Constrained Contrastive Distribution Learning for Unsupervised Anomaly Detection and Localisation in Medical Images
This work addresses the problem of detecting subtle abnormalities in medical images without labeled abnormal data, which is crucial for health screening programs, but it appears incremental as it builds on existing contrastive learning and anomaly detection techniques.
The paper tackles the challenge of learning effective low-dimensional representations for unsupervised anomaly detection and localization in medical images, particularly for small lesions, and shows that their method outperforms state-of-the-art approaches on three colonoscopy and fundus screening datasets.
Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i.e., healthy) images to detect any abnormal (i.e., unhealthy) samples that do not conform to the expected normal patterns. UAD has two main advantages over its fully supervised counterpart. Firstly, it is able to directly leverage large datasets available from health screening programs that contain mostly normal image samples, avoiding the costly manual labelling of abnormal samples and the subsequent issues involved in training with extremely class-imbalanced data. Further, UAD approaches can potentially detect and localise any type of lesions that deviate from the normal patterns. One significant challenge faced by UAD methods is how to learn effective low-dimensional image representations to detect and localise subtle abnormalities, generally consisting of small lesions. To address this challenge, we propose a novel self-supervised representation learning method, called Constrained Contrastive Distribution learning for anomaly detection (CCD), which learns fine-grained feature representations by simultaneously predicting the distribution of augmented data and image contexts using contrastive learning with pretext constraints. The learned representations can be leveraged to train more anomaly-sensitive detection models. Extensive experiment results show that our method outperforms current state-of-the-art UAD approaches on three different colonoscopy and fundus screening datasets. Our code is available at https://github.com/tianyu0207/CCD.