A DICOM Image De-identification Algorithm in the MIDI-B Challenge

2025-08-10

AI Summary

This study addresses privacy compliance challenges in public sharing of DICOM medical images, targeting stringent regulatory standards including HIPAA, DICOM PS3.15, and TCIA. We propose a multi-strategy de-identification framework that jointly applies pixel-level masking (to protect pixel-domain protected health information, PHI), date shifting and hashing (to ensure temporal anonymity), and OCR-based, regex-driven metadata cleansing (to precisely locate and redact textual PHI). This integrated approach enables systematic anonymization of both pixel data and metadata while preserving clinical utility. Experimental evaluation on the MIDI-B challenge demonstrates 99.92% operational accuracy—ranking second among ten participating teams—validating the method’s efficacy, robustness, and practical deployability in large-scale, real-world clinical imaging scenarios.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Medical and Biological Imaging
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Image de-identification is essential for the public sharing of medical images, particularly in the widely used Digital Imaging and Communications in Medicine (DICOM) format as required by various regulations and standards, including Health Insurance Portability and Accountability Act (HIPAA) privacy rules, the DICOM PS3.15 standard, and best practices recommended by the Cancer Imaging Archive (TCIA). The Medical Image De-Identification Benchmark (MIDI-B) Challenge at the 27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024) was organized to evaluate rule-based DICOM image de-identification algorithms with a large dataset of clinical DICOM images. In this report, we explore the critical challenges of de-identifying DICOM images, emphasize the importance of removing personally identifiable information (PII) to protect patient privacy while ensuring the continued utility of medical data for research, diagnostics, and treatment, and provide a comprehensive overview of the standards and regulations that govern this process. Additionally, we detail the de-identification methods we applied - such as pixel masking, date shifting, date hashing, text recognition, text replacement, and text removal - to process datasets during the test phase in strict compliance with these standards. According to the final leaderboard of the MIDI-B challenge, the latest version of our solution algorithm correctly executed 99.92% of the required actions and ranked 2nd out of 10 teams that completed the challenge (from a total of 22 registered teams). Finally, we conducted a thorough analysis of the resulting statistics and discussed the limitations of current approaches and potential avenues for future improvement.

Problem

• Develop algorithm to de-identify DICOM medical images
• Ensure compliance with HIPAA and DICOM privacy standards
• Balance patient privacy with medical data utility

Innovation

• Pixel masking for image de-identification
• Date shifting and hashing techniques
• Text recognition and replacement methods