Chapter 11 Self- and unsupervised learning for anomaly detection and localization
Zimmerer, David Maier-Hein, Klaus
Zimmerer, David
Maier-Hein, Klaus
Author
Supervisor
Department
Computer Vision
Embargo End Date
Type
Book chapter
Date
License
Language
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The growing role of machine learning in medical imaging offers significant opportunities for improving disease detection and diagnosis. Yet, the development of robust and generalizable models remains challenging due to the scarcity of annotated data, variability across imaging modalities, and the complexity of medical conditions. To address these limitations, self-supervised and unsupervised learning strategies are increasingly explored, as they can leverage abundant unlabeled data to learn meaningful representations and detect anomalies without costly manual annotations. This chapter provides an overview of key unsupervised approaches for anomaly detection and localization in medical imaging, focusing on methods such as Denoising Autoencoders (DAEs), Variational Autoencoders (VAEs) and their variants. Additionally, it introduces Contrastive Representations for Unsupervised Anomaly Detection and Localization (CRADL), a promising framework that employs contrastive learning to enhance anomaly detection capabilities. By learning to distinguish normal from abnormal patterns without supervision, these approaches open new avenues for scalable, adaptable, and clinically relevant medical imaging solutions.
Citation
D. Zimmerer, K. Maier-Hein, "Chapter 11 Self- and unsupervised learning for anomaly detection and localization," in Less-supervised Segmentation with CNNs, Elsevier, 2025, pp. 237-256.
Source
Less-supervised Segmentation with CNNs
Conference
Keywords
46 Information and Computing Sciences, 4611 Machine Learning
Subjects
Source
Publisher
Elsevier