Pan-mediastinal neoplasm diagnosis via nationwide federated learning: a multicentre cohort study.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Tang Ruijie, Liang Hengrui, Guo Yuchen, Li Zhigang, Liu Zhichao, Lin Xu, Yan Zeping, Liu Jun, Xu Xin, Shao Wenlong, Li Shuben, Liang Wenhua, Wang Wei, Cui Fei, He Huanghe, Yang Chao, Jiang Long, Wang Haixuan, Chen Huai, Guo Chenguang, Zhang Haipeng, Gao Zebin, He Yuwei, Chen Xiangru, Zhao Lei, Yu Hong, Hu Jian, Zhao Jiangang, Li Bin, Yin Ci, Mao Wenjie, Lin Wanli, Xie Yujie, Liu Jixian, Li Xiaoqiang, Wu Dingwang, Hou Qinghua, Chen Yongbing, Chen Donglai, Xue Yuhang, Liang Yi, Tang Wenfang, Wang Qi, Li Encheng, Liu Hongxu, Wang Guan, Yu Pingwen, Chen Chun, Zheng Bin, Chen Hao, Zhang Zhe, Wang Lunqing, Wang Ailin, Li Zongqi, Fu Junke, Zhang Guangjian, Zhang Jia, Liu Bohao, Zhao Jian, Deng Boyun, Han Yongtao, Leng Xuefeng, Li Zhiyu, Zhang Man, Liu Changling, Wang Tianhu, Luo Zhilin, Yang Chenglin, Guo Xiaotong, Ma Kai, Wang Lixu, Jiang Wenjun, Han Xu, Wang Qing, Qiao Kun, Xia Zhaohua, Zheng Shuo, Xu Chenyang, Peng Jidong, Wu Shilong, Zhang Zhifeng, Huang Haoda, Pang Dazhi, Liu Qiao, Li Jinglong, Ding Xueru, Liu Xiang, Zhong Liucheng, Lu Yutong, Xu Feng, Dai Qionghai, He Jianxing
Аннотация
METHODS: 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.
FINDINGS: 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).
INTERPRETATION: For mediastinal neoplasms, CAIMEN can produce high diagnostic accuracy and assist the diagnosis of human experts, showing its potential for clinical practice.
FUNDING: National Key R&D Program of China, National Natural Science Foundation of China, and Beijing Natural Science Foundation.