Feasibility of Universal Anomaly Detection without Knowing the Abnormality in Medical Images

TL;DR

This paper explores the feasibility of universal anomaly detection in medical images without prior knowledge of specific abnormalities, highlighting challenges in model validation and proposing an ensemble approach to improve robustness.

Contribution

It compares various anomaly detection methods, addresses validation biases, and introduces a simple ensemble technique to enhance universal anomaly detection performance.

Findings

No single method outperformed others across all datasets

The proposed ensemble improved robustness with an average AUC of 0.956

Validation bias remains a significant challenge in anomaly detection

Abstract

Many anomaly detection approaches, especially deep learning methods, have been recently developed to identify abnormal image morphology by only employing normal images during training. Unfortunately, many prior anomaly detection methods were optimized for a specific "known" abnormality (e.g., brain tumor, bone fraction, cell types). Moreover, even though only the normal images were used in the training process, the abnormal images were often employed during the validation process (e.g., epoch selection, hyper-parameter tuning), which might leak the supposed ``unknown" abnormality unintentionally. In this study, we investigated these two essential aspects regarding universal anomaly detection in medical images by (1) comparing various anomaly detection methods across four medical datasets, (2) investigating the inevitable but often neglected issues on how to unbiasedly select the optimal anomaly detection model during the validation phase using only normal images, and (3) proposing a simple decision-level ensemble method to leverage the advantage of different kinds of anomaly detection without knowing the abnormality. The results of our experiments indicate that none of the evaluated methods consistently achieved the best performance across all datasets. Our proposed method enhanced the robustness of performance in general (average AUC 0.956).