Overview
Seminar series focusing on topics related to the implementation and evaluation of AI in real-world scenarios.
Upcoming Events
Artificial Intelligence Models in Biomedical Image-Based Measurements
Friday, October 18, 2024
12-1 p.m. Pacific Time
Virtual Event
Register here
The deployment of Artificial Intelligence (AI) technology currently outpaces its rigorous test and evaluation. In bio-medical applications, AI-model image-based measurements can provide new quantitative measurements and predictions for diagnostic and treatment purposes, for instance, when assessing the quality of tissue engineering implants or using AI-enabled medical devices for automated diagnosis. In this seminar, Peter Bajcsy, PhD, Project Lead at the National Institute of Standards and Technologies (NIST), will examine efforts to utilize AI-based biomedical image analyses for predicting the functions of retinal pigment epithelial (RPE) implants from absorbance images. Following that, there will be discussion on the challenges of relying on AI-based analyses and approaches to mitigate the risks.
About Peter Bajcsy, PhD
Peter Bajcsy received his Ph.D. in Electrical and Computer Engineering in 1997 from the University of Illinois at Urbana-Champaign (UIUC) and his M.S. in Electrical and Computer Engineering in 1994 from the University of Pennsylvania (UPENN). He worked for machine vision, government contracting, and research and educational institutions before joining NIST in June 2011. At NIST, Peter has been leading efforts focusing on the application of computational science in metrology, specifically live cell, and material characterization at very large scales. Peter’s area of research is large-scale image-based analyses and syntheses using mathematical, statistical, and computational models while leveraging computer science fields, such as image processing, machine learning, artificial intelligence, computer vision, and pattern recognition. Peter has authored more than 50 papers in peer-reviewed journals, co-authored 10 books or book chapters, and more than 100 conference papers.
Additional sessions and topics to come:
- Examples of real-world AI projects at UCSF and Beyond
- AI Infrastructure and goverance at other hospitals and in the future
- LLMs for healthcare
- Methodological challenges in evaluating AI algorithms in real-world settings
- Artificial Intelligence (AI) Readiness at UCSF: Current State and Future Directions
Past Events
How are Medical AI Devices Evaluated, Updated, and Deployed?
September 13, 12-1 p.m. Virtual
Webinar Recording
UCSF AI Seminar Series returns for another year with an exciting lineup of events. Kicking off this year's seminars will be James Zou, PhD, an associate professor at Stanford University. His presentation will explore how medical AI devices are evaluated, updated, and deployed, presenting analyses of these questions using FDA documentations and large-scale insurance claims. Dr. Zou will also share his experience of bringing EchoNet, an AI model for analyzing cardiac ultrasound videos, from research to deployment; EchoNet was cleared by the FDA in April 2024. Finally, he will discuss the challenges and opportunities of deploying large language models.
Shaping the Responsible Adoption of AI in Healthcare
April 5th, 12-1 at Mission Hall
As the use of artificial intelligence (AI) moves from being a curiosity to a necessity, it is clear that the benefit obtained from using AI models to prioritize care interventions is an interplay of the model’s performance, the capacity to intervene, and the benefit/harm profile of the intervention. We will begin the conversation reviewing the necessary data strategy to enable organization wide AI adoption and leading into a discussion of the core intuition behind foundation models. After a brief review of the kinds of use-cases that AI can serve across multiple medical specialties, we will discuss Stanford Healthcare’s efforts to shape the adoption of health AI tools to be useful, reliable, and fair so that they lead to cost-effective solutions that meet health care's needs.
