Conditional Generative Models for Contrast-Enhanced Synthesis of T1w and T1 Maps in Brain MRI
This work addresses tumor diagnosis in neuroradiology by improving virtual enhancement prediction, but it is incremental as it focuses on comparing existing modalities and models.
The study tackled the problem of predicting contrast enhancement in brain MRI for tumor diagnosis by comparing generative models (conditional diffusion and flow matching) and evaluating T1 scans versus T1-weighted scans, finding that T1 scans led to better segmentation performance with Dice and Jaccard scores.
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.