Self-supervised anomaly detection, staging and segmentation for retinal images

• Published in: Medical image analysis 2023-07, Vol.87, p.102805-102805, Article 102805
• Main Authors: Li, Yiyue, Lao, Qicheng, Kang, Qingbo, Jiang, Zekun, Du, Shiyi, Zhang, Shaoting, Li, Kang
• Format: Article
• Language: English
• Subjects: Anomaly detection; Anomaly segmentation; Anomaly staging; Retinal images
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2023.102805

Unsupervised anomaly detection (UAD) is to detect anomalies through learning the distribution of normal data without labels and therefore has a wide application in medical images by alleviating the burden of collecting annotated medical data. Current UAD methods mostly learn the normal data by the reconstruction of the original input, but often lack the consideration of any prior information that has semantic meanings. In this paper, we first propose a universal unsupervised anomaly detection framework SSL-AnoVAE, which utilizes a self-supervised learning (SSL) module for providing more fine-grained semantics depending on the to-be detected anomalies in the retinal images. We also explore the relationship between the data transformation adopted in the SSL module and the quality of anomaly detection for retinal images. Moreover, to take full advantage of the proposed SSL-AnoVAE and apply towards clinical usages for computer-aided diagnosis of retinal-related diseases, we further propose to stage and segment the anomalies in retinal images detected by SSL-AnoVAE in an unsupervised manner. Experimental results demonstrate the effectiveness of our proposed method for unsupervised anomaly detection, staging and segmentation on both retinal optical coherence tomography images and color fundus photograph images. •We propose to use self-supervised learning to obtain more prior semantic features for unsupervised anomaly detection.•We explore the relationship between the data transformations used in the self-supervised learning and the anomaly detection performance.•An unsupervised anomaly staging method is introduced to better understand the severity of the retinal disease.•A label-free anomaly segmentation method is proposed based on layer-wise grey scale comparisons between the original and the reconstructed images.