DICODerma: A practical approach for metadata management of images in dermatology

TL;DR

Dermatology lacks standardized imaging metadata, hindering scale and AI-ready data workflows. The authors propose a practical design that embeds essential DICOM metadata into EXIF as JSON (via DICODerma) and exposes an ImageJ plugin (DIT4IJ) to tag, search, and convert images to DICOM, enabling enterprise-imaging interoperability with minimal disruption to clinicians. Built on open-source components like dcm4che and ImageJ, the approach aims to improve patient privacy, data sharing, and ML-ready datasets within an encounter-based workflow. This work presents a feasible, low-barrier path to standardizing dermatology imaging data and sketches a roadmap toward vendor adoption and specialty-specific IOD development.

Abstract

Clinical images are vital for diagnosing and monitoring skin diseases, and their importance has increased with the growing popularity of machine learning. Lack of standards has stifled innovation in dermatological imaging, unlike other image-intensive specialties such as radiology. We investigate the meta-requirements for utilizing the popular DICOM standard for metadata management of images in dermatology. We propose practical design solutions and provide open-source tools to integrate dermatologists' workflow with enterprise imaging systems. Using the tool, dermatologists can tag, search, organize and convert clinical images to the DICOM format. We believe that our less disruptive approach will improve the adoption of standards in the specialty.

Figures (2)

• Figure 1: Mapping of DICOM tags to JSON for inclusion in the UserComment EXIF tag
• Figure 2: The DIT4IJ interface for adding tags to an image