Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosis

TL;DR

This paper introduces a generative model for creating synthetic susceptibility maps of rim lesions in multiple sclerosis, enhancing detection accuracy and enabling a novel denoising method for ambiguous cases, thereby improving clinical diagnosis.

Contribution

The study presents a new generative network for synthetic rim lesion maps and a denoising approach that handles ambiguous cases, advancing lesion detection in multiple sclerosis.

Findings

Synthetic data improves classifier performance.

The denoising method increases detection of rare rim lesions.

Generated data closely matches real lesion distribution.

Abstract

Quantitative susceptibility maps from magnetic resonance images can provide both prognostic and diagnostic information in multiple sclerosis, a neurodegenerative disease characterized by the formation of lesions in white matter brain tissue. In particular, susceptibility maps provide adequate contrast to distinguish between "rim" lesions, surrounded by deposited paramagnetic iron, and "non-rim" lesion types. These paramagnetic rim lesions (PRLs) are an emerging biomarker in multiple sclerosis. Much effort has been devoted to both detection and segmentation of such lesions to monitor longitudinal change. As paramagnetic rim lesions are rare, addressing this problem requires confronting the class imbalance between rim and non-rim lesions. We produce synthetic quantitative susceptibility maps of paramagnetic rim lesions and show that inclusion of such synthetic data improves classifier performance and provide a multi-channel extension to generate accompanying contrasts and probabilistic segmentation maps. We exploit the projection capability of our trained generative network to demonstrate a novel denoising approach that allows us to train on ambiguous rim cases and substantially increase the minority class. We show that both synthetic lesion synthesis and our proposed rim lesion label denoising method best approximate the unseen rim lesion distribution and improve detection in a clinically interpretable manner. We release our code and generated data at https://github.com/agr78/PRLx-GAN upon publication.