Validation of a Jacobian AI-based method to measure cerebellar volume changes in multiple system atrophy
The accurate, consistent, and scalable estimation of cerebellar atrophy would be highly beneficial for clinical trials in multiple system atrophy (MSA)1-3. This work performs validation of a fully automatic volume change
workflow in MSA using Jacobian integration from non-linear warp-fields estimated with a convolutional neural
network (CNN)-based 3D T1- weighted (T1W) image analysis workflow.
The developed framework provides a fully automatic solution for estimating cerebellar volume change with increased sensitivity over comparable methods. Additionally, the framework is flexible and highly scalable, and as such has the potential to be advantageous for future clinical trials
Presented at ADPD 2023 in Gothenburg, SwedenDownload