Distinguished Service Professor of Radiology, Committee on Medical Physics, and the College at the University of Chicago. She has been working, for decades, on computer-aided diagnosis/machine learning/deep learning in medical imaging for cancer and other diseases diagnosis and management. Her AI research in breast cancer for risk assessment, diagnosis, prognosis, and therapeutic response has yielded various translated components, and she has now extended her AI in medical imaging research to include the analysis of COVID-19 on CT and chest radiographs, and is contact PI on the NIBIB-funded Medical Imaging and Data Resource Center (MIDRC; midrc.org). Giger is a member of the National Academy of Engineering (NAE); a former president of AAPM and of SPIE; is a member of the NIBIB Advisory Council of NIH; and is the Editor-in-Chief of the Journal of Medical Imaging. Giger was cofounder of Quantitative Insights [now Qlarity Imaging], which produces QuantX, the first FDA-cleared, machine-learning driven CADx (AI-aided) system.

11:15 AM
Using AI to Improve Accuracy and Access to Dermatological Care

Yuan Liu Software Engineer Google Health (United States)

Using AI to Improve Accuracy and Access to Dermatological Care
Skin diseases are an enormous global burden that affects 2 billion people worldwide, but a critical shortage of dermatologists can cause wait times to be months to a year. Recent progress in Artificial Intelligence (AI) has enabled developing medical imaging AI systems that reach clinical expert level performance across several imaging modalities. In this talk, we will introduce how Google is using AI to improve accuracy and access to dermatological care. In particular, we will focus on the research and development of an AI-powered dermatology assistive tool and how it’s benefiting users and clinical systems.

Bio: Yuan Liu is the technical lead and manager of the dermatology AI team in Google Health. She currently leads various dermatology related research and development efforts, with a focus on building AI assistant tools to improve the world’s access to accurate information and care for everyone. She also worked on applying computer vision techniques for large-scale user generated content in Google Maps. Prior to joining Google, she obtained her PhD in medical image processing at Vanderbilt University, where she conducted intelligent analysis of radiology images (CT, MRI) to advance image-guided neurosurgical procedures. She serves as a co-chair for the ISIC workshop at CVPR, and a guest editor for Medical Image Analysis.

11:30 AM
Panel Discussion
After the talks, all speakers will join the stage for panel discussion and Q&A.