Spatial–contextual variational autoencoder with attention correction for anomaly detection in retinal OCT images

• Published in: Computers in biology and medicine Vol. 152; p. 106328
• Main Authors: Zhou, Xueying, Niu, Sijie, Li, Xiaohui, Zhao, Hui, Gao, Xizhan, Liu, Tingting, Dong, Jiwen
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2023; Elsevier Limited
• Subjects: Ablation; Algorithms; Anomalies; Anomaly attention map; Anomaly detection; Biology; Error correction; Feature maps; Image segmentation; Information technology; Laboratories; Learning; Methods; Optical coherence tomography; Performance evaluation; Reconstruction; Retina; Retina - diagnostic imaging; Tomography; Tomography, Optical Coherence - methods; Variational autoencoder; Variational autoencoder; Optical coherence tomography; Anomaly attention map; Anomaly detection
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.106328

Anomaly detection refers to leveraging only normal data to train a model for identifying unseen abnormal cases, which is extensively studied in various fields. Most previous methods are based on reconstruction models, and use anomaly score calculated by the reconstruction error as the metric to tackle anomaly detection. However, these methods just employ single constraint on latent space to construct reconstruction model, resulting in limited performance in anomaly detection. To address this problem, we propose a Spatial–Contextual Variational Autoencoder with Attention Correction for anomaly detection in retinal OCT images. Specifically, we first propose a self-supervised segmentation network to extract retinal regions, which can effectively eliminate interference of background regions. Next, by introducing both multi-dimensional and one-dimensional latent space, our proposed framework can then learn the spatial and contextual manifolds of normal images, which is conducive to enlarging the difference between reconstruction errors of normal images and those of abnormal ones. Furthermore, an ablation-based method is proposed to localize anomalous regions by computing the importance of feature maps, which is used to correct anomaly score calculated by reconstruction error. Finally, a novel anomaly score is constructed to separate the abnormal images from the normal ones. Extensive experiments on two retinal OCT datasets are conducted to evaluate our proposed method, and the experimental results demonstrate the effectiveness of our approach. •Learning spatial and contextual manifolds of images by variational autoencoders.•Stably localizing abnormal regions in abnormal images in gradient-free way based on variational autoencoders trained with only normal images.•Enlarging the difference between reconstruction errors of normal images and those of abnormal ones.