Developing a deep learning-based imaging diagnostic framework, PVDNet, for differentiating pulmonary artery sarcoma and pulmonary thromboembolism: a multi-center observational study
机构：[1]China-Japan Friendship Hospital, Capital Medical University, Beijing, 100069, China[2]National Center for Respiratory Medicine, State Key Laboratory of Respiratory Health and Multimorbidity, National Clinical Research Center for Respiratory Diseases, Institute of Respiratory Medicine, Chinese Academy of Medical Sciences, Department of Pulmonary and Critical Care Medicine, Center of Respiratory Medicine, China-Japan Friendship Hospital, Beijing, 100029, China[3]Department of Radiology, China-Japan Friendship Hospital, Beijing, 100029, China[4]Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China[5]Institute of Advanced Research, Infervision Medical Technology Co., Ltd., Beijing, 100025, China[6]Department of Radiology and Interventional Radiology, The Red Cross Hospital in Qinghai, Xining, 810000, China[7]Department of Radiology, Beijing Chao-Yang Hospital, Capital Medical University, Beijing, 100020, China北京朝阳医院[8]Department of Magnetic Resonance Imaging, Fuwai Hospital and National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100037, China[9]Department of Radiology, Guangdong Provincial People’s Hospital, Southern Medical University, Guangzhou, 510080, China[10]School of Medicine, South China University of Technology, Guangzhou, 510006, China[11]Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, 264009, China[12]Department of Radiology, Affiliated Cancer Hospital of Nanjing Medical University, Jiangsu Cancer Hospital, Jiangsu Institute of Cancer Research, Nanjing, 210009, China[13]Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, 510120, China[14]Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China四川大学华西医院[15]Department of Respiratory Medicine, Wuhan No. 6 Hospital, Affiliated Hospital to Jianghan University, Wuhan, 430072, China[16]Department of Radiology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, 310009, China[17]Department of Radiology, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, 710004, China[18]Department of Radiology, Shanghai Chest Hospital, Shanghai Jiao-Tong University, Shanghai, 200030, China[19]Department of Radiology, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou, 310018, China[20]Department of PET/CT, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an, 710061, China[21]Department of MRI, Shaanxi Provincial People’s Hospital, Xi’an, 710068, China[22]Department of Radiology, The First Hospital of Lanzhou University, Lanzhou, 730000, China[23]Chinese Academy of Medical Sciences Fuwai Hospital Center for Respiratory and Pulmonary Vascular Diseases, Beijing, 100037, China[24]Department of Cardiovascular Surgery, China-Japan Friendship Hospital, Beijing, 100029, China[25]Academy for Multidisciplinary Studies, Capital Normal University, Beijing, 100080, China
Background Differentiating pulmonary artery sarcoma (PAS) from pulmonary thromboembolism (PTE) based on CT pulmonary angiography (CTPA) is a big challenge, necessitating the incorporation of other methods, such as deep learning (DL). This study aimed to develop and validate a DL-based model, PVDNet, for differentiating PAS and PTE on CTPA. Methods This study retrospectively analyzed CTPA image datasets from the prospective CHinese pulmOnary embolism multimodality Imaging artifiCial intelligencE (CHOICE) study to develop and validate a DL model for differentiating PAS from PTE. CTPA image datasets of 952 patients (470 acute PTE [APE], 363 chronic PTE [CPE], and 119 PAS) from 15 hospitals were included. The training set comprised CTPA images from 590 patients, and the internal test set comprised those from 186 patients, all obtained from the same three centers. CTPA images of 176 patients from 12 centers were used for external validation. A DL framework, PVDNet, was employed to perform fine-grained classification. Meanwhile, CTPA images in the external validation set were independently assessed by four radiologists with different levels of expertise. The main outcome measures were area under the curve (AUC) and the consistency test. Findings In the internal test set, PVDNet achieved an AUC of 0.972, 0.902, and 0.900 for PAS (95% CI: [0.945, 0.994]), APE (95% CI: [0.855, 0.944]), and CPE (95% CI: [0.852, 0.946]), respectively. Furthermore, PVDNet model demonstrated effective differentiation between PAS and PTE, showing comparable AUC values to a senior radiologist specialized in pulmonary vascular diseases (SRPV) in the external validation set (0.973 vs. 0.943, p = 0.308). The model achieved moderate agreement with SRPV (kappa = 0.651, p < 0.001), which was the highest among four readers. Interpretation PVDNet model could differentiate PAS from PTE, with performance approaching the proficiency level of a senior radiologist specializing in pulmonary vascular diseases. PVDNet's performance in distinguishing APE from CPE requires further optimization. (c) 2025 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC license.
基金：
National Natural Science Foundation of China [82272081]; Medical and Health Science and Technology Innovation Project of Chinese Academy of Medical Science [2021-I2M-1-049]; National Key Research and Development Program of China [2023YFC2507200]
语种：
外文
WOS：
PubmedID：
中科院(CAS)分区：
出版当年[2025]版：
大类|1 区医学
小类|1 区卫生保健与服务1 区公共卫生、环境卫生与职业卫生
最新[2025]版：
大类|1 区医学
小类|1 区卫生保健与服务1 区公共卫生、环境卫生与职业卫生
JCR分区：
出版当年[2024]版：
Q1HEALTH CARE SCIENCES & SERVICESQ1PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH
最新[2024]版：
Q1HEALTH CARE SCIENCES & SERVICESQ1PUBLIC, ENVIRONMENTAL & OCCUPATIONAL HEALTH
第一作者机构：[1]China-Japan Friendship Hospital, Capital Medical University, Beijing, 100069, China[2]National Center for Respiratory Medicine, State Key Laboratory of Respiratory Health and Multimorbidity, National Clinical Research Center for Respiratory Diseases, Institute of Respiratory Medicine, Chinese Academy of Medical Sciences, Department of Pulmonary and Critical Care Medicine, Center of Respiratory Medicine, China-Japan Friendship Hospital, Beijing, 100029, China
共同第一作者：
通讯作者：
推荐引用方式(GB/T 7714)：
Xi Linfeng,Liu Anqi,Kang Han,et al.Developing a deep learning-based imaging diagnostic framework, PVDNet, for differentiating pulmonary artery sarcoma and pulmonary thromboembolism: a multi-center observational study[J].LANCET REGIONAL HEALTH-WESTERN PACIFIC.2025,60:doi:10.1016/j.lanwpc.2025.101625.
APA：
Xi, Linfeng,Liu, Anqi,Kang, Han,Ni, Yifei,Wang, Jianping...&Liu, Min.(2025).Developing a deep learning-based imaging diagnostic framework, PVDNet, for differentiating pulmonary artery sarcoma and pulmonary thromboembolism: a multi-center observational study.LANCET REGIONAL HEALTH-WESTERN PACIFIC,60,
MLA：
Xi, Linfeng,et al."Developing a deep learning-based imaging diagnostic framework, PVDNet, for differentiating pulmonary artery sarcoma and pulmonary thromboembolism: a multi-center observational study".LANCET REGIONAL HEALTH-WESTERN PACIFIC 60.(2025)
医学