个人中心| | 帮助
高级检索
当前位置： 首页 > 详情页

Pan-mediastinal neoplasm diagnosis via nationwide federated learning: a multicentre cohort study

| 认领 | 导出 | |

文献详情

资源类型：
WOS体系：
Pubmed体系：

收录情况： ◇ SCIE

作者：
Ruijie Tang [1] ; Hengrui Liang [2] ; Yuchen Guo [3] ; Zhigang Li [4] ; Zhichao Liu [4] ; Xu Lin [5] ; Zeping Yan [6] ; Jun Liu [2] ; Xin Xu [2] ; Wenlong Shao [2] ; Shuben Li [2] ; Wenhua Liang [2] ; Wei Wang [2] ; Fei Cui [2] ; Huanghe He [2] ; Chao Yang [2] ; Long Jiang [2] ; Haixuan Wang [2] ; Huai Chen [7] ; Chenguang Guo [8] ; Haipeng Zhang [8] ; Zebin Gao [9] ; Yuwei He [10] ; Xiangru Chen [10] ; Lei Zhao [11] ; Hong Yu [12] ; Jian Hu [5] ; Jiangang Zhao [5] ; Bin Li [13] ; Ci Yin [13] ; Wenjie Mao [13] ; Wanli Lin [14] ; Yujie Xie [14] ; Jixian Liu [15] ; Xiaoqiang Li [15] ; Dingwang Wu [15] ; Qinghua Hou [15] ; Yongbing Chen [16] ; Donglai Chen [17] ; Yuhang Xue [16] ; Yi Liang [18] ; Wenfang Tang [18] ; Qi Wang [19] ; Encheng Li [19] ; Hongxu Liu [20] ; Guan Wang [20] ; Pingwen Yu [20] ; Chun Chen [21] ; Bin Zheng [21] ; Hao Chen [21] ; Zhe Zhang [22] ; Lunqing Wang [22] ; Ailin Wang [22] ; Zongqi Li [22] ; Junke Fu [23] ; Guangjian Zhang [23] ; Jia Zhang [23] ; Bohao Liu [23] ; Jian Zhao [24] ; Boyun Deng [25] ; Yongtao Han [26] ; Xuefeng Leng [26] ; Zhiyu Li [26] ; Man Zhang [27] ; Changling Liu [28] ; Tianhu Wang [29] ; Zhilin Luo [29] ; Chenglin Yang [30] ; Xiaotong Guo [30] ; Kai Ma [30] ; Lixu Wang [30] ; Wenjun Jiang [31] ; Xu Han [31] ; Qing Wang [31] ; Kun Qiao [32] ; Zhaohua Xia [32] ; Shuo Zheng [32] ; Chenyang Xu [33] ; Jidong Peng [34] ; Shilong Wu [33] ; Zhifeng Zhang [35] ; Haoda Huang [35] ; Dazhi Pang [36] ; Qiao Liu [36] ; Jinglong Li [36] ; Xueru Ding [36] ; Xiang Liu [37] ; Liucheng Zhong [38] ; Yutong Lu [39] ; Feng Xu [40,*1] ; Qionghai Dai [41,*2] ; Jianxing He [42,*3] ;
机构： [1]School of Software, Beijing National Research Center for Information Science and Technology, Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing, China [2]Department of Thoracic Oncology and Surgery, China State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China [3]Institute for Brain and Cognitive Sciences, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China [4]Department of Thoracic Surgery, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China [5]Department of Thoracic Surgery, The First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China [6]Department of Thoracic Oncology and Surgery, China State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China , Guangdong Association of Thoracic Disease, Guangzhou, China [7]Department of Radiology, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China [8]Guangdong Association of Thoracic Disease, Guangzhou, China [9]School of Information Science and Technology, Fudan University, Shanghai, China [10]Hangzhou Zhuoxi Institute of Brain and Intelligence, Hangzhou, China [11]Department of Physiology, School of Basic Medical Sciences, Guangzhou Medical University, Guangzhou, China [12]Department of Radiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China [13]Department of Thoracic Surgery, Lanzhou University Second Hospital, Lanzhou University Second Clinical Medical College, Lanzhou, China [14]Department of Thoracic Surgery, Gaozhou People's Hospital, Gaozhou, China [15]Department of Thoracic Surgery, Peking University Shenzhen Hospital, Shenzhen, China [16]Department of Thoracic Surgery, The Second Affiliated Hospital of Soochow University, Suzhou, China [17]Department of Thoracic Surgery, Zhongshan Hospital Fudan University, Shanghai, China [18]Department of Cardiothoracic Surgery, Zhongshan City People's Hospital, Zhongshan, China [19]Department of Respiratory Medicine, The Second Hospital of Dalian Medical University, Dalian, China [20]Department of Thoracic Surgery, Cancer Hospital of Dalian University of Technology, Liaoning Cancer Hospital & Institute, Shenyang, China [21]Department of Thoracic Surgery, Fujian Medical University Union Hospital, Fuzhou, China [22]Department of Thoracic Surgery, Qingdao Municipal Hospital, University of Health and Rehabilitation Sciences, Qingdao, China [23]Department of Thoracic Surgery, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China [24]Department of Chest Surgery, Affiliated Cancer Hospital & Institute of Guangzhou Medical University, Guangzhou, China [25]Department of Thoracic Surgery, Central People's Hospital of Zhanjiang, Zhanjiang, China [26]Division of Thoracic Surgery, Sichuan Cancer Hospital & Institute, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China [27]Department of Thoracic Oncology and Surgery, China State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China , Department of Thoracic Surgery, The Affiliated Hospital of Inner Mongolia Medical University, Hohhot, China [28]Department of Thoracic Surgery, The Affiliated Hospital of Inner Mongolia Medical University, Hohhot, China [29]Department of Thoracic Surgery, The Third Affiliated Hospital of Chongqing Medical University, Chongqing, China [30]National Cancer Center, National Clinical Research Center for Cancer, Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China [31]Department of Thoracic Surgery, The Fourth Affiliated Hospital of China Medical University, Shenyang, China [32]Department of Thoracic Surgery, The Third People's Hospital of Shenzhen, Shenzhen, China [33]Department of Thoracic Surgery, Ganzhou People's Hospital, Ganzhou, China [34]Department of Radiology, Ganzhou People's Hospital, Ganzhou, China [35]Department of Cardiothoracic Surgery, Jieyang People's Hospital, Jieyang, China [36]Department of Thoracic Surgery, The University of Hong Kong-Shenzhen Hospital, Shenzhen, China [37]Department of Thoracic Surgery, The Second Affiliated Hospital, Hengyang Medical School, University of South China, Hengyang, China [38]Department of Radiology, Huizhou First People's Hospital, Huizhou, China [39]School of Computer Science and Engineering, Sun Yat-sen University, National Supercomputer Center, Guangzhou, China [40]School of Software, Beijing National Research Center for Information Science and Technology, Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing, China [41]Institute for Brain and Cognitive Sciences, Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China [42]Department of Thoracic Oncology and Surgery, China State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China
出处：
DOI： 10.1016/S2589-7500(23)00106-1
ISSN：

