A Study of Representational Properties of Unsupervised Anomaly Detection in Brain MRI
This work provides insights into factorization for unsupervised anomaly detection in brain MRI, which could aid clinical diagnosis, but it is incremental as it analyzes existing methods.
The study investigated how unsupervised anomaly detection methods in brain MRI relate to factorization properties, finding that algorithms with such properties effectively distinguish normal from anomalous data, validated across multiple datasets.
Anomaly detection in MRI is of high clinical value in imaging and diagnosis. Unsupervised methods for anomaly detection provide interesting formulations based on reconstruction or latent embedding, offering a way to observe properties related to factorization. We study four existing modeling methods, and report our empirical observations using simple data science tools, to seek outcomes from the perspective of factorization as it would be most relevant to the task of unsupervised anomaly detection, considering the case of brain structural MRI. Our study indicates that anomaly detection algorithms that exhibit factorization related properties are well capacitated with delineatory capabilities to distinguish between normal and anomaly data. We have validated our observations in multiple anomaly and normal datasets.