Conditional Generative Models for Contrast-Enhanced Synthesis of T1w and T1 Maps in Brain MRI

TL;DR

This paper explores the use of conditional generative models, specifically diffusion and flow matching, to predict contrast enhancement in brain MRI, comparing T1 and T1-weighted scans for uncertainty quantification and segmentation accuracy.

Contribution

It introduces the application of conditional diffusion and flow matching models for uncertainty quantification in MRI contrast enhancement prediction and compares T1 versus T1-weighted scans for this task.

Findings

Better segmentation performance with T1 scans than T1-weighted scans.

Generative models can effectively quantify uncertainty in virtual enhancement.

T1 scans provide more physically meaningful voxel ranges for prediction.

Abstract

Contrast enhancement by Gadolinium-based contrast agents (GBCAs) is a vital tool for tumor diagnosis in neuroradiology. Based on brain MRI scans of glioblastoma before and after Gadolinium administration, we address enhancement prediction by neural networks with two new contributions. Firstly, we study the potential of generative models, more precisely conditional diffusion and flow matching, for uncertainty quantification in virtual enhancement. Secondly, we examine the performance of T1 scans from quantitive MRI versus T1-weighted scans. In contrast to T1-weighted scans, these scans have the advantage of a physically meaningful and thereby comparable voxel range. To compare network prediction performance of these two modalities with incompatible gray-value scales, we propose to evaluate segmentations of contrast-enhanced regions of interest using Dice and Jaccard scores. Across models, we observe better segmentations with T1 scans than with T1-weighted scans.