Application of artificial intelligence in the diagnosis of subepithelial lesions using endoscopic ultrasonography: a systematic review and meta-analysis

Abstract

Endoscopic ultrasonography (EUS) is the most common method for diagnosing gastrointestinal subepithelial lesions (SELs); however, it usually requires histopathological confirmation using invasive methods. Artificial intelligence (AI) algorithms have made significant progress in medical imaging diagnosis. The purpose of our research was to explore the application of AI in the diagnosis of SELs using EUS and to evaluate the diagnostic performance of AI-assisted EUS. Three databases, PubMed, EMBASE, and the Cochrane Library, were comprehensively searched for relevant literature. RevMan 5.4.1 and Stata 17.0, were used to calculate and analyze the combined sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and summary receiver-operating characteristic curve (SROC). Eight studies were selected from 380 potentially relevant studies for the meta-analysis of AI-aided EUS diagnosis of SELs. The combined sensitivity, specificity, and DOR of AI-aided EUS were 0.92 (95% CI, 0.85-0.96), 0.80 (95% CI, 0.70-0.87), and 46.27 (95% CI, 19.36-110.59), respectively). The area under the curve (AUC) was 0.92 (95% CI, 0.90-0.94). The AI model in differentiating GIST from leiomyoma had a pooled AUC of 0.95, sensitivity of 0.93, specificity of 0.88, PLR of 8.04, and NLR of 0.08. The combined sensitivity, specificity, and AUC of the AI-aided EUS diagnosis in the convolutional neural network (CNN) model were 0.93, 0.81, and 0.94, respectively. AI-aided EUS diagnosis using conventional brightness mode (B-mode) EUS images had a combined sensitivity of 0.92, specificity of 0.79, and AUC of 0.92. AI-aided EUS diagnosis based on patients had a combined sensitivity, specificity, and AUC of 0.95, 0.83, and 0.96, respectively. Additionally, AI-aided EUS was superior to EUS by experts in terms of sensitivity (0.93 vs. 0.71), specificity (0.81 vs. 0.69), and AUC (0.94 vs. 0.75). In conclusion, AI-assisted EUS is a promising and reliable method for distinguishing SELs, with excellent diagnostic performance. More multicenter cohort and prospective studies are expected to be conducted to further develop AI-assisted real-time diagnostic systems and validate the superiority of AI systems.Systematic Review Registration:PROSPERO (https://www.crd.york.ac.uk/PROSPERO/), identifier CRD42022303990.

Endoscopic ultrasound‐based application for determining the management of subepithelial lesions: Do androids dream of endoscopic ultrasound?

“…In this validation study, the sensitivities and specificities of the five diagnostic models (GIST, leiomyoma, neuroendocrine neoplasm, ectopic pancreas, and lipoma) were 68.3-95.7% and 64.1-83.3%, respectively. As a meta-analysis of previous EUS image-based AI-assisted diagnostic studies showed sensitivities and specificities of 0.93 (95% confidence interval [CI] 0.93-0.97) and 0.88 (95% CI 0.71-0.96), respectively, 6 the diagnostic results of this study seemed to be somewhat inferior to those of previous studies. However, previous studies were mainly focused on the distinction between GIST and non-GIST, and the results of this study were considered satisfactory for evaluating the EUS findings alone.…”

“…Because of these diagnostic difficulties, studies are reporting the use of EUS image-based scoring systems or computer-aided diagnosis, such as artificial intelligence (AI)-aided diagnosis. 5,6 Several similar studies are expected to be conducted in the future.…”

“…Recently, unroofing biopsy techniques have been reported as an alternative to EUS‐FNA; 3 however, they are still not commonly used. Because of these diagnostic difficulties, studies are reporting the use of EUS image‐based scoring systems or computer‐aided diagnosis, such as artificial intelligence (AI)‐aided diagnosis 5,6 . Several similar studies are expected to be conducted in the future.…”

Artificial intelligence in interventional pulmonology

“…A recent meta-analysis of ten studies evaluated the diagnostic accuracy of artificial intelligence in detecting pancreatic cancer using EUS images [39 ▪▪ ], revealing high diagnostic sensitivity (92%) and specificity (90%). Another meta-analysis demonstrated superior performance of CNN models in diagnosing gastro-intestinal subepithelial lesions from EUS images compared to EUS experts without artificial intelligence aids (sensitivity, 93 vs. 71%; specificity 81 vs. 69%) [40].…”