# Unsupervised Pathology Detection: A Deep Dive Into the State of the Art

## TL;DR

This paper benchmarks and evaluates recent unsupervised pathology detection methods across multiple medical imaging datasets, demonstrating new state-of-the-art performance and the benefits of self-supervised pre-training.

## Contribution

It provides a comprehensive evaluation of cutting-edge unsupervised anomaly detection methods on medical datasets, establishing new SOTA and insights into their characteristics.

## Key findings

- Feature-modeling methods outperform previous approaches.
- Self-supervised pre-training enhances detection performance.
- New SOTA achieved across multiple modalities.

## Abstract

Deep unsupervised approaches are gathering increased attention for applications such as pathology detection and segmentation in medical images since they promise to alleviate the need for large labeled datasets and are more generalizable than their supervised counterparts in detecting any kind of rare pathology. As the Unsupervised Anomaly Detection (UAD) literature continuously grows and new paradigms emerge, it is vital to continuously evaluate and benchmark new methods in a common framework, in order to reassess the state-of-the-art (SOTA) and identify promising research directions. To this end, we evaluate a diverse selection of cutting-edge UAD methods on multiple medical datasets, comparing them against the established SOTA in UAD for brain MRI. Our experiments demonstrate that newly developed feature-modeling methods from the industrial and medical literature achieve increased performance compared to previous work and set the new SOTA in a variety of modalities and datasets. Additionally, we show that such methods are capable of benefiting from recently developed self-supervised pre-training algorithms, further increasing their performance. Finally, we perform a series of experiments in order to gain further insights into some unique characteristics of selected models and datasets. Our code can be found under https://github.com/iolag/UPD_study/.