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

Abstract

<bold>Background:</bold> 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. <bold>Methods:</bold> 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. <bold>Results:</bold> 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 (rho = 0.60, p < 0.001). Lesions >50 mL were associated with reduced favorable outcomes (17.3% [26/150] vs. 54.2% [246/453], p < 0.001) and higher hemorrhagic transformation rates (66.0% [99/150] vs. 46.3% [210/453], p < 0.001). Radiomics features improved hemorrhagic transformation prediction beyond clinical variables alone (area under the receiver operating characteristic curve, 0.833 vs. 0.626; p = 0.003). <bold>Conclusion:</bold> The automated NCCT-based lesion detection model demonstrated reliable diagnostic performance and provided clinically relevant prognostic information in endovascular thrombectomy-treated stroke patients.