RESUMO
Objective:To explore the feasibility of smart phone real-time picture exchange-assisted telecytopathology for rapid on-site evaluation (tele-ROSE), and the role of tele-ROSE in improving the diagnostic efficiency of endoscopic physicians.Methods:Data of patients who underwent endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) from April 2020 to May 2021 in Qilu Hospital of Shandong University were retrospectively collected. Patients who didn't receive ROSE from April 2020 to October 2020 were enrolled in the non-ROSE group, and those who underwent ROSE from November 2020 to May 2021 were enrolled in the ROSE group, of which endosonographers used WeChat on the smartphone to send ROSE images to cytopathologists from November 2020 to March 2021 were the mobile phone group, and those whose ROSE results independently diagnosed by trained endosonographers from April 2021 to May 2021 were the self-ROSE group. Basic information, ROSE results, postoperative pathology and follow-up were compared, and the diagnostic effectiveness of tele-ROSE was analyzed.Results:A total of 188 cases were included, of which 179 cases (95.2%) were solid pancreatic lesions and 9 (4.8%) were enterocoelia lesions. There was no significant difference in the puncture time among the non-ROSE, mobile phone and self-ROSE groups [3 (3, 4) VS 3 (3, 4) VS 3 (2, 4), H=1.320, P=0.517]. With the final diagnosis as the golden standard, the sensitivity, the specificity, the accuracy, the positive predictive value, the negative predictive value and Kappa value of the non-ROSE group were 80.6% (58/72), 89.5% (17/19), 82.4% (75/91), 96.7% (58/60), 54.8% (17/31), and 0.6 respectively. The corresponding indices in the ROSE group were 97.4% (74/76), 100.0% (21/21), 97.9% (95/97), 100.0% (74/74), 91.3% (21/23), and 0.9 respectively, those of the mobile phone group were 95.2% (40/42), 100.0% (10/10), 96.2% (50/52), 100.0% (40/40), 83.3% (10/12), and 0.9 respcetively, and those of the self-ROSE group were 100.0% (34/34), 100.0% (11/11), 100.0% (45/45), 100.0% (34/34), 100.0% (11/11), and 1.0 respectively. The sensitivity ( P=0.002), the accuracy ( P=0.001) and the negative predictive value ( P=0.009) of the ROSE group were significantly higher than those of the non-ROSE group, and there was no significant difference in other diagnostic efficacy indices ( P>0.05). There was no significant difference between the mobile phone group and the self-ROSE group in diagnostic efficacy ( P>0.05). Conclusion:Instant smartphone-assisted tele-ROSE through WeChat can well meet the needs of pathologists and endoscopic physicians. After the application of tele-ROSE training, the diagnostic accuracy of endoscopic physicians is equivalent to that of cytopathologist, which helps to obtain more sufficient specimens under endoscopy and improve the diagnostic accuracy of EUS-FNA.
RESUMO
Objective:Based on the artificial intelligence (AI) technology in endoscopy and the internet platform, to explore and construct a safe, standardized, scientific and rigorous database for digestive endoscopy, and to provide reference and evidence for the data quality control of AI in digestive endoscopy in China.Methods:After referring to relevant guidelines and standards, data collection and labelling standards of digestive endoscopy of 12 common gastrointestinal diseases were determined. The software of online collection and labelling of multi-center digestive endoscopy data in Shandong Province was developed. Endoscopic equipment with a domestic market share of >5% was used and dozens of experienced endoscopists from 9 medical centers in Shandong Province were uniformly trained for data labelling. From July 2019 to July 2020, the endoscopic examination data from 9 medical centers including Qilu Hospital of Shandong University, Shandong Provincial Hospital , Liaocheng People′s Hospital, Linyi People′s Hospital, Weihai Municipal Hospital, Taian City Central Hospital, Binzhou Medical University Hospital, Yantai Yuhuangding Hospital and Qilu Hospital of Shandong University (Qingdao) were prospectively and continuously collected and labeled. The optimized, desensitized, and generalized data were uploaded to the server. After the file synchronization, data processing, and expert review, a multi-center digestive endoscopy AI database with standard data collection and labelling in Shandong Province was constructed, namely cloud platform. Descriptive methods were used for statistical analysis.Results:The collection and labelling standards for multi-center digestive endoscopy AI data in Shandong province was established. The software of online collection and labelling of multi-center digestive endoscopy AI data in Shandong province was developed. The database in Shandong province was successfully constructed. In the database, 43 010 lesions, 40 353 images, and 11 289 examinations were labeled. Among them, there were 2 906 cases of early esophageal cancer, 2 912 cases of early gastric cancer, 2 397 cases of early colorectal cancer, and 9 773 cases of colorectal polyps (5 539 cases of adenomatous polyps, 1 161 cases of non-adenomatous polyps and 3 073 case of undetermined polyps).Conclusions:The multi-center AI cloud platform for digestive endoscopy in Shandong Province adopts unified standards and collection and labeling software, which ensures the safety and standardization of endoscopy data. It provides a reference and basis for the construction of a quality control system for standardized data collection and labelling of digestive endoscopy AI data in our country and for the third-party data supervision.