Lecturer
Dr. Nigam H. Shah, MBBS, PhD
Professor of Medicine, and of Biomedical Data Science
Chief Data Scientist, Stanford Healthcare
Associate Dean for Research, School of Medicine
Associate Director, Stanford Center for Biomedical Informatics Research
About
Dr. Nigam Shah is Professor of Medicine at Stanford University, and Chief Data Scientist for Stanford Health Care. His research group analyzes multiple types of health data (EHR, Claims, Wearables, Weblogs, and Patient blogs), to answer clinical questions, generate insights, and build predictive models for the learning health system. At Stanford Healthcare, he leads artificial intelligence and data science efforts for advancing the scientific understanding of disease, improving the practice of clinical medicine and orchestrating the delivery of health care. Dr. Shah is an inventor on eight patents and patent applications, has authored over 200 scientific publications and has co-founded three companies. Dr. Shah was elected into the American College of Medical Informatics (ACMI) in 2015 and was inducted into the American Society for Clinical Investigation (ASCI) in 2016. He holds an MBBS from Baroda Medical College, India, a PhD from Penn State University and completed postdoctoral training at Stanford University.
Artificial Intelligence (AI) and Data Science in the Medical Imaging of COVID and CANCER: MIDRC to the Real World
Artificial Intelligence in medical imaging involves research in task-based discovery, predictive modeling, and robust clinical translation. This presentation will discuss the development, validation, database needs, and ultimate future implementation of AI in the radiology workflow including examples from cancer and COVID-19, including the creation and benefits of MIDRC (midrc.org).
January 29, 2024
3 - 4 p.m.
In person: Genentech N114
Lecturer
Maryellen L. Giger, PhD
A.N. Pritzker Distinguished Service Professor of Radiology
University of Chicago
About
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, thoracic diseases, neuro-imaging, and other diseases diagnosis and management. Her AI research in cancer (breast cancer, thyroid cancer) for risk assessment, diagnosis, prognosis, and therapeutic response has yielded various translated components, and she has used these “virtual biopsies” in imaging-genomics association studies. She has 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), which has ingested more than 300,000 medical imaging studies, with currently more than 160,000 imaging studies publicly available for use by AI investigators. Giger has more than 280 peer-reviewed publications and has more than 30 patents, and has mentored over 100 graduate students, residents, medical students, and undergraduate students. Giger is a former president of AAPM and of SPIE; a past member of the NIBIB Advisory Council of NIH; and was the Editor-in-Chief of the Journal of Medical Imaging (2013-2023). She is a member of the National Academy of Engineering (NAE), a recipient of the AAPM William D. Coolidge Gold Medal, the SPIE Director’s Award, the SPIE Harrison H. Barrett Award in Medical Imaging, the RSNA’s Honored Educator Award, and the RSNA’s Outstanding Researcher Award, and is a Fellow of AAPM, AIMBE, SPIE, SBMR, IEEE, IAMBE, and COS. In 2013, Giger was named by the International Congress on Medical Physics (ICMP) as one of the 50 medical physicists with the most impact on the field in the last 50 years. Giger was cofounder of Quantitative Insights [now Qlarity Imaging], which produced QuantX, the first FDA-cleared, machine-learning driven CADx (AI-aided) system.
Join us for the the inaugural session of this seminar series will feature a panel discussion on the state of clinical AI at UCSF and review the school's progress in each aspect of being an AI-ready hospital, including data accessibility, infrastructure for model deployment and evaluation, and governance/organizational structures.
January 12, 2024
12 - 1 p.m.
In person: MH-1401 & 1402
Panelists
- Sara Murray, MD, MAS, Vice President and Chief Health AI Officer, Associate Chief Medical Information Officer, Inpatient Care, UCSF Health, Associate Professor of Clinical Medicine, Division of Clinical Informatics and Digital Transformation, Department of Medicine
- Ida Sim, MD, PhD, FACMI, Professor of Medicine and Computational Precision Health, UCSF, Chief Research Informatics Officer, Co-Director, UCSF UC Joint Program in Computational Precision Health
- Atul Butte, MD, Phd, Professor, Director of Bakar Computational Health Institute, Chief Data Scientist UC Health
- Mark Pletcher, MD, MPH, Professor and Chair, Department of Epidemiology and Biostatistics
Moderator
- Julia Adler-Milstein, Phd, Chief, Division of Clinical Informatics and Digital Transformation, Director, Center for Clinical Inforamtics and Improvement Research