AUTHOR=Lee Minwoo , Suh Chong Hyun , Sohn Jong-Hee , Kim Chulho , Han Sang-Won , Sung Joo Hye , Yu Kyung-Ho , Lim Jae-Sung , Lee Sang-Hwa 

TITLE=Impact of white matter hyperintensity volumes estimated by automated methods using deep learning on stroke outcomes in small vessel occlusion stroke

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 16 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2024.1399457

DOI=10.3389/fnagi.2024.1399457

ISSN=1663-4365

ABSTRACT=Although white matter hyperintensity (WMH) share similar vascular risk and pathology with small vessel occlusion (SVO) stroke, there were few studies to evaluate the impact of burden of WMH volume on early and delayed stroke outcomes in SVO stroke.Using multicenter registry database, we enrolled SVO stroke patients between August 2013 and November 2022. The WMH volume was estimated by automated methods using deep learning, VUNO Med-DeepBrain, which was commercially available segmentation model.After propensity score matching (PSM), we evaluate the impact of WMH volume on early neurological deterioration (END) and poor functional outcome at 3-month (modified Rankin Scale [mRS]>2) after SVO stroke.Among 1,718 SVO stroke, the subjects with severe WMH group (Fazekas score≥3) were 68.9%. After PSM, END and poor functional outcome at 3month (mRS>2) was higher in severe WMH group (END: 6.9% vs. 13.5%, p<0.001; 3-month mRS>2: 11.4% vs. 24.7%, p<0.001).The logistic regression analysis using PSM cohort showed that total WMH volume increased the risk of END (odd ratio [OR], 95% confidence interval [CI]; 1.01, 1.00-1.02, p=0.048) and 3-month mRS>2 (OR, 95% CI; 1.02, 1.01-1.03, p<0.001). Deep WMH was associated with both END and 3-month mRS>2, but periventricular WMH was associated with 3-month mRS>2 only.