Deep learning-based identification and localization of intracranial hemorrhage in patients using a large annotated head computed tomography dataset:A retrospective multicenter study  

作　　者：Jingjing Liu Weijie Fan Yi Yang Qi Peng Bingjun Ji Luxing He Yang Li Jing Yuan Wei Li Xianqi Wang Yi Wu Chen Liu Qingfang Gong Mi He Yeqin Fu Dong Zhang Si Zhang Yongjian Nian 

机构地区：[1]Department of Digital Medicine,School of Biomedical Engineering and Imaging Medicine,Army Medical University,Chongqing 400038,China [2]Department of Radiology,Second Affiliated Hospital,Army Medical University,Chongqing 400037,China [3]Radiotherapy Center,Sunshine Union Hospital,Weifang,Shandong 261061,China [4]Department of Radiology,Air Force Hospital of Western Theater Command,Chengdu,Sichuan 610011,China [5]Department of Radiology,Army Medical Center,Army Medical University,Chongqing 400037,China [6]Department of Radiology,First Affiliated Hospital,Army Medical University,Chongqing 400037,China [7]Department of Medical Instruments and Metrology,School of Biomedical Engineering and Imaging Medicine,Army Medical University,Chongqing 400038,China

出　　处：《Intelligent Medicine》2025年第1期14-22,共9页智慧医学(英文)

基　　金：supported by Science and Technology Research Project of Chongqing Education Commission(Grant No.KJQN202212804).

摘　　要：Background Accurately identifying and localizing the five subtypes of intracranial hemorrhage(ICH)are crucial steps for subsequent clinical treatment;however,the lack of a large computed tomography(CT)dataset with annotations of the categorization and localization of ICH considerably limits the development of deep learningbased identification and localization methods.We aimed to construct this large dataset and develop a deep learning-based model to identify and localize the five ICH subtypes,including intraventricular hemorrhage(IVH),intraparenchymal hemorrhage(IPH),subdural hemorrhage(SDH),subarachnoid hemorrhage(SAH),and epidural hemorrhage(EDH),in non-contrast head CT scans.Methods Based on the public Radiological Society of North America(RSNA)2019 dataset,we constructed a large CT dataset named RSNA 2019+that was annotated for bleeding localization of the five ICH subtypes by three radiologists.An improved YOLOv8 architecture with the bidirectional feature pyramid network was proposed and trained using the RSNA 2019+training dataset and evaluated on the RSNA 2019+test dataset.The public CQ500,and two private datasets collected from the Xinqiao and Sunshine Union Hospitals,respectively,were also annotated to perform multicenter validation.Furthermore,the performance of the deep learning model was compared with that of four radiologists.Multiple performance metrics,including the average precision(AP),precision,recall and F1-score,were used for performance evaluation.The McNemar and chi-squared tests were performed,and the 95%Wilson confidence intervals were given for the precision and recall.Results There were 175,125;4,707;8,259;and 3,104 bounding boxes after annotation on the RSNA 2019+;CQ500+;and the PD 1 and PD 2 datasets,respectively.With an intersection-over-union threshold of 0.5,the APs of IVH,IPH,SAH,SDH and EDH are 0.852,0.820,0.574,0.639,and 0.558,respectively,yielding a mean average precision(mAP)of 0.688 for our proposed deep learning model on the RSNA 2019+test dataset.For the multicenter validat

关 键 词：Intracranial hemorrhage Identification and localization Deep learning model Bounding box 

分 类 号：R74[医药卫生—神经病学与精神病学]