Medical Imaging De-Identification Workshop (Overview)

Overview

Access Workshop Recordings and Slides Here

The Center for Biomedical Informatics and Information Technology of the National Cancer Institute (NCI) invites you to attend this virtual Medical Imaging De-Identification (MIDI) workshop focused on public sharing of imaging data.

Medical imaging data are important to diagnose, treat, and research diseases. Sharing imaging data can facilitate research and discoveries while promoting collaboration. However, medical images often contain sensitive information such as personally identifiable information (PII) or protected health information (PHI) in both the pixel data and file header. Therefore, sensitive information removal, as known as de-identification, is critical before sharing images publicly.

Manual de-identification is time-consuming, tedious, and laborious. As such, a semi- or full-automatic de-identification is highly desired. Artificial intelligence (AI), and machine learning (ML) algorithms may be deployed in the cloud to de-identify medical images, offering scalable and traceable solutions.

The primary emphasis of the workshop is on medical images with accompanying data elements, especially those in formats in which the data elements are embedded, particularly DICOM.

The goals of the two-day workshop are to:

  • Share best practices and recommendations for medical imaging de-identification, as identified by the MIDI Task Group convened by the NCI.
  • Learn about approaches to conventional image de-identification in the United States, the European Union, and Canada.
  • Discuss approaches to image de-identification by industry.
  • Explore the roles of statistical risk analysis, de-facing, and AI in de-identification.

For further information, or questions about the MIDI workshop, please contact the NCI CBIIT MIDI Group.

Workshop Program Chairs:

Keyvan Farahani, National Heart, Lung, and Blood Institute & National Cancer Institute, National Institutes of Health

David Clunie, PixelMed

Fred Prior, University of Arkansas Medical Sciences

Will Parker, University of British Columbia

Juergen Klenk, Deloitte Consulting

Adam Taylor, Sage Bionetworks

Ying Xiao, Hospital of the University of Pennsylvania

Judy Gichoya, Emory University