Comparison of Automated White Matter Lesion Segmentation Approaches for Use in Large, Multi-Site Data Analyses in Parkinson's Disease
Sarah Al–Bachari, So Hoon Yoon, Phoebe Emson, Shauna Angell, J. R. Cain, Aswin Abraham, Azeem Chugtai, Edward Sizer, Edwin Barnes, Maryam Al-Wardy, Siddarth Kannan, Rohan Paul-Thaper, Joanna K. Bright, Conor Owens‐Walton, Corey T. McMillan, , Hamied A. Haroon
This paper evaluates automated white matter lesion segmentation methods in Parkinson's disease and healthy controls, finding U-Net-pgs to be the most accurate and reliable approach across multiple metrics and datasets.
Frontiers in Neuroscience · Sep 24, 2026Peer-reviewedNeuroscience