Deep learning for colorectal cancer detection in contrast-enhanced CT without bowel preparation: a retrospective, multicentre study
作者全名：Yao, Lisha; Li, Suyun; Tao, Quan; Mao, Yun; Dong, Jie; Lu, Cheng; Han, Chu; Qiu, Bingjiang; Huang, Yanqi; Huang, Xin; Liang, Yanting; Lin, Huan; Guo, Yongmei; Liang, Yingying; Chen, Yizhou; Lin, Jie; Chen, Enyan; Jia, Yanlian; Chen, Zhihong; Zheng, Bochi; Ling, Tong; Liu, Shunli; Tong, Tong; Cao, Wuteng; Zhang, Ruiping; Chen, Xin; Liu, Zaiyi
作者地址：[Yao, Lisha; Li, Suyun; Lu, Cheng; Han, Chu; Qiu, Bingjiang; Huang, Yanqi; Huang, Xin; Liang, Yanting; Lin, Huan; Ling, Tong; Liu, Zaiyi] Southern Med Univ, Guangdong Prov Peoples Hosp, Guangdong Acad Med Sci, Dept Radiol, Guangzhou 510080, Peoples R China; [Yao, Lisha; Lin, Huan; Liu, Zaiyi] South China Univ Technol, Sch Med, Guangzhou, Peoples R China; [Yao, Lisha; Li, Suyun; Lu, Cheng; Han, Chu; Qiu, Bingjiang; Huang, Yanqi; Huang, Xin; Liang, Yanting; Lin, Huan; Ling, Tong; Liu, Zaiyi] Guangdong Prov Key Lab Artificial Intelligence Med, Guangzhou, Peoples R China; [Li, Suyun; Liang, Yanting] South Med Univ, Sch Med, Guangzhou, Peoples R China; [Tao, Quan] Southern Med Univ, Zhujiang Hosp, Dept Rehabil Med, Guangzhou, Peoples R China; [Mao, Yun] Chongqing Med Univ, Affiliated Hosp 1, Dept Radiol, Chongqing, Peoples R China; [Dong, Jie; Zhang, Ruiping] Shanxi Med Univ, Shanxi Bethune Hosp, Affiliated Hosp 3, Shanxi Acad Med Sci,Dept Radiol, Taiyuan, Peoples R China; [Lu, Cheng; Han, Chu] Southern Med Univ, Guangdong Prov Peoples Hosp, Med Res Inst, Guangdong Acad Med Sci, Guangzhou, Peoples R China; [Qiu, Bingjiang] Guangdong Prov Peoples Hosp, Guangdong Acad Sci, Guangdong Cardiovasc Inst, Guangzhou, Peoples R China; [Huang, Xin] Shantou Univ, Med Coll, Sch Med, Shantou, Peoples R China; [Guo, Yongmei; Liang, Yingying; Chen, Xin] South China Univ Technol, Guangzhou Peoples Hosp 1, Dept Radiol, Guangzhou, Peoples R China; [Chen, Yizhou; Lin, Jie; Chen, Enyan] Southern Med Univ, Puning Peoples Hosp, Dept Radiol, Jieyang, Peoples R China; [Jia, Yanlian] Liaobu Hosp Guangdong, Dept Radiol, Dongguan, Peoples R China; [Chen, Zhihong] Guangzhou Univ, Inst Comp Sci & Technol, Guangzhou, Peoples R China; [Zheng, Bochi] Southern Univ Sci & Technol, Dept Biomed Engn, Shenzhen, Peoples R China; [Liu, Shunli] Qingdao Univ, Affiliated Hosp, Dept Radiol, Qingdao, Peoples R China; [Tong, Tong] Fudan Univ, Shanghai Canc Ctr, Dept Radiol, Shanghai, Peoples R China; [Tong, Tong] Fudan Univ, Shanghai Med Coll, Dept Oncol, Shanghai, Peoples R China; [Cao, Wuteng] Sun Yat sen Univ, Affiliated Hosp 6, Dept Radiol, Guangzhou, Peoples R China; [Zhang, Ruiping] Shanxi Med Univ, Shanxi Bethune Hosp, Shanxi Acad Med Sci, Dept Radiol, Taiyuan 030032, Peoples R China; [Chen, Xin] South China Univ Technol, Guangzhou Peoples Hosp 1, Sch Med, Dept Radiol, Guangzhou 510180, Peoples R China
通信作者：Liu, ZY (通讯作者)，Southern Med Univ, Guangdong Prov Peoples Hosp, Guangdong Acad Med Sci, Dept Radiol, Guangzhou 510080, Peoples R China.; Zhang, RP (通讯作者)，Shanxi Med Univ, Shanxi Bethune Hosp, Shanxi Acad Med Sci, Dept Radiol, Taiyuan 030032, Peoples R China.; Chen, X (通讯作者)，South China Univ Technol, Guangzhou Peoples Hosp 1, Sch Med, Dept Radiol, Guangzhou 510180, Peoples R China.
来源：EBIOMEDICINE
ESI学科分类：CLINICAL MEDICINE
WOS号：WOS:001252787700001
JCR分区：Q1
影响因子：9.7
年份：2024
卷号：104
期号：
开始页：
结束页：
文献类型：Article
关键词：
摘要：Background Contrast-enhanced CT scans provide a means to detect unsuspected colorectal cancer. However, colorectal cancers in contrast-enhanced CT without bowel preparation may elude detection by radiologists. We aimed to develop a deep learning (DL) model for accurate detection of colorectal cancer, and evaluate whether it could improve the detection performance of radiologists. Methods We developed a DL model using a manually annotated dataset (1196 cancer vs 1034 normal). The DL model was tested using an internal test set (98 vs 115), two external test sets (202 vs 265 in 1, and 252 vs 481 in 2), and a real-world test set (53 vs 1524). We compared the detection performance of the DL model with radiologists, and evaluated its capacity to enhance radiologists ' detection performance. Findings In the four test sets, the DL model had the area under the receiver operating characteristic curves (AUCs) ranging between 0.957 and 0.994. In both the internal test set and external test set 1, the DL model yielded higher accuracy than that of radiologists (97.2% vs 86.0%, p < 0.0001; 94.9% vs 85.3%, p < 0.0001), and significantly improved the accuracy of radiologists (93.4% vs 86.0%, p < 0.0001; 93.6% vs 85.3%, p < 0.0001). In the real -world test set, the DL model delivered sensitivity comparable to that of radiologists who had been informed about clinical indications for most cancer cases (94.3% vs 96.2%, p > 0.99), and it detected 2 cases that had been missed by radiologists. Interpretation The developed DL model can accurately detect colorectal cancer and improve radiologists ' detection performance, showing its potential as an effective computer -aided detection tool.
基金机构：National Science Fund for Distinguished Young Scholars of China [81925023]; Regional Innovation and Development Joint Fund of National Natural Science Foundation of China [U22A20345]; National Natural Science Foundation of China [82072090, 82371954]; Guangdong Provincial Key Laboratory of Arti fi cial Intelligence in Medical Image Analysis and Application [2022B1212010011]; High-level Hospital Construction Project [DFJHBF202105]
基金资助正文：Funding This study was supported by National Science Fund for Distinguished Young Scholars of China (No. 81925023) ; Regional Innovation and Development Joint Fund of National Natural Science Foundation of China (No. U22A20345) ; National Natural Science Foundation of China (No. 82072090 and No. 82371954) ; Guangdong Provincial Key Laboratory of Arti fi cial Intelligence in Medical Image Analysis and Application (No. 2022B1212010011) ; High-level Hospital Construction Project (No. DFJHBF202105) .
