Publication Type
Journal Article
Version
submittedVersion
Publication Date
12-2023
Abstract
Unsupervised anomaly detection (UAD) methods are trained with normal (or healthy) images only, but during testing, they are able to classify normal and abnormal (or disease) images. UAD is an important medical image analysis (MIA) method to be applied in disease screening problems because the training sets available for those problems usually contain only normal images. However, the exclusive reliance on normal images may result in the learning of ineffective low-dimensional image representations that are not sensitive enough to detect and segment unseen abnormal lesions of varying size, appearance, and shape. Pre-training UAD methods with self-supervised learning, based on computer vision techniques, can mitigate this challenge, but they are sub-optimal because they do not explore domain knowledge for designing the pretext tasks, and their contrastive learning losses do not try to cluster the normal training images, which may result in a sparse distribution of normal images that is ineffective for anomaly detection. In this paper, we propose a new self-supervised pre-training method for MIA UAD applications, named Pseudo Multi-class Strong Augmentation via Contrastive Learning (PMSACL). PMSACL consists of a novel optimisation method that contrasts a normal image class from multiple pseudo classes of synthesised abnormal images, with each class enforced to form a dense cluster in the feature space. In the experiments, we show that our PMSACL pre-training improves the accuracy of SOTA UAD methods on many MIA benchmarks using colonoscopy, fundus screening and Covid-19 Chest X-ray datasets.
Keywords
Anomaly segmentation, Colonoscopy, Covid-19, Fundus image, Lesion segmentation, One-class classification, Self-supervised learning, Unsupervised anomaly detection
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces | Medical Sciences
Research Areas
Data Science and Engineering
Publication
Medical Image Analysis
Volume
90
First Page
1
Last Page
11
ISSN
1361-8415
Identifier
10.1016/j.media.2023.102930
Publisher
Elsevier
Citation
TIAN, Yu; LIU, Fengbei; PANG, Guansong; CHEN, Yuanhong; LIU, Yuyuan; VERJANS, Johan W.; SINGH, Rajvinder; and CARNEIRO, Gustavo.
Self-supervised pseudo multi-class pre-training for unsupervised anomaly detection and segmentation in medical images. (2023). Medical Image Analysis. 90, 1-11.
Available at: https://ink.library.smu.edu.sg/sis_research/8142
Copyright Owner and License
Authors
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/10.1016/j.media.2023.102930
Included in
Databases and Information Systems Commons, Graphics and Human Computer Interfaces Commons, Medical Sciences Commons