Confidence-Aware and Self-Supervised Image Anomaly Localisation
Preprint
Abstract
Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class of normative samples, e.g., through epistemic uncertainty estimates, auto-encoding models, or from synthetic anomalies in a self-supervised way. The performance of self-supervised anomaly detection approaches is still inferior compared to methods that use examples from known unknown classes to shape the decision boundary. However, outlier exposure methods often do not identify unknown unknowns. Here we discuss an improved self-supervised single-class training strategy that supports the approximation of probabilistic inference with loosen feature locality constraints. We show that up-scaling of gradients with histogram-equalised images is beneficial for recently proposed self-supervision tasks. Our method is integrated into several out-of-distribution (OOD) detection models and we show evidence that our method outperforms the state-of-the-art on various benchmark datasets. Source code will be publicly available by the time of the conference.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Diffusion Models for Medical Anomaly Detection2022
- Detecting Outliers with Foreign Patch InterpolationMachine Learning for Biomedical Imaging, 2022
- Anomaly Detection in Medical Imaging - A Mini Review2022
- Anomaly detection in chest 18F-FDG PET/CT by Bayesian deep learningJapanese Journal of Radiology, 2022
- Anomaly Detection for Medical Images Using Self-Supervised and Translation-Consistent FeaturesIEEE Transactions on Medical Imaging, 2021
- Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCTIEEE Transactions on Medical Imaging, 2019
- f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networksMedical Image Analysis, 2019
- Breast cancer detection using synthetic mammograms from generative adversarial networks in convolutional neural networksJournal of Medical Imaging, 2019
- DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learningJournal of Medical Imaging, 2018