A deep-learning model for intracranial aneurysm detection on CT angiography images in China: a stepwise, multicentre, early-stage clinical validation study

作者：Bin Hu, Zhao Shi, Lu Li, Zhongchang Miao, Hao Wang, Zhen Zhou, Fandong Zhang, Rongpin Wang, Xiao Luo, Feng Xu, Sheng Li, Xiangming Fang, Xiaodong Wang, Ge Yan, Fajin Lv, Meng Zhang, Qiu Sun, Guangbin Cui, Yubao Liu, S Zhang, Chengwei Pan, Zhibo Hou, Huiying Liang, Yuning Pan, Xiaoxia Chen, Xiaorong Li, Fei Zhou, U. Joseph Schoepf, Ákos Varga‐Szemes, W Garrison Moore, Yizhou Yu, Chunfeng Hu, Long Jiang Zhang, Bin Hu, Zhao Shi, Li Xia Lu, Miao Zhongchang, Hao Wang, Zhen Zhou, Fandong Zhang, Rongpin Wang, Xiao Luo, Feng Xu, Sheng Li, Xiangming Fang, Xiaodong Wang, Ge Yan, Fajin Lv, Meng Zhang, Qiu Sun, Guangbin Cui, Yubao Liu, Shu Zhang, Chengwei Pan, Zhibo Hou, Huiying Liang, Yuning Pan, Xiaoxia Chen, Xiaorong Li, Fei Zhou, Bin Tan, Feidi Liu, Feng Chen, Hongmei Gu, Mingli Hou, Rui Xu, Rui Zuo, Shumin Tao, Weiwei Chen, Xue Chai, Wulin Wang, Yongjian Dai, Yueqin Chen, Changsheng Zhou, Guangming Lu, U. Joseph Schoepf, W Garrison Moore, Ákos Varga‐Szemes, Yizhou Yu, Chunfeng Hu, Long Jiang Zhang · 发表于：The Lancet Digital Health · 年份：2024 · DOI：10.1016/s2589-7500(23)00268-6 · 被引用次数：58 · 研究领域：Intracranial Aneurysms: Treatment and Complications、Retinal Imaging and Analysis、Artificial Intelligence in Healthcare and Education

BACKGROUND: Artificial intelligence (AI) models in real-world implementation are scarce. Our study aimed to develop a CT angiography (CTA)-based AI model for intracranial aneurysm detection, assess how it helps clinicians improve diagnostic performance, and validate its application in real-world clinical implementation. METHODS: We developed a deep-learning model using 16 546 head and neck CTA examination images from 14 517 patients at eight Chinese hospitals. Using an adapted, stepwise implementation and evaluation, 120 certified clinicians from 15 geographically different hospitals were recruited. Initially, the AI model was externally validated with images of 900 digital subtraction angiography-verified CTA cases (examinations) and compared with the performance of 24 clinicians who each viewed 300 of these cases (stage 1). Next, as a further external validation a multi-reader multi-case study enrolled 48 clinicians to individually review 298 digital subtraction angiography-verified CTA cases (stage 2). The clinicians reviewed each CTA examination twice (ie, with and without the AI model), separated by a 4-week washout period. Then, a randomised open-label comparison study enrolled 48 clinicians to assess the acceptance and performance of this AI model (stage 3). Finally, the model was prospectively deployed and validated in 1562 real-world clinical CTA cases. FINDINGS: The AI model in the internal dataset achieved a patient-level diagnostic sensitivity of 0·957 (95% CI 0·9...