Computer-Aided Diagnosis of Diminutive Colorectal Polyps in Endoscopic Images: Systematic Review and Meta-analysis of Diagnostic Test Accuracy

Abstract

Background Most colorectal polyps are diminutive and benign, especially those in the rectosigmoid colon, and the resection of these polyps is not cost-effective. Advancements in image-enhanced endoscopy have improved the optical prediction of colorectal polyp histology. However, subjective interpretability and inter- and intraobserver variability prohibits widespread implementation. The number of studies on computer-aided diagnosis (CAD) is increasing; however, their small sample sizes limit statistical significance. Objective This review aims to evaluate the diagnostic test accuracy of CAD models in predicting the histology of diminutive colorectal polyps by using endoscopic images. Methods Core databases were searched for studies that were based on endoscopic imaging, used CAD models for the histologic diagnosis of diminutive colorectal polyps, and presented data on diagnostic performance. A systematic review and diagnostic test accuracy meta-analysis were performed. Results Overall, 13 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of diminutive colorectal polyps (adenomatous or neoplastic vs nonadenomatous or nonneoplastic) were 0.96 (95% CI 0.93-0.97), 0.93 (95% CI 0.91-0.95), 0.87 (95% CI 0.76-0.93), and 87 (95% CI 38-201), respectively. The meta-regression analysis showed no heterogeneity, and no publication bias was detected. Subgroup analyses showed robust results. The negative predictive value of CAD models for the diagnosis of adenomatous polyps in the rectosigmoid colon was 0.96 (95% CI 0.95-0.97), and this value exceeded the threshold of the diagnosis and leave strategy. Conclusions CAD models show potential for the optical histological diagnosis of diminutive colorectal polyps via the use of endoscopic images. Trial Registration PROSPERO CRD42021232189; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=232189

Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis

“…Modeling is an assumption that observations follow certain statistical rules, and external validation is a method to check whether this assumption is correct or generalizable. Therefore, the confirmation of performance in the established CAD models with unused data in the training or internal testing process is essential [53]. However, no single study conducted performance verification in an external validation setting.…”

Impact of 3-second rule for high confidence assignment on the performance of endoscopists for the real-time optical diagnosis of colorectal polyps

“…Recently, artificial intelligence has been introduced to the field of colonoscopy to address the suboptimal performance of human-based optical diagnosis. Several studies have suggested that computer-aided diagnosis (CADx) can help increase the high confidence rate and accuracy regardless of the endoscopist's prior knowledge [3,17]. However, according to ex vivo studies, CADx faces the same challenge of poor translation to real-time optical diagnosis.…”

“…Use of the 3second rule resulted in significant improvement especially among nonexpert endoscopists. Many studies have achieved exceptional performances in ex vivo optical diagnosis with CADx, but translation into real-time optical diagnosis has been challenging [17]. Implementing a 3-second rule in real-time optical diagnosis would be useful for nonexpert endoscopists to help differentiate between high confidence and low confidence decisions in optical diagnosis.…”

Artificial intelligence within the small bowel: are we lagging behind?

“…For example, the use of artificial intelligence in endoscopic assessment of inflammatory bowel disease will minimize the need to obtain colonic biopsies and subsequent pathological assessment [61]. It will also help to identify diminutive nonneoplastic polyps that would otherwise be removed and require pathological assessment [62,63]. In a recent study, artificial intelligence was estimated to reduce the average colonoscopy cost and the gross annual reimbursement for colonoscopies by up to 18.9% and US$149.2 million, respectively, in different countries [64].…”