1. Effects of diabetes on rebleeding after endoscopic treatment in liver cirrhosis patients with esophageal varices
Xi WANG ; Xuecan MEI ; Na ZHANG ; Derun KONG
Chinese Journal of Digestive Endoscopy 2020;37(1):33-37
Objective:
To investigate whether combined diabetes affects rebleeding after endoscopic treatment in cirrhosis patients with esophageal varices.
Methods:
A total of 207 liver cirrhosis cases with esophageal varices bleeding who underwent initial treatment of endoscopic variced ligation or endoscopic injection sclerotherapy in the First Affiliated Hospital of Anhui Medical University from June 2015 to March 2018 were included in the retrospective study. The cases were divided into bleeding group (n=54) and non-bleeding group (n=153) according to the presence or absence of rebleeding within 6 months after treatment. The influencing factors on postoperative bleeding were analyzed by univariate analysis and logistic regession analysis.
Results:
Univariate analysis showed that gender composition, age, presence or absence of portal vein thrombosis, smoking history, drinking history (
2.Comparative analysis of endoscopic ligation and tissue adhesive injection for tortuous gastric varices
Yi XIANG ; Xi WANG ; Xuecan MEI ; Wenyue WU ; Fumin ZHANG ; Zexue WANG ; Yi HAN ; Kai WANG ; Derun KONG
Chinese Journal of Digestive Endoscopy 2021;38(11):901-906
Objective:To evaluate the risks and benefits of endoscopic ligation and tissue adhesive injection for tortuous gastric varices.Methods:A total of 193 patients with esophagogastric varices, who underwent endoscopic variceal ligation or endoscopic tissue adhesive injection in Department of Gastroenterology of the First Affiliated Hospital of Anhui Medical University from June 2015 to June 2020, were included in the retrospective analysis. These cases were connected vessels (type Le and gf based on LDRf standard) of tortuous gastric varices (F1 in Hashizume standard). According to the treatment, the patients were divided into three groups: gastric fundus and esophageal ligation group (endoscopic ligation of gastric fundus and esophageal varices, 32 cases), tissue adhesive group (endoscopic tissue adhesive injection of gastric varices, endoscopic ligation of esophageal varices, 71 cases) and esophageal ligation group (endoscopic ligation of esophageal varices, 90 cases). The re-bleeding rate, the effectiveness rate, the significant effectiveness rate and complications of the three groups were compared.Results:The rates of re-bleeding in gastric fundus and esophageal ligation group, tissue adhesive group and esophageal ligation group were 18.75% (6/32), 12.68% (9/71) and 3.33% (3/90), respectively.There was significant difference only between gastric fundus and esophageal ligation group and esophageal ligation group ( χ2=6.110, P<0.016). The effectiveness rates of the three groups were all 100.00%. The significant effectiveness rates in gastric fundus and esophageal ligation group, tissue adhesive group and esophageal ligation group were 37.50% (12/32), 25.35% (18/71) and 14.44% (13/90), respectively. There was significant difference only between gastric fundus and esophageal ligation group and esophageal ligation group ( χ2=7.702, P<0.016). No pulmonary infection, hepatic encephalopathy, spontaneous bacterial peritonitis or perforation occurred in the three groups.The incidences of chest pain or abdominal pain in gastric fundus and esophageal ligation group, tissue adhesive group and esophageal ligation group were 18.75% (6/32), 11.27% (8/71) and 2.22% (2/90), respectively.There was significant difference only between gastric fundus and esophageal ligation group and esophageal ligation group ( χ2=10.524, P<0.016). There was no significant difference in the incidence of fever, nausea or vomiting among the three groups ( P>0.05). Conclusion:Simultaneous endoscopic ligation of gastric fundus and esophageal varices, and endoscopic tissue adhesive injection of gastric varices combined with endoscopic ligation of esophageal varices is of no benefit for patients with tortuous gastric varices, but endoscopic ligation of esophageal varices alone may yield more benefit.
3.Detection of early gastric cancer in white light imagings based on region-based convolutional neural networks
Jing Jin ; Qianqian Zhang ; Bill Dong ; Tao Ma ; Xi Wang ; Xuecan Mei ; Shaofang Song ; Jie Peng ; Aijiu Wu ; Lanfang Dong ; Derun Kong
Acta Universitatis Medicinalis Anhui 2023;58(2):285-291
Objective :
To develop an endoscopic automatic detection system in early gastric cancer (EGC) based on a region-based convolutional neural network ( Mask R-CNN) .
Methods :
A total of 3 579 and 892 white light images (WLI) of EGC were obtained from the First Affiliated Hospital of Anhui Medical University for training and testing,respectively.Then,10 WLI videos were obtained prospectively to test dynamic performance of the RCNN system.In addition,400 WLI images were randomly selected for comparison with the Mask R-CNN system and endoscopists.Diagnostic ability was assessed by accuracy,sensitivity,specificity,positive predictive value ( PPV) , and negative predictive value (NPV) .
Results :
The accuracy,sensitivity and specificity of the Mask R-CNN system in diagnosing EGC in WLI images were 90. 25% ,91. 06% and 89. 01% ,respectively,and there was no significant statistical difference with the results of pathological diagnosis.Among WLI real-time videos,the diagnostic accuracy was 90. 27%.The speed of test videos was up to 35 frames / s in real time.In the controlled experiment, the sensitivity of Maks R-CNN system was higher than that of the experts (93. 00% vs 80. 20% ,χ2 = 7. 059,P < 0. 001) ,and the specificity was higher than that of the juniors (82. 67% vs 71. 87% ,χ2 = 9. 955,P<0. 001) , and the overall accuracy rate was higher than that of the seniors (85. 25% vs 78. 00% ,χ2 = 7. 009,P<0. 001) .
Conclusion
The Mask R-CNN system has excellent performance for detection of EGC under WLI,which has great potential for practical clinical application.