Development of a deep-learning algorithm for etiological classification of subarachnoid hemorrhage using non-contrast CT scans

• Published in: European radiology Vol. 35; no. 11; pp. 6775 - 6784
• Main Authors: Chen, Lingxu, Wang, Xiaochen, Li, Yuanjun, Bao, Yang, Wang, Sihui, Zhao, Xuening, Yuan, Mengyuan, Kang, Jianghe, Sun, Shengjun
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2025; Springer Nature B.V
• Subjects: Accuracy; Adult; Aged; Algorithms; Aneurysm; Aneurysms; Angiography; Classification; Clinical medicine; Computed tomography; Correlation coefficient; Correlation coefficients; Decision making; Deep Learning; Diagnosis; Diagnostic Radiology; Electronic health records; Etiology; Female; Hemorrhage; Hospitals; Humans; Imaging; Internal Medicine; Interventional Radiology; Machine learning; Male; Medical imaging; Medical records; Medicine; Medicine & Public Health; Middle Aged; Neuro; Neuroradiology; Patients; Radiographic Image Interpretation, Computer-Assisted - methods; Radiology; Retrospective Studies; Sensitivity; Sensitivity and Specificity; Subarachnoid hemorrhage; Subarachnoid Hemorrhage - classification; Subarachnoid Hemorrhage - diagnostic imaging; Subarachnoid Hemorrhage - etiology; Tomography, X-Ray Computed - methods; Ultrasound; Beijing China; China; Deep learning; Computed tomography; Subarachnoid hemorrhage; Intracranial aneurysm
• ISSN: 1432-1084; 0938-7994; 1432-1084
• DOI: 10.1007/s00330-025-11666-2

Objectives This study aims to develop a deep learning algorithm for differentiating aneurysmal subarachnoid hemorrhage (aSAH) from non-aneurysmal subarachnoid hemorrhage (naSAH) using non-contrast computed tomography (NCCT) scans. Methods This retrospective study included 618 patients diagnosed with SAH. The dataset was divided into a training and internal validation cohort (533 cases: aSAH = 305, naSAH = 228) and an external test cohort (85 cases: aSAH = 55, naSAH = 30). Hemorrhage regions were automatically segmented using a U-Net + + architecture. A ResNet-based deep learning model was trained to classify the etiology of SAH. Results The model achieved robust performance in distinguishing aSAH from naSAH. In the internal validation cohort, it yielded an average sensitivity of 0.898, specificity of 0.877, accuracy of 0.889, Matthews correlation coefficient (MCC) of 0.777, and an area under the curve (AUC) of 0.948 (95% CI: 0.929–0.967). In the external test cohort, the model demonstrated an average sensitivity of 0.891, specificity of 0.880, accuracy of 0.887, MCC of 0.761, and AUC of 0.914 (95% CI: 0.889–0.940), outperforming junior radiologists (average accuracy: 0.836; MCC: 0.660). Conclusion The study presents a deep learning architecture capable of accurately identifying SAH etiology from NCCT scans. The model’s high diagnostic performance highlights its potential to support rapid and precise clinical decision-making in emergency settings. Key Points Question Differentiating aneurysmal from naSAH is crucial for timely treatment, yet existing imaging modalities are not universally accessible or convenient for rapid diagnosis . Findings A ResNet-variant-based deep learning model utilizing non-contrast CT scans demonstrated high accuracy in classifying SAH etiology and enhanced junior radiologists’ diagnostic performance . Clinical relevance AI-driven analysis of non-contrast CT scans provides a fast, cost-effective, and non-invasive solution for preoperative SAH diagnosis. This approach facilitates early identification of patients needing aneurysm surgery while minimizing unnecessary angiography in non-aneurysmal cases, enhancing clinical workflow efficiency . Graphical Abstract