A No-Code Tool for De-identification of Digital Imaging and Communications in Medicine Whole-Slide Images: DICOM-WSI-De-Identifier

Context.— Pathology departments transitioning to a digital workflow are encouraged to adopt the digital imaging and communications in medicine (DICOM) format for routine diagnosis, leading to a substantial increase in histopathological image-based research projects using this format. Nevertheless, DICOM for whole-slide images (WSIs) remains an emerging file type, with few tools currently available for de-identification that do not require coding skills. Objective.— To develop an easy-to-use, no-code tool for de-identifying DICOM WSIs and providing feedback on the de-identification process. Design.— An open-source and Python-based solution, with detailed explanations, is proposed to de-identify DICOM WSI files, relying on the Pydicom package. The de-identification process removes the label image and the macro/overview image, and modifies DICOM metadata in accordance with the DICOM Basic Application Level Confidentiality Profile. The native Python script was converted with PyInstaller into executables compatible with Windows and macOS. Tests for residual protected health information were performed using 2 distinct open-source solutions. Results.— The solution was tested on 73 DICOM slides coming from 5 major vendors (Leica, 3DHistech, Roche, Hamamatsu, and Olympus/Evident), encompassing brightfield and fluorescence modalities, single- and multi-plane acquisitions, and single- and multi-plex images. Average de-identification time did not exceed 1 or 2 s/GB. The executables can be used without any coding expertise, while providing access to the remaining metadata for compliance verification. Conclusions.— An efficient solution for de-identifying DICOM WSI is presented, addressing a practical need among pathologists who lack programming skills but wish to use digitized slides for research and educational purposes.

Authors

Institutions

Publication Details

Journal
Archives of Pathology & Laboratory Medicine
Published
2026-11-14
DOI
https://doi.org/10.5858/arpa.2026-0099-oa
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A No-Code Tool for De-identification of Digital Imaging and Communications in Medicine Whole-Slide Images: DICOM-WSI-De-Identifier

Bertrand Chauveau
Archives of Pathology & Laboratory Medicine
AI in cancer detection
article

A No-Code Tool for De-identification of Digital Imaging and Communications in Medicine Whole-Slide Images: DICOM-WSI-De-Identifier

Bertrand Chauveau
article en

Abstract

Context.— Pathology departments transitioning to a digital workflow are encouraged to adopt the digital imaging and communications in medicine (DICOM) format for routine diagnosis, leading to a substantial increase in histopathological image-based research projects using this format. Nevertheless, DICOM for whole-slide images (WSIs) remains an emerging file type, with few tools currently available for de-identification that do not require coding skills. Objective.— To develop an easy-to-use, no-code tool for de-identifying DICOM WSIs and providing feedback on the de-identification process. Design.— An open-source and Python-based solution, with detailed explanations, is proposed to de-identify DICOM WSI files, relying on the Pydicom package. The de-identification process removes the label image and the macro/overview image, and modifies DICOM metadata in accordance with the DICOM Basic Application Level Confidentiality Profile. The native Python script was converted with PyInstaller into executables compatible with Windows and macOS. Tests for residual protected health information were performed using 2 distinct open-source solutions. Results.— The solution was tested on 73 DICOM slides coming from 5 major vendors (Leica, 3DHistech, Roche, Hamamatsu, and Olympus/Evident), encompassing brightfield and fluorescence modalities, single- and multi-plane acquisitions, and single- and multi-plex images. Average de-identification time did not exceed 1 or 2 s/GB. The executables can be used without any coding expertise, while providing access to the remaining metadata for compliance verification. Conclusions.— An efficient solution for de-identifying DICOM WSI is presented, addressing a practical need among pathologists who lack programming skills but wish to use digitized slides for research and educational purposes.

Archives of Pathology & Laboratory Medicine
Université de Bordeaux (FR), Hôpital Pellegrin (FR)
AI in cancer detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon