Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
10-2021
Abstract
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.
Keywords
Anomaly detection, Unsupervised learning, Lesion detection and segmentation, Self-supervised pre-training, Colonoscopy
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces | Health Information Technology
Research Areas
Intelligent Systems and Optimization
Publication
Medical Image Computing and Computer-Assisted Intervention: MICCAI 2021: 24th International Conference, Strasbourg, France, September 27 - October 1: Proceedings
Volume
12905
First Page
128
Last Page
140
ISBN
9783030872397
Identifier
10.1007/978-3-030-87240-3_13
Publisher
Springer
City or Country
Cham
Citation
TIAN, Yu; PANG, Guansong; LIU, Fengbei; CHEN, Yuanhong; SHIN, Seon Ho; VERJANS, Johan W.; and SINGH, Rajvinder.
Constrained contrastive distribution learning for unsupervised anomaly detection and localisation in medical images. (2021). Medical Image Computing and Computer-Assisted Intervention: MICCAI 2021: 24th International Conference, Strasbourg, France, September 27 - October 1: Proceedings. 12905, 128-140.
Available at: https://ink.library.smu.edu.sg/sis_research/7035
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1007/978-3-030-87240-3_13
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons, Health Information Technology Commons