Monday, November 9, 2026

Geometric brain signatures for characterising hereditary ataxia and predicting functional brain organisation: a retrospective multicohort study

Zuitian Tao, Gilles Naeije, Fuad Noman, Thiago J R Rezende, Marcondes C França, Alex Fornito, Ian H Harding, Nellie Georgiou-Karistianis, Trang Cao, Susmita Saha, Nellie Georgiou-Karistianis, Louise A Corben, Eric F Lock, Helena Bujalka, Isaac Adanyeguh, Manuela Corti, Daniel Chung, Martin Delatycki, Imis Dogan, Jennifer Farmer, Marcondes França, Anthony S Gabay, William Gaetz, Ian H Harding, Pierre-Gilles Henry, James Joers, Christophe Lenglet, Michelle A Lax, Jiakun Li, David Lynch, Thomas Mareci, Alberto R M Martinez, Massimo Pandolfo, Marina Papoutsi, Myriam Rai, Kathrin Reetz, Thiago J R Rezende, Timothy P Roberts, Sandro Romanzetti, David A Rudko, Susmita Saha, Jörg B Schulz, S H Subramony, Veena G Supramaniam, Geometric brain signatures for characterising hereditary ataxia and predicting functional brain organisation: a retrospective multicohort study, The Lancet Medical Imaging & Theranostics, Volume 1, Issue 2, 2026, 100016, ISSN 3117-4523, doi:10.1016/j.lanmit.2026.100016. 

 The study analysed MRI scans from over 500 participants across three independent cohorts, including people with Friedreich ataxia, spinocerebellar ataxia types 1 and 3, and healthy participants. The model analysed brain scans using 200 geometric features that captured patterns of brain structure and activity across the whole brain. 
The exploratory geometry-driven deep learning approach used in this study proposes to describe brain changes across multiple scales by integrating structural and functional information and predicts brain function when fMRI data are unavailable. Thus, geometric brain signatures might support biomarker development for HCA subtype differentiation and disease progression tracking in larger prospective studies.