Regional CSF Volume Quantification Using Deep Learning for Comparative Analysis of Brain Atrophy in Frontotemporal Dementia Subtypes

Kyoung Yoon Lim¹Soyeon Yoon²Seongbeom Park¹Seongmi Kim²Kyoungmin Kim²Jehyun Ahn²Junpyo Kim^2,3Hee Jin Kim^2,3,4,5Duk L. Na³Sang Won Seo^2,3,4,5*Kichang Kwak^1*

• ¹BeauBrain Healthcare, Inc., Seoul, Republic of Korea
• ²Samsung Alzheimer Convergence Research Center, Samsung Medical Center, Sungkyunkwan University, Seoul, Republic of Korea
• ³Department of Neurology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
• ⁴Department of Health Sciences and Technology, Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan University, Seoul, Republic of Korea
• ⁵Department of Digital Health, Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan University, Gangnam-gu, Seoul, Republic of Korea

Frontotemporal dementia (FTD) encompasses heterogeneous clinical syndromes, and distinguishing its subtypes using imaging remains challenging. We developed a deep learning model to quantify brain atrophy by measuring cerebrospinal fluid (CSF) volumes in key regions of interest (RoIs) on standard MRI scans. In a retrospective study, we analyzed 3D T1-weighted MRI data from 1,854 individuals, including cognitively unimpaired (CU) controls, patients with dementia of the Alzheimer type (DAT), and FTD subtypes: behavioral variant FTD (bvFTD), nonfluent variant primary progressive aphasia (nfvPPA), and semantic variant PPA (svPPA). The model quantified CSF volumes in 14 clinically relevant RoIs and generated age-and sex-adjusted W-scores to express regional atrophy. Each FTD subtype exhibited a distinct, lateralized atrophy pattern: bvFTD showed widespread bilateral frontal and right-predominant parietal and temporal atrophy; nfvPPA showed left-predominant frontal and parietal atrophy; and svPPA exhibited marked left-lateralized temporal and hippocampal atrophy. All FTD subtypes demonstrated significantly greater CSF expansion in these characteristic regions compared to DAT and CU. This deep learning approach provides a simple, interpretable measure of brain atrophy that differentiates FTD subtypes, requiring only standard MRI with minimal preprocessing and offers clinical utility.