摘要：
Mediastinal neoplasms are typical thoracic diseases with increasing incidence in the general global population and can lead to poor prognosis. In clinical practice, the mediastinum's complex anatomic structures and intertype confusion among different mediastinal neoplasm pathologies severely hinder accurate diagnosis. To solve these difficulties, we organised a multicentre national collaboration on the basis of privacy-secured federated learning and developed CAIMEN, an efficient chest CT-based artificial intelligence (AI) mediastinal neoplasm diagnosis system.In this multicentre cohort study, 7825 mediastinal neoplasm cases and 796 normal controls were collected from 24 centres in China to develop CAIMEN. We further enhanced CAIMEN with several novel algorithms in a multiview, knowledge-transferred, multilevel decision-making pattern. CAIMEN was tested by internal (929 cases at 15 centres), external (1216 cases at five centres and a real-world cohort of 11 162 cases), and human-AI (60 positive cases from four centres and radiologists from 15 institutions) test sets to evaluate its detection, segmentation, and classification performance.In the external test experiments, the area under the receiver operating characteristic curve for detecting mediastinal neoplasms of CAIMEN was 0·973 (95% CI 0·969-0·977). In the real-world cohort, CAIMEN detected 13 false-negative cases confirmed by radiologists. The dice score for segmenting mediastinal neoplasms of CAIMEN was 0·765 (0·738-0·792). The mediastinal neoplasm classification top-1 and top-3 accuracy of CAIMEN were 0·523 (0·497-0·554) and 0·799 (0·778-0·822), respectively. In the human-AI test experiments, CAIMEN outperformed clinicians with top-1 and top-3 accuracy of 0·500 (0·383-0·633) and 0·800 (0·700-0·900), respectively. Meanwhile, with assistance from the computer aided diagnosis software based on CAIMEN, the 46 clinicians improved their average top-1 accuracy by 19·1% (0·345-0·411) and top-3 accuracy by 13·0% (0·545-0·616).For mediastinal neoplasms, CAIMEN can produce high diagnostic accuracy and assist the diagnosis of human experts, showing its potential for clinical practice.National Key R&D Program of China, National Natural Science Foundation of China, and Beijing Natural Science Foundation.Copyright © 2023 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.

