Rxivist logo

Artificial intelligence assisted standard white light endoscopy accurately characters early colorectal cancer: a multicenter diagnostic study

By Sijun Meng, Yueping Zheng, Ruizhang Su, Wangyue Wang, Yu Zhang, Hang Xiao, Zhaofang Han, Wen Zhang, Wenjuan Qin, Chen Yang, Lichong Yan, Haineng Xu, Yemei Bu, Yuhuan Zhong, Yi Zhang, Yulong He, Hesong Qiu, Wen Xu, Hong Chen, Siqi Wu, Zhenghua Jiang, Yongxiu Zhang, Chao Dong, Yongchao Hu, Lizhong Xie, Xugong Li, Jianping Jiang, Huafen Zhu, Wenxia Li, Zhang Wen, Xiaofang Zheng, Yuanlong Sun, Xiaolu Zhou, Limin Ding, Changhua Zhang, Wensheng Pan, Shuisheng Wu, Yiqun Hu

Posted 23 Feb 2020
medRxiv DOI: 10.1101/2020.02.21.20025650

Colorectal cancer (CRC) is the third in incidence and mortality1 of cancer. Screening with colonoscopy has been shown to reduce mortality by 40-60%2. Challenge for screening indistinguishable precancerous and noninvasive lesion using conventional colonoscopy was still existing3. We propose to establish a propagable artificial intelligence assisted high malignant potential early CRC characterization system (ECRC-CAD). 4,390 endoscopic images of early CRC were used to establish the model. The diagnostic accuracy of high malignant potential early CRC was 0.963 (95% CI, 0.941-0.978) in the internal validation set and 0.835 (95% CI, 0.805-0.862) in external datasets. It achieved better performance than the expert endoscopists. Spreading of ECRC-CAD to regions with different medical levels can assist in CRC screening and prevention.

Download data

  • Downloaded 299 times
  • Download rankings, all-time:
    • Site-wide: 91,980
    • In oncology: 166
  • Year to date:
    • Site-wide: 70,207
  • Since beginning of last month:
    • Site-wide: 61,442

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

News