Workshop
Event Title
Public Workshop - Evolving Role of Artificial Intelligence in Radiological Imaging
February 25 - 26, 2020
- Date:
- February 25 - 26, 2020
- Time:
- 8:00 AM - 5:30 PM ET
- Location:
-
Event Location
The Food and Drug Administration (FDA) is announcing the following public workshop entitled "Evolving Role of Artificial Intelligence in Radiological Imaging." The intent of this public workshop is to discuss emerging applications of Artificial Intelligence (AI) in radiological imaging including AI devices intended to automate the diagnostic radiology workflow as well as guided image acquisition. The purpose of the workshop is to work with interested stakeholders to identify the benefits and risks associated with use of AI in radiological imaging. We also plan to discuss best practices for the validation of AI-automated radiological imaging software and image acquisition devices. Validation of device performance with respect to the intended use is critical to assess safety and effectiveness.
INTRODUCTION:
Artificial intelligence (AI), including machine learning technologies, has the potential to transform healthcare by deriving new and important insights from the vast amount of data generated during the delivery of health care every day. Radiological applications of AI-based technologies are numerous and expanding. These applications aim to automate and streamline tasks to improve efficiency, accuracy, and consistency. Early applications of AI in radiological imaging include computer aided-detection and diagnosis software (CADe and CADx). CADe and CADx software analyze radiological images to suggest clinically relevant findings and aid diagnostic decisions. Similarly, computer aided triage (CADt) software analyzes images to prioritize the review of images for patients with potentially time sensitive findings.
Large sets of widely available imaging data across imaging modalities have supported the development of AI based algorithms for these devices. While historically the information provided by these algorithms has augmented the tasks performed by radiologists, software developments now can enable the devices to perform certain tasks autonomously. The potential for independent action by these devices to bypass human clinical review is an important factor in their benefit-risk profile, and it heightens expectations for the safety and effectiveness of these devices.
Another area of growth is the use of AI to provide prescriptive guidance for the operator to acquire optimal images. The image quality of ultrasound imaging can be greatly influenced by how the operator uses a handheld probe. Clinical AI applications may assist the acquisition of standardized images independent of the operator, guiding both sonographers and non-experts in sonography, potentially including lay users, to acquire images with equivalent diagnostic quality. The addition of such clinical AI applications and the potential for new users of these devices, similarly affect the benefit risk profiles for these devices and the expectations for the safety and effectiveness of these devices.
Through this workshop, FDA is seeking to engage with stakeholders to explore benefits and risks of these evolving applications of AI in radiology. As the benefit-risk profile changes, it is critical to adapt the methods used to evaluate and characterize their performance. In this workshop, FDA is also seeking innovative and consistent ways to leverage existing methods and to develop new methods for validation of these AI-based algorithms and explore opportunities for stakeholder collaboration in these efforts.
During the workshop, we will be discussing specific topics outlined in the Agenda below.
- Date, Time, and Location
- Webcast
- Transcripts
- Agenda
- Registration
- Requests for Oral Presentations
- Submit Comments
- Contact
DATE, TIME, and LOCATION
This public workshop will be held on February 25, 2020 from 8:00 a.m. to 5:30 p.m. (EST) and February 26, 2020 from 9:00 a.m. to 5:00 p.m. (EST) at the following location:
Natcher Conference Center, Building 45
Ruth Kirschstein Auditorium
NIH Main Campus
National Institutes of Health, 9000 Rockville Pike, Bethesda MD 20892
NIH Campus Information, (e.g., local airports, directions, local hotels, etc.)
