Optimal withdrawal and examination in colonoscopy

Challenges Facing the Detection of Colonic Polyps: What Can Deep Learning Do?

Colorectal cancer (CRC) is one of the most common causes of cancer mortality in the world. The incidence is related to increases with age and western dietary habits. Early detection through screening by colonoscopy has been proven to effectively reduce disease-related mortality. Currently, it is generally accepted that most colorectal cancers originate from adenomas. This is known as the "adenoma-carcinoma sequence", and several studies have shown that early detection and removal of adenomas can effectively prevent the development of colorectal cancer. The other two pathways for CRC development are the Lynch syndrome pathway and the sessile serrated pathway. The adenoma detection rate is an established indicator of a colonoscopy's quality. A 1% increase in the adenoma detection rate has been associated with a 3% decrease in interval CRC incidence. However, several factors may affect the adenoma detection rate during a colonoscopy, and techniques to address these factors have been thoroughly discussed in the literature. Interestingly, despite the use of these techniques in colonoscopy training programs and the introduction of quality measures in colonoscopy, the adenoma detection rate varies widely. Considering these limitations, initiatives that use deep learning, particularly convolutional neural networks (CNNs), to detect cancerous lesions and colonic polyps have been introduced. The CNN architecture seems to offer several advantages in this field, including polyp classification, detection, and segmentation, polyp tracking, and an increase in the rate of accurate diagnosis. Given the challenges in the detection of colon cancer affecting the ascending (proximal) colon, which is more common in women aged over 65 years old and is responsible for the higher mortality of these patients, one of the questions that remains to be answered is whether CNNs can help to maximize the CRC detection rate in proximal versus distal colon in relation to a gender distribution. This review discusses the current challenges facing CRC screening and training programs, quality measures in colonoscopy, and the role of CNNs in increasing the detection rate of colonic polyps and early cancerous lesions.

Impact of feedback and monitoring on colonoscopy withdrawal times and polyp detection rates

Background

Previous studies have shown colonoscopy withdrawal time (WT) to be a reliable surrogate indicator for polyp detection rate (PDR) and adenoma detection rate (ADR) in colonoscopy. Our aim was to assess the impact of feedback and monitoring of WT on PDR in routine colonoscopies with long-term follow-up.

Materials and methods

A total of 307 colonoscopies were performed in three separate clinical scenarios. First, PDR and WT were recorded without the staff being aware of the specific objective of the study. Before the second scenario, the staff was given interventional information and feedback on WTs and PDRs from the first scenario and was encouraged to aim for a minimum WT of 8 min. Retention of knowledge gained was reassessed in the third scenario 1 year later.

Results

The PDR in the first two scenarios differed significantly (p<0.01), with a more than 90% increase in PDR after intervention from 22% to 42% (95% CI 1.44 to 4.95), although the mean WT did not change (6.8 vs 7.2 min; p>0.05). The increase in PDR between the first and second scenarios was retained in the third follow-up scenario 1 year later where the WT of both polyp-positive and polyp-negative colonoscopies was found to be longer.

Conclusions

PDR almost doubled from the first to the second scenario of a real-life colonoscopy setting, indicating that awareness of WT is crucial. The knowledge gained from this intervention in routine practice was even retained after a year.

Technical interventions to increase adenoma detection rate in colonoscopy

Adenoma detection rate (ADR) is the most robust colonoscopy quality metric and clinical studies have adopted it as the ideal method to assess the impact of technical interventions. Areas covered: We reviewed papers focusing on the impact of colonoscopy technical issues on ADR, including withdrawal time and technique, second evaluation of the right colon, patient positional changes, gastrointestinal assistant participation during colonoscopy, water-aided technique, optimization of bowel preparation and antispasmodic administration. Expert commentary: Overall, technical interventions are inexpensive, available worldwide and easy to implement. Some of them, such as the adoption of split dose regimen and slow scope withdrawal to allow a careful inspection, have been demonstrated to significantly improve ADR. Emerging data support the use of water-exchange colonoscopy. According to published studies, other technical interventions seem to provide only marginal benefit to ADR. Unfortunately, the available evidence has methodological limitations, such as small sample sizes, the inclusion of expert endoscopists only and the evaluation of single technical interventions. Additionally, larger studies are needed to clarify whether these interventions might have a higher benefit on low adenoma detectors and whether the implementation of a bundle of them, instead of a single technical maneuver, might have a greater impact on ADR.

Management of Malignant Adenomas

Most polyps that originate in the colon and rectum are benign. A small subset of polyps will contain a malignancy. Although most malignant adenomas are managed with colonic resection a number can be approached with endoscopic, minimally invasive, and observational techniques. This article reviews the histologic characteristics and adverse risk factors that would portend a poor oncologic outcome and therefore suggest formal colonic resection. Modern endoscopic techniques such as endoscopic mucosal resection and endoscopic submucosal resection are discussed.

Computer vision and augmented reality in gastrointestinal endoscopy

Augmented reality (AR) is an environment-enhancing technology, widely applied in the computer sciences, which has only recently begun to permeate the medical field. Gastrointestinal endoscopy—which relies on the integration of high-definition video data with pathologic correlates—requires endoscopists to assimilate and process a tremendous amount of data in real time. We believe that AR is well positioned to provide computer-guided assistance with a wide variety of endoscopic applications, beginning with polyp detection. In this article, we review the principles of AR, describe its potential integration into an endoscopy set-up, and envisage a series of novel uses. With close collaboration between physicians and computer scientists, AR promises to contribute significant improvements to the field of endoscopy.

Colonoscopy in Colorectal Cancer Screening: Current Aspects

Colonoscopy represents a very important diagnostic modality for screening for colorectal cancer, because it has the ability to both detect and effectively remove pro-malignant and malignant lesions. It is recommended by almost all international and national gastroenterology and cancer societies, as an initial screening modality or, following a positive fecal occult blood test, to be performed every 10 years in individuals of average risk starting from the age of 50. However, a significant problem is the so-called post-screening (interval) polyps and cancers found some years after the index colonoscopy. In order to reduce the rate of interval cancers it is extremely necessary to optimize the quality and effectiveness of colonoscopy. Bowel preparation is of paramount importance for both accurate diagnosis and subsequent treatment of lesions found on colonoscopy. The quality of bowel preparation could be significantly improved by splitting the dose regimens, a strategy that has been shown to be superior to single-dose regimen. A good endoscopic technique and optimal withdrawal time offering adequate time for inspection, would further optimize the rate of cecal intubation and the number of lesions detected. During the last years, sophisticated devices have been introduced that would further facilitate cecal intubation. The percentage of total colonoscopies is now super-passing the level of 95 % allowing the adenoma detection rate to be greater than the suggestive level of 25 % in men and 15 % in women. This review aims to provide the reader with the current knowledge concerning indications, usefulness, limitations and future perspectives of this probably most important screening technique for colorectal cancer available today.

Colonoscopy quality assessment

Colonoscopy is the cornerstone of colorectal cancer screening programs. There is significant variability in the quality of colonoscopy between endoscopists. Colonoscopy quality assessment tracks various metrics to improve the effectiveness of colonoscopy, aiming at reducing the incidence and mortality from colorectal cancer. Adenoma detection rate is the prime metric, because it is associated with the risk of interval cancer. Implementing processes to measure and improve the adenoma detection rate is essential to improve the quality of colonoscopy.

Dual optical modality endoscopic imaging of cancer development in the mouse colon

BACKGROUND AND OBJECTIVE

We utilize a miniature, dual-modality endoscope that combines fluorescence-based surface magnifying chromoendoscopy (SMC) and optical coherence tomography (OCT) to follow the anatomical changes that occur during adenoma development in the mouse colon.

MATERIALS AND METHODS

Twenty-five mice were treated with the carcinogen azoxymethane (AOM) to induce tumor development in the distal colon, or were treated with saline as control, and were imaged over six months. OCT detects adenoma number with high sensitivity and specificity and can measure lesion size. In methylene blue-lavaged colons, SMC detects changes in the colonic crypts. SMC images of control mouse colons exhibit reticulated patterns of crypts of equal size, forming either a dot or honeycomb pattern.

RESULTS

Images of AOM-treated colons show mild crypt irregularities even in grossly normal tissue. Images of small to medium adenoma exhibit larger crypts, more intense signal, and irregular spacing whereas those of large adenoma have heterogeneous, intense signal and loss of crypt structure.

CONCLUSIONS

The combination of OCT and SMC permits the detection of neoplastic events from the earliest stages of crypt irregularities before gross tissue changes are noted, through to measuring the growth of protruding adenoma.

Higher adenoma detection rates with endocuff-assisted colonoscopy - a randomized controlled multicenter trial

Objectives

The Endocuff is a device mounted on the tip of the colonoscope to help flatten the colonic folds during withdrawal. This study aimed to compare the adenoma detection rates between Endocuff-assisted (EC) colonoscopy and standard colonoscopy (SC).

Methods

This randomized prospective multicenter trial was conducted at four academic endoscopy units in Germany. Participants: 500 patients (235 males, median age 64[IQR 54–73]) for colon adenoma detection purposes were included in the study. All patients were either allocated to EC or SC. The primary outcome measure was the determination of the adenoma detection rates (ADR).

Results

The ADR significantly increased with the use of the Endocuff compared to standard colonoscopy (35.4%[95% confidence interval{CI} 29–41%] vs. 20.7%[95%CI 15–26%], p<0.0001). Significantly more sessile polyps were detected by EC. Overall procedure time and withdrawal time did not differ. Caecal and ileum intubation rates were similar. No major adverse events occurred in both groups. In multivariate analysis, age (odds ratio [OR] 1.03; 95%[CI] 1.01–1.05), male sex (OR 1.74; 95%CI 1.10–2.73), withdrawal time (OR 1.16; 95%CI 1.05–1.30), procedure time (OR 1.07; 95%CI 1.04–1.10), colon cleanliness (OR 0.60; 95%CI 0.39–0.94) and use of Endocuff (OR 2.09; 95%CI 1.34–3.27) were independent predictors of adenoma detection rates.

Conclusions

EC increases the adenoma detection rate by 14.7%(95%CI 6.9–22.5%). EC is safe, effective, easy to handle and might reduce colorectal interval carcinomas.

Trial Registration

ClinicalTrials.gov NCT02034929.