A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis
This work addresses the need for accurate and adaptable segmentation tools in neuroimaging for multiple sclerosis research, offering a publicly available solution that is incremental by integrating lesion modeling into an existing framework.
The paper tackles the problem of simultaneously segmenting white matter lesions and normal brain structures from multi-contrast MRI scans in multiple sclerosis patients, achieving robust performance across four disparate datasets without requiring retraining for different scanners or protocols. It also demonstrates applicability to healthy controls and replicates known atrophy patterns in MS.
Here we present a method for the simultaneous segmentation of white matter lesions and normal-appearing neuroanatomical structures from multi-contrast brain MRI scans of multiple sclerosis patients. The method integrates a novel model for white matter lesions into a previously validated generative model for whole-brain segmentation. By using separate models for the shape of anatomical structures and their appearance in MRI, the algorithm can adapt to data acquired with different scanners and imaging protocols without retraining. We validate the method using four disparate datasets, showing robust performance in white matter lesion segmentation while simultaneously segmenting dozens of other brain structures. We further demonstrate that the contrast-adaptive method can also be safely applied to MRI scans of healthy controls, and replicate previously documented atrophy patterns in deep gray matter structures in MS. The algorithm is publicly available as part of the open-source neuroimaging package FreeSurfer.