Bethesda Hotels Local to NIH Campus
American Inn of Bethesda
8130 Wisconsin Avenue, Bethesda, MD 20814
T: (301) 656-9300, F: (301) 656-2907
Bethesda Marriott Hotel
5151 Pooks Hill Road, Bethesda, MD 20814
T: (301) 897-9400, F: (301) 897-0192
Bethesda North Marriott & Conference Center
5701 Marinelli Road, N. Bethesda, MD 20852
T: (301) 984-0004, F: (301) 984-1209
Embassy Suites Hotel at the Chevy Chase Pavilion
4300 Military Road, NW, Washington, DC 20015
T: (202) 362-9300, F: (202) 686-3405
Double Tree Bethesda
8120 Wisconsin Avenue, Bethesda, MD 20814
T: (301) 652-2000, F: (301) 652-3806
Hilton Garden Inn Washington DC/Bethesda
7301 Waverly St., Bethesda, MD 20814
T: 1-800-230-4134, Group Sales: 1-800-906-2871
Hyatt Regency Bethesda
One Bethesda Metro Center, Bethesda, MD 20814
T: (301) 657-1234, F: (301) 657-6453
Marriott Suites Bethesda
6711 Democracy Blvd., Bethesda, MD 20817
T: (301) 897-5600, F: (301) 530-1427
Residence Inn by Marriott
7335 Wisconsin Avenue, Bethesda, MD 20814
T: (301) 718-0200, F: (301) 718-0679
WEBCAST
AGENDA
The following public workshop Agenda is current as of 2/28/2020 and subject to change. More information will be made available as presenters are confirmed.
February 25, 2020, Day 1
Day 1 Organizing Committee: Alex Cadotte PhD, Yanna Kang PhD, Berkman Sahiner PhD, Subok Park PhD, and Jennifer Segui (FDA)
8:00 – 8:15 AM |
Welcome Day 1 |
8:15 – 9:15 AM |
Responsible Innovation and Regulation of AI/ML in Radiological Imaging Software This session will provide an overview of the evolving role of AI in radiology and the medical device regulatory framework. |
8:15 – 8:35 AM |
Bakul Patel, MSEE, MBA, Director, Division of Digital Health, Center for Devices and Radiological Health (FDA) Tailoring FDA's Regulatory Framework to Encourage Responsible Innovation in AI/ML |
8:35 – 8:55 AM |
Ronald M. Summers, MD, PhD, FSAR, FAIMBE, Senior Investigator, Imaging Biomarkers and Computer-aided Diagnosis Lab, Radiology and Imaging Sciences, NIH Clinical Center (NIH) Artificial Intelligence in Radiology: Where Does It Stand and Where Is It Going? |
8:55 – 9:15 AM |
Robert Ochs, PhD, Deputy Director for Radiological Health, Office of In Vitro Diagnostics and Radiological Health (FDA) New Challenges in Regulating Artificial Intelligence in Radiological Imaging |
9:15 – 10:15 AM |
Emerging Trends in Radiological AI Software - Exploring Benefits and Risks Advances in AI technology are leading to an expanding role for AI throughout the diagnostic clinical workflow. In this session, we aim to identify scientific, clinical, and regulatory challenges for radiological AI software that is intended for increased automation of triage, detection, or diagnosis of disease based on the review of medical images. Presentations will discuss the impact of radiological AI software on standard of care, clinical benefit, and risk. |
9:15 – 9:35 AM |
Constance Lehman, MD, PhD, FACR, Professor of Radiology Harvard Medical School, Chief of Breast Imaging, Massachusetts General Hospital Clinical Insights on Autonomous AI Implementation: A Radiologist's Perspective |
9:35 – 9:55 AM |
Lisa M. Baumhardt, Sr. Manager of AI Regulatory Strategy, IBM Watson Health Imaging |
9:55 – 10:15 AM |
Joshua Schulman, PhD, VP Clinical, Regulatory, and Quality Affairs, MaxQ AI |
10:15 – 10:30 AM |
Morning break |
10:30 AM – 12:00 PM |
Emerging Trends in Radiological AI Software – Discussion Panel Participants in this moderated discussion panel include:
|
12:00 – 1:00 PM |
Lunch |
1:00 – 2:00 PM |
