International Multi-Centre Validation of Unsupervised Domain Adaptation for Precise Discrimination between Normal and Abnormal Retinal Development

Zhanhan Tu; Nikhil Reddy; Helen J. Kuht; Ha-Jun Yoon; Gail D. E. Maconachie; Ravi Purohit; Prateek Pani; Line Kessel

cs.CVOct 15, 2026

International Multi-Centre Validation of Unsupervised Domain Adaptation for Precise Discrimination between Normal and Abnormal Retinal Development

Authors: Zhanhan Tu, Nikhil Reddy, Helen J. Kuht, Ha-Jun Yoon, Gail D. E. Maconachie, Ravi Purohit, Prateek Pani, Line Kessel,

Organizations: The University of Leicester Ulverscroft Eye Unit, School of Psychology and Vision Sciences, University of Leicester, RKCSB, PO Box 65, Leicester, LE2 7LX, UK · International Institute of Information Technology, Gachibowli, Hyderabad - 500 032, India · inAmind Laboratory, Department of Neuroscience, Psychology and Behaviour, University of Leicester, George Davies Centre, Lancaster Road, Leicester, LE1 7RH, UK. · Academic Unit of Ophthalmology and Orthoptics, University of Sheffield, Sheffield, UK · Department of Ophthalmology, Copenhagen University Hospital, Rigshospitalet-Glostrup, Copenhagen, Denmark · The Department of Clinical Medicine, University of Copenhagen, Denmark · Institute of Vision Research, Department of Ophthalmology, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Korea; Foveal Development Investigators Group. · Sidney Kimmel Medical College of Thomas Jefferson University, Philadelphia, Pennsylvania; Nemours Children's Health, Wilmington, Delaware. · School of Computing and Mathematical Sciences, University of Leicester, LE1 7RH, UK. · Université Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, 38000, Grenoble, France. · Oxford Eye Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford, UK; Ophthalmology Department, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK. · Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK; Oxford University Hospitals NHS Foundation Trust, Oxford, UK; Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK. · Department of Ophthalmology, University Hospitals of Leicester, Infirmary Square, LE1 5WW, Leicester, UK. · School of Computer Science and Engineering, Southeast University, Nanjing, Jiangsu 211102, China

Abstract

Arrested retinal development can cause childhood visual impairment, but grading optical coherence tomography scans is difficult to standardise across devices and centres. We developed and evaluated an unsupervised domain adaptation model to classify normal and abnormal retinal development across different OCT systems. This retrospective multicentre study used OCT scans from five centres in four countries and the UK Biobank. Data covered four OCT devices, including table mounted and handheld systems. A ResNet50 based Domain Adversarial Neural Network was trained using labelled images from a source device and unlabelled images from a target device. We evaluated six source to target pairings and compared model performance with seven clinician graders. A separate Heidelberg Spectralis dataset was reserved for external evaluation. Across validation sets, accuracy ranged from 87.75% to 96.06%, sensitivity from 88.68% to 98.38%, and specificity from 78.00% to 98.02%. The best performing model, adapted from TM OCT1 to HH OCT1, achieved 96.06% accuracy and an area under the receiver operating characteristic curve of 0.994, with a 95% confidence interval from 0.981 to 0.999. Several models also maintained discrimination on the unseen Heidelberg device. Unsupervised domain adaptation enabled OCT classification across devices without labelled target device data. The approach may support more consistent assessment of retinal development and large scale analysis of existing imaging datasets.

Unsupervised Domain Adaptation

Unsupervised domain adaptation transfers models from labeled source data to unlabeled target domains with different data distributions.

See all 183 papers

Anatomy-Aware Unsupervised Detection and Localization of Retinal Abnormalities in Optical Coherence Tomography
Apr 24, 2026Tania Haghighi, Sina Gholami, Hamed Tabkhi +1Medical Imaging Medical Image Anomaly Detection
University of North Carolina at Charlotte Charlotte, NC, USA
Uncertainty-Aware Multi-Source Retinal Fluid Segmentation in OCT
Jul 9, 2026Animesh KumarDomain Adaptation Medical Imaging
Newcastle University, Newcastle upon Tyne NE1 7RU, United Kingdom
TRIAGE: Risk-Controlled Pseudo-Label Admission for Annotation-Efficient Semi-Supervised Retinal OCT Classification
Aug 14, 2026Md Ashraful Hossen Akash, Shyla Afroge, Abdullah Al Mamun +2Medical Image Classification Retinal Disease Classification
Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi-6204, Bangladesh · Elite Research Lab LLC, New York, USA · Faculty of Information Science and Technology, Multimedia University, Melaka, Malaysia +1

Apr 24, 2026J/K move · Enter open · S save

Anatomy-Aware Unsupervised Detection and Localization of Retinal Abnormalities in Optical Coherence Tomography

Tania Haghighi, Sina Gholami, Hamed Tabkhi, Minhaj Nur Alam

University of North Carolina at Charlotte Charlotte, NC, USA

Medical Imaging Medical Image Anomaly Detection Optical Coherence Tomography Anomaly Localization Reconstruction-Based Anomaly Detection Unsupervised Anomaly Detection

Open paper AskPDF arXiv

Reliable automated analysis of Optical Coherence Tomography (OCT) imaging is crucial for diagnosing retinal disorders but faces a critical barrier: the need for expensive, labor-intensive expert annotations. Supervised deep learning models struggle to generalize across diverse pathologies, imaging devices, and patient populations due to their restricted vocabulary of annotated abnormalities. We propose an unsupervised anomaly detection framework that learns the normative distribution of healthy retinal anatomy without lesion annotations, directly addressing annotation efficiency challenges in clinical deployment. Our approach leverages a discrete latent model trained on normal B-scans to capture OCT-specific structural patterns. To enhance clinical robustness, we incorporate retinal layer-aware supervision and structured triplet learning to separate healthy from pathological representations, improving model reliability across varied imaging conditions. During inference, anomalies are detected and localized via reconstruction discrepancies, enabling both image and pixel-level identification without requiring disease-specific labels. On the Kermany dataset (AUROC: 0.799), our method substantially outperforms VAE, VQVAE, VQGAN, and f-AnoGAN baselines. Critically, cross-dataset evaluation on Srinivasan achieves AUROC 0.884 with superior generalization, demonstrating robust domain adaptation. On the external RETOUCH benchmark, unsupervised anomaly segmentation achieves competitive Dice (0.200) and mIoU (0.117) scores, validating reproducibility across institutions.

Abstract

Unsupervised Domain Adaptation

Explore similar work

Anatomy-Aware Unsupervised Detection and Localization of Retinal Abnormalities in Optical Coherence Tomography

Uncertainty-Aware Multi-Source Retinal Fluid Segmentation in OCT

TRIAGE: Risk-Controlled Pseudo-Label Admission for Annotation-Efficient Semi-Supervised Retinal OCT Classification