Background and Aim Although endoscopic resection with careful surveillance instead of total proctocolectomy become to be permitted for visible low‐grade dysplasia, it is unclear how accurately endoscopists can differentiate these lesions, as classifying neoplasias occurring in inflammatory bowel disease (IBDN) is exceedingly challenging due to background chronic inflammation. We evaluated a pilot model of an artificial intelligence (AI) system for classifying IBDN and compared it with the endoscopist's ability. Methods This study used a deep convolutional neural network, the EfficientNet‐B3. Among patients who underwent treatment for IBDN at two hospitals between 2003 and 2021, we selected 862 non‐magnified endoscopic images from 99 IBDN lesions and utilized 6 375 352 images that were increased by data augmentation for the development of AI. We evaluated the diagnostic ability of AI using two classifications: the “adenocarcinoma/high‐grade dysplasia” and “low‐grade dysplasia/sporadic adenoma/normal mucosa” groups. We compared the diagnostic accuracy between AI and endoscopists (three non‐experts and four experts) using 186 test set images. Results The diagnostic ability of the experts/non‐experts/AI for the two classifications in the test set images had a sensitivity of 60.5% (95% confidence interval [CI]: 54.5–66.3)/70.5% (95% CI: 63.8–76.6)/72.5% (95% CI: 60.4–82.5), specificity of 88.0% (95% CI: 84.7–90.8)/78.8% (95% CI: 74.3–83.1)/82.9% (95% CI: 74.8–89.2), and accuracy of 77.8% (95% CI: 74.7–80.8)/75.8% (95% CI: 72–79.3)/79.0% (95% CI: 72.5–84.6), respectively. Conclusions The diagnostic accuracy of the two classifications of IBDN was higher than that of the experts. Our AI system is valuable enough to contribute to the next generation of clinical practice.
Objective This study aimed to determine the prevalence and endoscopic features of zinc acetate dihydrate tablet-associated gastric lesions. Methods We retrospectively examined the endoscopic features of 47 patients taking zinc acetate dihydrate tablets who underwent esophagogastroduodenoscopy. Results Gastric mucosal alterations, including redness, erosions, ulcers, and adhesion of the white coat, were observed in 29 of 47 patients (61.7%). Among patients with gastric lesions (group A), there was a significantly higher percentage of symptomatic patients in comparison to patients without lesions (group B) (65.5% vs. 22.2%; p<0.01). The background characteristics of the two groups did not differ to a statistically significant extent. On esophagogastroduodenoscopy, mucosal redness (n=27, 93.1%), erosions (n=26, 90.0%), adhesion of the white coat (n=25, 86.2%), and ulcers (n=9, 31.0%) were observed. None of the 19 patients who previously underwent esophagogastroduodenoscopy had gastric lesions before starting zinc acetate dihydrate. Esophagogastroduodenoscopy was performed after the cessation of zinc acetate dihydrate intake in six patients, and revealed the resolution of gastric lesions. Conclusion Gastric lesions were observed in 29 of 47 patients who were taking zinc acetate dihydrate tablets. The most common endoscopic findings were mucosal redness (93.1%), erosions (90.0%), adhesion of the white coat (86.2%), and ulcers (31.0%). Although the exact pathogenesis is uncertain, we believe that understanding the unique manifestations of this gastric lesion will help physicians manage adverse events in patients taking zinc acetate dihydrate tablets.
Objective Although Barrett's adenocarcinoma (BA) remains a minor disease in Japan, its incidence has been gradually increasing. We analyzed the characteristics of BA in Japanese populations. Methods We retrospectively reviewed medical records and analyzed the clinicopathological differences between short-segment Barrett's esophagus (SSBE) and long-segment Barrett's esophagus (LSBE), as well as metastasis. Local recurrence and metachronous lesions were analyzed only in patients who underwent endoscopic resection (ER). Patients Consecutive patients who had pathological T1 BAs resected by ER or surgery from January 2003 to December 2017. Results A total of 168 patients were analyzed, including 139 with SSBE and 29 with LSBE. In total, 67% of the SSBE lesions and 32% of the LSBE lesions were located between 0 and 3 o'clock (p=0.0014). No patients who achieved pathological margin-free resection (pR0) and 17% of patients who did not achieve pR0 experienced local recurrence (p=0.0131). None of the patients without lymphovascular involvement, a poorly differentiated component, lesion size of >30 mm, and submucosal invasion of >500 μm experienced metastasis. The 5-year cumulative incidence rate of metachronous BA after ER was 0% in patients with SSBE and 40% in patients with LSBE (p=0.0005). Conclusion Superficial BA was likely to be detected at the right anterior wall of SSBE in the Japanese population. The risk for metachronous BA after ER was high in Japanese patients with LSBE, as in Western patients.
A 45-year-old Japanese man underwent esophagogastroduodenoscopy, which revealed spotty redness at the gastric fornix, mucosal swelling, diffuse redness in the corpus, and mucosal atrophy in the gastric angle and antrum. Histological examination showed rod-shaped bacteria that appeared larger than Helicobacter pylori. The patient tested positive for rapid urease test, and serum anti-H. pylori IgG antibody test results were negative. Further examination of the bacteria revealed that H. suis antibody test was positive, and the presence of H. suis was confirmed using H. suis-specific real-time PCR. H. suis was successfully eradicated after triple therapy with vonoprazan, amoxicillin, and clarithromycin. This case reinforces the notion that non-H. pylori Helicobacter species such as H. suis and H. heilmannii may be involved in the pathogenesis of active gastritis in patients who test negative for H. pylori antibodies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.