Public Presentations Scientific, Clinical & Regulatory Challenges for Radiological AI Software, R. Chad McClennan, MBA, President & CEO, koios AI in Dental Radiography, E. Gültürk, Head of Quality & Regulatory, videahealth AI-Assisted Autonomous Imaging: Brain MR, G. Srinivasan, MediYantri AI in Nuclear-Medicine Imaging: Opportunities and Risks, A. K. Jha, Assistant Professor of Biomedical Engineering, Washington University Will AI Make a Better Doctor? J. Weiner, Boca Raton Regional Hospital The Role of Medical Physics in Artificial Intelligence in Medical Imaging, C. H. McCollough, Professor of Medical Physics and Biomedical Engineering, Mayo Clinic NCI Image Repositories for Imaging AI, K. Farahani, National Cancer Institute The Importance of Data Quality and True Noise, P. Kinahan, Vice Chair of Radiology, University of Washington, Chair AAPM Research Committee, AAPM Metrology and Standards Subcommittee AI in Medical Imaging and Decision Support: The Perspective of the RSNA Quantitative Imaging Biomarkers Alliance (QIBA®), T. J. Hall, Vice-Chair RSNA-QIBA Deployment of AI in Hospitals: Considerations Beyond AI Models, B. Hashemian, MGH & BWH Center for Clinical Data Science; Partners Healthcare Medical Imaging AI - Data Standards, Kevin O’Donnell, Canon Medical Research USA Autonomous AI and Ethics: lessons from real world implementation: Role of Physicians, M.D. Abramoff, Founder and Executive Chairman, IDx |
2:00 – 3:25 PM |
Evaluation of AI Software for Radiological Applications Stakeholders across the medical imaging community are working to develop effective methods for the validation of radiological AI software. This session will feature a discussion of ongoing efforts to develop methods and standards for the validation of these medical devices and different roles stakeholders can play. Presentations will discuss individual and collaborative efforts to develop validation methods for imaging-related AI inside and outside the traditional medical imaging community. |
2:00 – 2:15 PM |
Nicholas Petrick, PhD, Deputy Director Division of Imaging, Diagnostics and Software Reliability, Office of Science and Engineering Laboratories (FDA) Pre- and Post-Market Evaluation of Autonomous AI/ML: Lessons Learned from Prior CAD Devices |
2:15 – 2:30 PM |
Matthew Diamond, MD, PhD, Medical Officer, Digital Health, Center for Devices and Radiological Health (FDA) |
2:30 – 2:50 PM |
Peter Chang, MD, Assistant Professor-in-Residence, Department of Radiological Sciences, Co-Director, Center for Artificial Intelligence in Diagnostic Medicine (CAIDM), University of California, Irvine Evolving Paradigms of Radiology AI Software - Current and Future Trends |
2:50 – 3:10 PM |
Laura P Coombs, PhD, VP, Data Science and Informatics, American College of Radiology and Keith Dreyer DO, PhD, FACR, FSIIM, Chief Data Science Officer, Partners Healthcare, Chief Science Officer, ACR Data Science Institute |
3:10 – 3:25 PM |
Robert Lindsey, PhD, Co-Founder & Chief Science Officer, Imagen Technologies |
3:25 – 3:40 PM |
Afternoon break |
3:40 – 5:20 PM |
Evaluation of AI Software for Radiological Applications- Discussion Panel Participants in this moderated discussion panel include:
|
5:20 – 5:30 PM |
Conclusion – Day 1 Summary |
February 26, 2020, Day 2
Day 2 Organizing Committee: Shahram Vaezy PhD, Marjan Nabili PhD, Tracy Gray, Jennifer Segui (FDA)
9:00 – 9:10 AM |
Welcome Day 2 |
9:10 – 9:50 AM |
Opportunities and Challenges in AI-Enabled Healthcare |
9:10 – 9:30 AM |
Anthony Samir, MD, Director of CURT and Service Chief, Body Ultrasound No-Human-in-the-Loop AI-enabled Healthcare: Risk, Rewards, and Regulation |
9:30 – 9:50 AM |
Randy King, Ph.D., Program Director, Ultrasound, Division of Applied Science and Technology and Behrouz Shabestari, Ph.D., Acting Director - Division of Health Informatics Technologies, Division of Applied Science & Technology (Bioimaging), National Institute of Biomedical Imaging and Bioengineering (NIBIB) Implications and Opportunities for AI Implementation in Diagnostic Medical Imaging |
9:50 – 10:50 AM |
