Many tasks make light work: Learning to localise medical anomalies from multiple synthetic tasks

TL;DR

This paper introduces a multi-task synthetic anomaly learning approach for medical image out-of-distribution detection, improving robustness and generalization over existing methods in brain MRI and chest X-ray analysis.

Contribution

It proposes using multiple synthetic anomaly tasks for training and validation, enhancing model robustness and out-of-distribution detection in medical imaging.

Findings

Outperforms state-of-the-art methods on brain MRI and chest X-ray datasets.

Enables more robust training and generalization through multi-task synthetic anomalies.

Provides a structured validation framework for better calibration in deployment.

Abstract

There is a growing interest in single-class modelling and out-of-distribution detection as fully supervised machine learning models cannot reliably identify classes not included in their training. The long tail of infinitely many out-of-distribution classes in real-world scenarios, e.g., for screening, triage, and quality control, means that it is often necessary to train single-class models that represent an expected feature distribution, e.g., from only strictly healthy volunteer data. Conventional supervised machine learning would require the collection of datasets that contain enough samples of all possible diseases in every imaging modality, which is not realistic. Self-supervised learning methods with synthetic anomalies are currently amongst the most promising approaches, alongside generative auto-encoders that analyse the residual reconstruction error. However, all methods suffer from a lack of structured validation, which makes calibration for deployment difficult and dataset-dependant. Our method alleviates this by making use of multiple visually-distinct synthetic anomaly learning tasks for both training and validation. This enables more robust training and generalisation. With our approach we can readily outperform state-of-the-art methods, which we demonstrate on exemplars in brain MRI and chest X-rays. Code is available at https://github.com/matt-baugh/many-tasks-make-light-work .