Robust retinal biometrics for patient identity verification and retrieval across age and imaging devices
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a system that uses pictures of the back of the eye (retina) to check if a patient's identity is correct in medical records. They trained a computer model on a large number of retinal images from different studies, devices, and over many years. This system was very accurate at confirming identities and finding the right patient, even with long time gaps and different image qualities. It also helped find some mistakes in patient labeling in the datasets. The authors show that retinal patterns are reliable for protecting patient identity in medical records over time.
retinal biometricpatient identity verificationcolor fundus imagesmetric learningConvNeXtV2ArcFace losstriplet lossAUROCRecall@1longitudinal imaging
Authors
Jose D. Vargas-Quiros, Dennis Bontempi, Jeroen Vermeulen, Bart Liefers, Sven Bergmann, Caroline C. W. Klaver
Abstract
Patient identity errors can compromise longitudinal medical records, research databases, and downstream clinical decisions. We present a retinal biometric system for verifying claimed identities and retrieving the correct identity from color fundus images. We trained a 512-dimensional metric-learning encoder combining a ConvNeXtV2 backbone with ArcFace and triplet losses on 227,004 images from 21,851 patient-eye identities in the Rotterdam Study, spanning multiple imaging devices and up to 32.6 years of follow-up. The system was evaluated on held-out Rotterdam Study data and externally on the UK Biobank and Age-Related Eye Disease Study (AREDS). Before evaluation, we used the model to screen for identity inconsistencies and manually adjudicated flagged images, identifying incorrect assignments in 0.588% of Rotterdam Study images, 0.259% of UK Biobank images, and 0.164% of AREDS images. In retrospective-only verification after removing near-duplicate images, the system achieved AUROCs of 0.9998, 0.9997, and 0.9998 in the Rotterdam Study, UK Biobank, and AREDS, respectively. For identity retrieval using only previously acquired images, Recall@1 was 99.7%, 97.2%, and 97.6%, respectively, from galleries averaging 4436-8510 identities; the correct identity appeared among the top five results in at least 98.6% of cases. Performance remained robust across imaging devices and long follow-up intervals, while lower image quality and inconsistent retinal fields accounted for most failures. These findings establish retinal anatomy as a durable biometric signal, useful for safeguarding the integrity of longitudinal imaging records.