Innovation in AI-Guided Image Acquisition Artificial intelligence may be applied in imaging to provide guidance for the operator to acquire optimal images and signals. The clinical applications include assisting sonography experts for standardization of image quality, helping non-experts in sonography for acquiring images with quality equivalent to those obtained by expert, and guiding novices, such as home users, for collecting images of diagnostic quality and value. In this session, we aim to identify scientific, clinical, and regulatory challenges for AI-Guided Image/Signal Acquisition systems. Presentations will discuss the impact of AI-Guided Image/Signal Acquisition systems on the standard of care, clinical benefits, and risks. |
9:50 – 10:05 AM |
Ha Hong PhD, Investigator, Co-founder, Caption Health Inc. Development and Validation of a Breakthrough AI-Guided Echocardiography System |
10:05 – 10:20 AM |
Benny Lam PhD, Principal Regulatory Affairs Specialist, AI/DH Regulatory Intelligence, Philips Ultrasound Deep Learning-enabled Ultrasound Imaging – Opportunities, Risks, and Challenges |
10:20 – 10:35 AM |
John Martin, MD, Chief Medical Officer, Butterfly Network Can machine learning tools bring diagnostic imaging to the home with safety and efficacy? |
10:35: 10:50 AM |
Mike Washburn, Chief Engineer, GE Healthcare - Ultrasound |
10:50 – 11:00 AM |
Morning Break |
11:00 – 11:45 AM |
AI-Guided Image Acquisition: Clinical and Patient Perspectives |
11:00 – 11:15 AM |
Helen Feltovich, MD MS, Attending Physician, Intermountain Healthcare, and Associate Research Scientist, Medical Physics, University of Wisconsin, Madison What's Real About Artificial Intelligence: A Clinician's Perspective |
11:15 – 11:30 AM |
Jean Lea Spitz, MPH, CAE, RDMS, Executive Director, Perinatal Quality Foundation |
11:30 – 11:45 AM |
Joshua Basile, Founder, Determined2Heal & SPINALpedia; Patient Perspectives: Real-Life Excitement and Concerns of Community-Based AI Imaging Isabella and Amy O'Brien, Youth Member and Parent, International Children's Advisory Network (iCAN) |
11:45 AM – 12:45 PM |
AI-Guided Image Acquisition - Discussion Panel Participants in this moderated discussion panel include:
|
12:45 – 1:45 PM |
Lunch |
1:45 – 2:45 PM |
Public Presentations Explainable AI and Regulation in Medical Devices, D. Ritscher, Senior Consult, Cambridge Consultants AI in Medicine: Not Optional, A. A. Patel, Chair, Department of Radiology, Medical Director – Artificial Intelligence, Vice Chair, Imaging Informatics, Medical Director – 3D Laboratory, Geisinger AI in Pediatric Radiology: Special Considerations, Ethics, and Explainability, A. Annapragada, Professor and Director of Basic Research in Radiology, The E.B.Singleton Department of Pediatric Radiology, Texas Children’s Hospital and Baylor College of Medicine Applications of AI to Ultrasonography, H. Sagreiya, Assistant Professor of Radiology, University of Pennsylvania AI software for image enhancement and better acquisition, E. Gong, Subtle Medical AI-enabled imaging acquisition, image transformation, and dose reduction, G. Zaharchuk, Professor of Radiology, Stanford University Build Trustworthy Medical Imaging AI. S. Wu, Associate Professor, Director, Intelligent Computing for Clinical Imaging (ICCI) Lab, Dept. Radiology, University of Pittsburgh How Investors Can Encourage Startups to Work Constructively with the FDA, A. A. Vidian, Partner, DCVC Connected Health Initiative, B. Scarpelli, Senior Global Policy Counsel NCI Funding Opportunities for Early, Mid, Advanced and Translational Stage AI Imaging Developments, G. Redmond, H. Baker, Imaging Technology Development Branch, National Cancer Institute |
2:45 – 3:45 PM |
Regulation of Imaging Devices Containing AI Software This session will feature a discussion of regulatory evaluation of AI-Guided Image Acquisition systems. Ongoing efforts to develop methods and standards for the verification and validation of AI-Guided Image Acquisition systems will be discussed. Some emphasis will be placed on use of these devices by non-expert clinicians and patients as well as use of image acquisition systems in extreme environments. Presentations will discuss individual and collaborative efforts to develop validation strategies for AI-Guided Image Acquisition inside and outside of the traditional medical imaging community. . |