基金：
National Key R&D Program of China, National Natural Science Foundation of China, and Beijing Natural Science Foundation.
语种：
外文
被引次数：
WOS：
PubmedID：
中科院(CAS)分区：
出版当年[2023]版：
大类 | 1 区 医学
小类 | 1 区 医学：信息 1 区 医学：内科
最新[2023]版：
大类 | 1 区 医学
小类 | 1 区 医学：信息 1 区 医学：内科
JCR分区：
出版当年[2023]版：
Q1 MEDICAL INFORMATICS Q1 MEDICINE, GENERAL & INTERNAL
最新[2023]版：
Q1 MEDICAL INFORMATICS Q1 MEDICINE, GENERAL & INTERNAL

影响因子： 最新[2023版] 最新五年平均 出版当年[2023版] 出版当年五年平均 出版前一年[2022版]

第一作者：
第一作者机构： [1]School of Software, Beijing National Research Center for Information Science and Technology, Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing, China
共同第一作者：
通讯作者：
通讯机构： [40]School of Software, Beijing National Research Center for Information Science and Technology, Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing, China [41]Institute for Brain and Cognitive Sciences, Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China [42]Department of Thoracic Oncology and Surgery, China State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China [*1]School of Software, Beijing National Research Center for Information Science and Technology, Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing 100084, China [*2]Institute for Brain and Cognitive Sciences, Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China [*3]Department of Thoracic Oncology and Surgery, China State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Disease, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou 510120, China
推荐引用方式(GB/T 7714)：
Ruijie Tang,Hengrui Liang,Yuchen Guo,et al.Pan-mediastinal neoplasm diagnosis via nationwide federated learning: a multicentre cohort study[J].LANCET DIGITAL HEALTH.2023,5(9):E560-E570.doi:10.1016/S2589-7500(23)00106-1.
APA：
Ruijie Tang,Hengrui Liang,Yuchen Guo,Zhigang Li,Zhichao Liu...&Jianxing He.(2023).Pan-mediastinal neoplasm diagnosis via nationwide federated learning: a multicentre cohort study.LANCET DIGITAL HEALTH,5,(9)
MLA：
Ruijie Tang,et al."Pan-mediastinal neoplasm diagnosis via nationwide federated learning: a multicentre cohort study".LANCET DIGITAL HEALTH 5..9(2023):E560-E570

资源点击量：46861 今日访问量：0 总访问量：3333 更新日期：2024-11-01 建议使用谷歌、火狐浏览器 常见问题

版权所有©2020 四川省肿瘤医院 技术支持：重庆聚合科技有限公司 地址：成都市人民南路四段55号