Standardizing sharing of image data in pathology using DICOM format
Sharing standardized image-derived data in computational pathology using DICOM
Computer Vision and Pattern RecognitionArtificial IntelligenceMachine Learning
Summary
Collecting and sharing medical images from pathology helps create better computer tools to analyze diseases, but sharing detailed image results like marked regions or segments is hard. The authors converted several existing datasets into a common format called DICOM, used widely for medical images, to make sharing image-derived pathology data easier and more consistent. They also improved open-source tools to support this format and shared the converted data publicly. This work could make it simpler to develop and test computational pathology methods using large, standardized image data.
What this means in practice
- •For hospital data teams: Integrate standardized pathology image annotations into hospital imaging archives using the DICOM format to improve interoperability and data sharing.
- •For medical software developers: Build pathology image analysis tools that directly read and produce DICOM-compliant image-derived data for seamless compatibility with public datasets in the IDC.$Commercial implications: Enables creation and sale of clinical software integrating standardized pathology image annotations aligned with regulatory and interoperability standards.
Authors
Daniela P. Schacherer, Christopher P. Bridge, David Clunie, Igor Octaviano, André Homeyer, Markus D. Herrmann, Olivier Gevaert, Tabita Ghete, Markus Metzler, Henning Hoefener, Tahsin Kurc, Curtis Lisle, Kenneth Philbrick, Joel Saltz, Yuanning Zheng, Andrey Fedorov
Abstract
Development and evaluation of computational pathology methods require access to large and diverse datasets. Over the past decade, various initiatives invested significantly into collecting, centralizing, and sharing pathology imaging data. In contrast, sharing of image-derived data such as region-of-interest delineations or segmentation masks is less well developed. In this work, we describe our approach to encoding and sharing image-derived pathology data in a standardized manner within the National Cancer Institute (NCI) Imaging Data Commons (IDC), a platform that hosts and provides public access to de-identified radiology and pathology data. The IDC relies on the Digital Imaging and Communications in Medicine (DICOM) standard for data harmonization, yet the adoption of DICOM for pathology image-derived content has remained largely unexplored until now. Here, we present five representative datasets harmonized by conversion from their original representations into DICOM and shared publicly in the IDC. We demonstrate the benefits of this harmonization, describe contributions to critical open-source tooling, and discuss technical considerations relevant to broader adoption of DICOM for pathology image-derived data.