2:45 – 3:00 PM |
Shahram Vaezy, PhD, Biomedical Engineer, Division of Radiological Health (FDA) Regulatory Considerations for AI-Guided Image Acquisition and Optimization |
3:00 – 3:15 PM |
Scott Paulson, Sr. Director of Regulatory Affairs and Quality Systems; Compliance Officer, FUJIFILM SonoSite |
3:15 – 3:30 PM |
Berkman Sahiner, PhD, Physicist, Division of Imaging, Diagnostics, and Software Reliability (FDA) |
3:30 – 3:45 PM |
Xin Feng, PhD, Human Factors and Reliability Engineering Team (FDA) Human Factors and Usability Engineering for AI-guided Acquisitions |
3:45 – 4:00 PM |
Andy Milkowski, Senior Director Ultrasound R&D, Siemens Healthineers |
4:00 – 4:45 PM |
Public Health and Regulation of Imaging Devices Containing AI Software - Discussion Panel Participants in this moderated discussion panel include:
|
4:45 – 5:00 PM |
Conclusion – Day 2 Summary Path Forward for AI in Radiological Imaging: Guidance & Autonomy |
Event Managerial and Supervisory Committee:
- Robert Ochs PhD, Deputy Director for Radiological Health, Office of In Vitro Diagnostics and Radiological Health (FDA)
- Thalia Mills PhD, Director, Division Radiological Health (FDA)
- Jessica Lamb PhD, Assistant Director (Acting), Mammography, Ultrasound, and Imaging Software Team, Division of Radiological Health (FDA)
- Laurel Burk PhD, Assistant Director, Diagnostic X-ray Systems Team, Division of Radiological Health (FDA)
- Robert Sauer, Deputy Director, Division of Program Operations and Management (FDA)
- Nicholas Petrick PhD, Deputy Director Division of Imaging, Diagnostics and Software Reliability, Office of Science and Engineering Laboratories (FDA)
- Matthew Diamond MD, PhD, Medical Officer, Digital Health, Center for Devices and Radiological Health (FDA)
- Michelle Tarver MD, PhD, Director, Patient Science & Engagement, Center for Devices and Radiological Health (FDA)
Transcripts
REGISTRATION
Registration is now closed as of February 14, 2020.
There is no fee to register for the workshop and registration will be on a first-come, first-served basis.
If you need special accommodations due to a disability, please contact Susan Monahan at 301-796-5661, at susan.monahan@fda.hhs.gov at least 7 days in advance of the meeting.
Registrants will receive confirmation when requests for participation have been accepted. Onsite registration will not be available.
REQUESTS FOR ORAL PRESENTATIONS
This public workshop includes a public comment session and topic-focused sessions. During online registration, you may indicate if you wish to present during a public comment session, and which topics you wish to address. All requests to make oral presentations must be received by January 10, 2020, 4 p.m. If selected for presentation, FDA will notify presenters by January, 24, 2020 and presentation materials must be emailed to RadAIWorkshop2020@fda.hhs.gov by February 5, 2020 to present at the event. No commercial or promotional material will be permitted to be presented or distributed at the public workshop.
If you require special accommodations due to a disability, or need additional information regarding registration, please contact Susan Monahan, Office of Communication and Education, Center for Devices and Radiological Health, Food and Drug Administration, 10903 New Hampshire Avenue, Bldg. 32, Silver Spring, MD 20993, 301-796-5661, Susan.Monahan@fda.hhs.gov
SUBMIT COMMENTS
Please submit your comments regarding the workshop to https://www.regulations.gov/, Docket No. FDA-2019-N-5592 by June 30, 2020.
Please refer to the instructions for submitting comments to the docket to ensure that your feedback is received.
Please be advised that as soon as a transcript is available, it will be posted in the Dockets and accessible at http://www.regulations.gov.
CONTACT
For questions regarding workshop content please contact RadHealth@fda.hhs.gov