Implicit field learning for unsupervised anomaly detection in medical images

TL;DR

This paper introduces an unsupervised anomaly detection method for medical images using implicit field representations, effectively localizing gliomas in brain MR images with higher accuracy and efficiency than existing VAE-based methods.

Contribution

The paper presents a novel implicit field-based approach for unsupervised anomaly detection in medical images, outperforming VAE methods in accuracy and computational efficiency.

Findings

Outperforms VAE-based methods in glioma localization (DICE 0.640 vs 0.518)

Requires less computing time than existing methods

Effective in unsupervised detection of anomalies in brain MRI

Abstract

We propose a novel unsupervised out-of-distribution detection method for medical images based on implicit fields image representations. In our approach, an auto-decoder feed-forward neural network learns the distribution of healthy images in the form of a mapping between spatial coordinates and probabilities over a proxy for tissue types. At inference time, the learnt distribution is used to retrieve, from a given test image, a restoration, i.e. an image maximally consistent with the input one but belonging to the healthy distribution. Anomalies are localized using the voxel-wise probability predicted by our model for the restored image. We tested our approach in the task of unsupervised localization of gliomas on brain MR images and compared it to several other VAE-based anomaly detection methods. Results show that the proposed technique substantially outperforms them (average DICE 0.640 vs 0.518 for the best performing VAE-based alternative) while also requiring considerably less computing time.