Toward AI-Ready Medical Imaging Data

TL;DR

This paper develops standardized data management procedures for medical imaging data, enhancing FAIR principles and facilitating AI readiness, especially for complex DICOM formats and emerging video modalities.

Contribution

It introduces novel SOPs for medical imaging data management, covering static and video modalities, and addresses challenges like data validation, de-identification, and interoperability.

Findings

Established SOPs for DICOM data management.

Validated de-identification techniques including facial defacing.

Applied SOPs to diverse imaging datasets, including ophthalmology retinal scans.

Abstract

Medical imaging data plays a vital role in disease diagnosis, monitoring, and clinical research discovery. Biomedical data managers and clinical researchers must navigate a complex landscape of medical imaging infrastructure, input/output tools and data reliability workflow configurations taking months to operationalize. While standard formats exist for medical imaging data, standard operating procedures (SOPs) for data management are lacking. These data management SOPs are key for developing Findable, Accessible, Interoperable, and Reusable (FAIR) data, a prerequisite for AI-ready datasets. The National Institutes of Health (NIH) Bridge to Artificial Intelligence (Bridge2AI) Standards Working Group members and domain-expert stakeholders from the Bridge2AI Grand Challenges teams developed data management SOPs for the Digital Imaging and Communications in Medicine (DICOM) format. We describe novel SOPs applying to both static and cutting edge video imaging modalities. We emphasize steps required for centralized data aggregation, validation, and de-identification, including a review of new defacing methods for facial DICOM scans, anticipating adversarial AI/ML data re-identification methods. Data management vignettes based on Bridge2AI datasets include example parameters for efficient capture of a wide modality spectrum, including datasets from new ophthalmology retinal scans DICOM modalities.