The Medical Imaging De-Identification workshop is being offered to examine the state of the science for the de-identification of publicly released medical images. The primary emphasis is on medical images with accompanying data elements, especially those encoded in formats in which the data elements are embedded, particularly DICOM. The sessions described below make up the workshop.
DAY 1, May 22, 2023 (10:00 am to 2:00 pm EDT)
Welcome and Opening Comments
Dr. Farahani is the senior program director of data science, imaging, and AI at the National Heart, Lung, and Blood Institute. He's on detail at NCI CBIIT as a program director for imaging informatics and serves as the federal lead for several imaging projects, including the MIDI Initiative.
Session 1: Report of the MIDI Task Group - Best Practices and Recommendations
Session Chair: David Clunie, MBBS, PixelMed, LLC
In this session, David Clunie, chair of the MIDI Task Group, will summarize the best practices and recommendations included in the task group's report, recently available in pre-print, followed by a question and answer period.
Session 2: Tools for Conventional Approaches to De-Identification
Session Chair: Fred Prior, PhD, University of Arkansas for Medical Sciences
In this session, speakers will share methods currently in use for medical de-identification.
Break
Estimated at 11:55-12:05 p.m.
Session 3: International Approaches to De-Identification
Session chair: Will Parker, MD, DABR, FRCPC, University of British Columbia
This session will focus on requirements for de-identification outside of the United States.
Session 4: Industry Approaches to De-Identification
Session chair: Keyvan Farahani, PhD, Center for Biomedical Informatics and Information Technology, National Cancer Institute, National Institutes of Health
Industry has a role to play in de-identification, developing tools that protect human identity in medical images. This session will feature presentations by industry groups that examine their approaches and offerings.
Closing Remarks
David Clunie, MBBS, PixelMed, Inc.
DAY 2, May 23, 2023 (10:00 am to 2:00 pm EDT)
Welcome and Recap
David Clunie, MBBS, PixelMed, LLC
Session 5: Pathology Whole Slide Image De-Identification
Session chair: Adam Taylor, PhD, Sage Bionetworks
In this session, researchers will discuss pathology whole slide image de-identification.
Session 6: De-facing
Session chair: Ying Xiao, PhD, Hospital of the University of Pennsylvania
This session will focus on balancing the risks of removing potentially reconstructable facial information in head and neck cross-sectional images, also called de-facing, with the diminished utility of these images caused by restricted access to them.
Break
Estimated at 11:50 a.m. - 12:00 p.m.
Session 7: The Role of Artificial Intelligence in De-Identification
Session chair: Judy Wawira Gichoya, MD, MS, Emory University
In this session, researchers discuss the utility and risk of using algorithms from machine learning (ML) and artificial intelligence (AI) to de-identify medical images.
Session 8: Panel Discussion
Session chair: Jürgen Klenk, PhD, Deloitte Consulting LLP
Discussion of the approaches and challenges identified during the workshop and opportunities for the future.
Closing Remarks
David Clunie, MBBS, PixelMed, LLC
Keyvan Farahani, PhD, NCI
