Re-identification from histopathology images

Abstract

In numerous studies, deep learning algorithms have proven their potential for the analysis of histopathology images, for example, for revealing the subtypes of tumors or the primary origin of metastases. These models require large datasets for training, which must be anonymized to prevent possible patient identity leaks. This study demonstrates that even relatively simple deep learning algorithms can re-identify patients in large histopathology datasets with substantial accuracy. We evaluated our algorithms on two TCIA datasets including lung squamous cell carcinoma (LSCC) and lung adenocarcinoma (LUAD). We also demonstrate the algorithm's performance on an in-house dataset of meningioma tissue. We predicted the source patient of a slide with F1 scores of 50.16 % and 52.30 % on the LSCC and LUAD datasets, respectively, and with 62.31 % on our meningioma dataset. Based on our findings, we formulated a risk assessment scheme to estimate the risk to the patient's privacy prior to publication.

20 pages, 7 figures, 2 tables

References in corpus (9)

• DINOv2: Learning Robust Visual Features without Supervision
• Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary
• TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
• Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge
• Mitosis domain generalization in histopathology images -- The MIDOG challenge
• Palmprint Recognition in Uncontrolled and Uncooperative Environment
• Deep Learning-based Patient Re-identification Is able to Exploit the Biometric Nature of Medical Chest X-ray Data
• Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset
• Anonymization of Whole Slide Images in Histopathology for Research and Education