Two-step artificial intelligence system for endoscopic gastric biopsy improves the diagnostic accuracy of pathologists.

Autor:	Zhu Y; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai, China., Yuan W; Department of Pathology, Zhongshan Hospital, Fudan University, Shanghai, China., Xie CM; Ping An Healthcare Technology, Shanghai, China., Xu W; Department of Gastroenterology, Jiangyin Hospital Affiliated to Nanjing University of Chinese Medicine, Jiangsu, China., Wang JP; Ping An Healthcare Technology, Shanghai, China., Feng L; Endoscopy Center, Central Hospital of Minhang District, Shanghai, China., Wu HL; Department of Gastroenterology , Zhengzhou Central Hospital, Henan, China., Lu PX; Endoscopy Center, Central Hospital of Xuhui District, Shanghai, China., Geng ZH; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai, China., Lv CF; Ping An Healthcare Technology, Shanghai, China., Li QL; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai, China., Hou YY; Department of Pathology, Zhongshan Hospital, Fudan University, Shanghai, China., Chen WF; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai, China., Zhou PH; Endoscopy Center and Endoscopy Research Institute, Zhongshan Hospital, Fudan University, Shanghai, China.; Shanghai Collaborative Innovation Center of Endoscopy, Shanghai, China.
Jazyk:	angličtina
Zdroj:	Frontiers in oncology [Front Oncol] 2022 Sep 23; Vol. 12, pp. 1008537. Date of Electronic Publication: 2022 Sep 23 (Print Publication: 2022).
DOI:	10.3389/fonc.2022.1008537
Abstrakt:	Background: Endoscopic biopsy is the pivotal procedure for the diagnosis of gastric cancer. In this study, we applied whole-slide images (WSIs) of endoscopic gastric biopsy specimens to develop an endoscopic gastric biopsy assistant system (EGBAS). Methods: The EGBAS was trained using 2373 WSIs expertly annotated and internally validated on 245 WSIs. A large-scale, multicenter test dataset of 2003 WSIs was used to externally evaluate EGBAS. Eight pathologists were compared with the EGBAS using a man-machine comparison test dataset. The fully manual performance of the pathologists was also compared with semi-manual performance using EGBAS assistance. Results: The average area under the curve of the EGBAS was 0·979 (0·958-0·990). For the diagnosis of all four categories, the overall accuracy of EGBAS was 86·95%, which was significantly higher than pathologists (P< 0·05). The EGBAS achieved a higher κ score (0·880, very good κ) than junior and senior pathologists (0·641 ± 0·088 and 0·729 ± 0·056). With EGBAS assistance, the overall accuracy (four-tier classification) of the pathologists increased from 66·49 ± 7·73% to 73·83 ± 5·73% (P< 0·05). The length of time for pathologists to manually complete the dataset was 461·44 ± 117·96 minutes; this time was reduced to 305·71 ± 82·43 minutes with EGBAS assistance (P = 0·00). Conclusions: The EGBAS is a promising system for improving the diagnosis ability and reducing the workload of pathologists. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2022 Zhu, Yuan, Xie, Xu, Wang, Feng, Wu, Lu, Geng, Lv, Li, Hou, Chen and Zhou.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu