Adenoma and polyp detection rates during insertion versus withdrawal phase of colonoscopy: a systematic review and meta-analysis of randomized controlled trials

Optimizing adenoma detection in screening-related colonoscopy

INTRODUCTION

Screening-related colonoscopy is a vital component of screening initiatives to both diagnose and prevent colorectal cancer (CRC), with prevention being reliant upon early and accurate detection of pre-malignant lesions. Several strategies, techniques, and interventions exist to optimize endoscopists' adenoma detection rates (ADR).

AREAS COVERED

This narrative review provides an overview of the importance of ADR and other colonoscopy quality indicators. It then summarizes the available evidence regarding the effectiveness of the following domains in terms of improving ADR: endoscopist factors, pre-procedural parameters, peri-procedural parameters, intra-procedural strategies and techniques, antispasmodics, distal attachment devices, enhanced colonoscopy technologies, enhanced optics, and artificial intelligence. These summaries are based on an electronic search of the databases Embase, Pubmed, and Cochrane performed on December 12, 2022.

EXPERT OPINION

Given the prevalence and associated morbidity and mortality of CRC, the quality of screening-related colonoscopy quality is appropriately prioritized by patients, endoscopists, units, and payers alike. Endoscopists performing colonoscopy should be up to date regarding available strategies, techniques, and interventions to optimize their performance.

Progress in understanding of factors related to colonoscopic adenoma detection rate

Adenoma detection rate (ADR) is the proportion of average-risk patients undergoing screening colonoscopy in whom an adenoma is found, and it is an important quality indicator of colonoscopy. ADR is closely related to the risk of interval colorectal cancer. A deeply study of ADR is essential for endoscopists. In this paper, we review the progress in the understanding of factors related to ADR before, during, and after colonoscopy, as well as several issues worthy of attention.

Automatic colonic polyp detection using integration of modified deep residual convolutional neural network and ensemble learning approaches

BACKGROUND AND OBJECTIVE

The increased incidence of colorectal cancer (CRC) and its mortality rate have attracted interest in the use of artificial intelligence (AI) based computer-aided diagnosis (CAD) tools to detect polyps at an early stage. Although these CAD tools have thus far achieved a good accuracy level to detect polyps, they still have room to improve further (e.g. sensitivity). Therefore, a new CAD tool is developed in this study to detect colonic polyps accurately.

METHODS

In this paper, we propose a novel approach to distinguish colonic polyps by integrating several techniques, including a modified deep residual network, principal component analysis and AdaBoost ensemble learning. A powerful deep residual network architecture, ResNet-50, was investigated to reduce the computational time by altering its architecture. To keep the interference to a minimum, median filter, image thresholding, contrast enhancement, and normalisation techniques were exploited on the endoscopic images to train the classification model. Three publicly available datasets, i.e., Kvasir, ETIS-LaribPolypDB, and CVC-ClinicDB, were merged to train the model, which included images with and without polyps.

RESULTS

The proposed approach trained with a combination of three datasets achieved Matthews Correlation Coefficient (MCC) of 0.9819 with accuracy, sensitivity, precision, and specificity of 99.10%, 98.82%, 99.37%, and 99.38%, respectively.

CONCLUSIONS

These results show that our method could repeatedly classify endoscopic images automatically and could be used to effectively develop computer-aided diagnostic tools for early CRC detection.