Automated ischemic stroke lesion detection on non-contrast brain CT: a large-scale clinical feasibility test AI stroke lesion detection on NCCT

作者：JoonNyung Heo, Wi‐Sun Ryu, Jong‐Won Chung, Chi Kyung Kim, Joon-Tae Kim, Myung-Jae Lee, Dongmin Kim, Leonard Sunwoo, Johanna M. Ospel, Nishita Singh, Hee‐Joon Bae, Beom Joon Kim · 发表于：Frontiers in Neuroscience · 年份：2025 · DOI：10.3389/fnins.2025.1643479 · 被引用次数：3 · 研究领域：Acute Ischemic Stroke Management、Cerebrovascular and Carotid Artery Diseases、Intracerebral and Subarachnoid Hemorrhage Research

Background Non-contrast CT (NCCT) is widely used imaging modality for acute stroke imaging but often fails to detect subtle early ischemic changes. Such underestimation can lead clinicians to overlook tissue-level information. This study aimed to develop and externally validate automated software for detecting ischemic lesions on NCCT and to assess its clinical feasibility in stroke patients undergoing endovascular thrombectomy. Methods In this retrospective, multicenter cohort study (May 2011–April 2024), a modified 3D U-Net model was trained using paired NCCT and diffusion-weighted imaging (DWI) data from 2,214 patients with acute ischemic stroke. External validation was performed in 458 subjects. Clinical feasibility was assessed in 603 endovascular thrombectomy-treated patients with complete recanalization. Model outputs were compared against expert-annotated DWI lesions for sensitivity, specificity, and volumetric correlation. Clinical endpoints included follow-up DWI lesion volumes, hemorrhagic transformation, and 3-month modified Rankin Scale outcomes. Results A total of 458 subjects were evaluated for external validation (mean age, 64 years ± 16; 265 men). The model achieved 75.3% sensitivity (95% CI, 70.9–79.9%) and 79.1% specificity (95% CI, 77.1–81.3%). In the feasibility cohort ( n = 603; mean age, 69 years ± 13; 362 men), NCCT-derived lesion volumes correlated with follow-up DWI volumes ( ρ = 0.60, p < 0.001). Lesions >50 mL were associated with red...