Search

With recent significant improvements in artificial intelligence (AI), especially in the field of deep learning, an increasing number of studies have evaluated the use of AI in endoscopy to detect and diagnose gastrointestinal (GI) lesions. The present review summarizes current publications on the use of AI in GI endoscopy and focuses on the challenges and future of AI‐aided systems. We expect AI to provide an effective and practical method for endoscopists in lesion detection and characterization as well as in quality control in endoscopy. However, so far, most studies have remained at the preclinical stage. More attention should be paid in the future to the use of AI in real‐life clinical applications. [ABSTRACT FROM AUTHOR]

Peroral endoscopic myotomy ( POEM) is a natural orifice, translumenal endoscopic surgical procedure that achieves endoscopic myotomy by conducting a submucosal tunnel as an operating space. It is conventionally performed in achalasia. Recently, several centers worldwide have reported the feasibility of this procedure not only in early achalasia but also in other particular patient cohorts. Possible indications for POEM include previously failed Heller myotomy, pneumatic balloon dilatation or POEM, sigmoid achalasia, pediatric patients, spastic esophagus disorders, Zenker's diverticulum and gastroparesis. However, its application in large numbers of special patient groups awaits knowledge of the long-term outcome and greater experience with POEM. [ABSTRACT FROM AUTHOR]

Th article reports on the perioperative medications during endoscopic submucosal dissection (ESD) for gastric lesions. Topics discussed include the indications and contraindications of gastric ESD, complications of ESD, and diagnosis of perforation. Also being discussed are the aim and types of perioperative medications.

Objectives Confocal laser endomicroscopy ( CLE) consists of endoscope-based CLE ( eCLE) and probe-based CLE ( pCLE). This study aimed to compare e CLE and pCLE in their diagnostic yield in different parts of the gastrointestinal ( GI) tract. Methods Consecutive patients were scheduled for CLE examination due to GI symptoms. All patients were randomly assigned to eCLE or pCLE group and underwent a programmed procedure using one type of CLE. Differences in procedure time, complication rate, CLE image quality and image acquisition feasibility between these two types of CLE for esophagogastroduodenoscopy (EGD) and colonoscopy were calculated. Results Altogether 513 CLE procedures were performed, including 324 EGD and 189 colonoscopy. The procedure time of pCLE was significantly shorter than that of eCLE both in EGD and colonoscopy (16.78 min vs 18.13 min for EGD, P = 0.027; 32.48 min vs 39.89 min for colonoscopy, P < 0.001). No significant difference was found between these two types of CLE in diagnostic utility, including the detection and prediction of histopathological results of the lesions. The CLE image quality of both e CLE and p CLE were comparable in the stomach and colon, but eCLE seemed to be superior to pCLE in examining the esophagus. Colonoscopy using pCLE had a higher complete rate than that of eCLE, although the difference was not statistically significant ( P = 0.065). Conclusions pCLE is more flexible in diagnosing GI diseases with a shorter procedure time than eCLE regardless of comparable diagnostic yields, except the diagnosis of esophageal diseases in which eCLE provides better image quality. [ABSTRACT FROM AUTHOR]

Objective This study aimed to compare the diagnostic value and image quality of high-definition magnifying white light endoscopy ( M- WLE) and high-definition magnifying endoscopy with i-scan ( M-i-scan) for Helicobacter pylori ( H. pylori) infection. Methods Patients complaining of dyspepsia who underwent esophagogastroduodenoscopy at the Endoscopy Unit of Qilu Hospital ( Jinan, Shandong Province, China) from January to March, 2011 were prospectively recruited. The greater curvature of the stomach was carefully observed using both M- WLE and M-i-scan. The gastric mucosal classification and image quality scores were recorded. The relationship between gastric mucosal classification and final diagnosis of H. pylori infection was determined. Results A total of 84 patients were recruited in this study. The accuracy and specificity of the combination of types 2-3 patterns predicting H. pylori infection were significantly higher for M-i-scan than those for M- WLE (accuracy: 94.0% vs 84.5%, P = 0.046; and specificity: 93.5% vs 80.6%, P = 0.032), while the sensitivity of the two modes was the same. The M-i-scan provided a better image quality for H. pylori infection than M- WLE ( P < 0.001). Conclusion The M-i-scan may be superior to M- WLE for the prediction of H. pylori infection, but its diagnostic sensitivity needs to be improved. [ABSTRACT FROM AUTHOR]