Towards frugal unsupervised detection of subtle abnormalities in medical imaging

TL;DR

This paper proposes an online, scalable method using mixtures of probability distributions for unsupervised detection of subtle abnormalities in medical images, specifically MR brain scans of Parkinson's patients.

Contribution

It introduces an incremental inference approach for mixture models, enabling efficient unsupervised anomaly detection in large-scale medical imaging data.

Findings

Detected abnormalities align with Parkinson's disease progression.

Method is computationally efficient and interpretable.

Effective in identifying subtle brain abnormalities.

Abstract

Anomaly detection in medical imaging is a challenging task in contexts where abnormalities are not annotated. This problem can be addressed through unsupervised anomaly detection (UAD) methods, which identify features that do not match with a reference model of normal profiles. Artificial neural networks have been extensively used for UAD but they do not generally achieve an optimal trade-o$\hookleftarrow$ between accuracy and computational demand. As an alternative, we investigate mixtures of probability distributions whose versatility has been widely recognized for a variety of data and tasks, while not requiring excessive design e$\hookleftarrow$ort or tuning. Their expressivity makes them good candidates to account for complex multivariate reference models. Their much smaller number of parameters makes them more amenable to interpretation and e cient learning. However, standard estimation procedures, such as the Expectation-Maximization algorithm, do not scale well to large data volumes as they require high memory usage. To address this issue, we propose to incrementally compute inferential quantities. This online approach is illustrated on the challenging detection of subtle abnormalities in MR brain scans for the follow-up of newly diagnosed Parkinsonian patients. The identified structural abnormalities are consistent with the disease progression, as accounted by the Hoehn and Yahr scale.