Toward AI-Ready Medical Imaging Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nikolov, Milen, Amorim, Edilberto, Caufield, J Harry, Gim, Nayoon, Harris, Nomi L, Houghtaling, Jared, Li, Xiang, Morrison, Danielle, Rameau, Anaïs, Shaffer, Jamie, Trivedi, Hari, Munoz-Torres, Monica C
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909941784117248
author Nikolov, Milen
Amorim, Edilberto
Caufield, J Harry
Gim, Nayoon
Harris, Nomi L
Houghtaling, Jared
Li, Xiang
Morrison, Danielle
Rameau, Anaïs
Shaffer, Jamie
Trivedi, Hari
Munoz-Torres, Monica C
author_facet Nikolov, Milen
Amorim, Edilberto
Caufield, J Harry
Gim, Nayoon
Harris, Nomi L
Houghtaling, Jared
Li, Xiang
Morrison, Danielle
Rameau, Anaïs
Shaffer, Jamie
Trivedi, Hari
Munoz-Torres, Monica C
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03541
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward AI-Ready Medical Imaging Data
Nikolov, Milen
Amorim, Edilberto
Caufield, J Harry
Gim, Nayoon
Harris, Nomi L
Houghtaling, Jared
Li, Xiang
Morrison, Danielle
Rameau, Anaïs
Shaffer, Jamie
Trivedi, Hari
Munoz-Torres, Monica C
Other Quantitative Biology
H.4.0
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.
title Toward AI-Ready Medical Imaging Data
topic Other Quantitative Biology
H.4.0
url https://arxiv.org/abs/2512.03541