Can technology increase adenoma detection rate?

Improving polyp detection at colonoscopy: Non-technological techniques

Colonoscopy and polypectomy remain the gold standard investigation for the detection and prevention of colorectal cancer. Halting the progression of colonic adenoma through adequate detection of pre-cancerous lesions interrupts the progression to carcinoma. The adenoma detection rate is a key performance indicator. Increasing adenoma detection rates are associated with reducing rates of interval colorectal cancer. Endoscopists with high baseline adenoma detection rate have a meticulous technique during colonoscopy withdrawal that improves their adenoma detection. This minireview article summarizes the evidence on the following simple operator techniques and their effects on the adenoma detection rate; minimum withdrawal times, dynamic patient position change and proximal colon retroflexion.

Adenoma detection rate using narrow-band imaging is inferior to high-definition white light colonoscopy in screening and surveillance colonoscopies in daily clinical care: A randomized controlled trial

BACKGROUND

Despite recent advances in endoscopic technology adenoma miss rate still is up to 20% contributing to interval cancers. Improved imaging modalities have been introduced to increase adenoma detection rate (ADR). Recently, narrow-band imaging (NBI) (Exera II series, Olympus Corporation) was not significantly better than high-definition white light colonoscopy (HD-WLC). An improved second generation of NBI (190-NBI) is characterized by better illumination of the bowel lumen and may be associated with a higher ADR.

METHODS

We performed a prospective randomized study on patients referred to the Jena University Hospital for screening or surveillance colonoscopy between January 2015 and April 2017. Participating endoscopists were divided into 2 subgroups depending on their individual experience. Colonoscopy was performed by use of HD-WLC or 190-NBI upon withdrawal.

RESULTS

Five hundred fifty-three patients participated in the study. Eighty patients were excluded (insufficient bowel cleansing [n = 34], anticoagulation precluding polypectomy [n=15], partial colonic resection [n=9], other reasons [n = 22]). Mean age was 66.9 years (standard deviation 10.3 years), and 253 patients were male (53.5%). Bowel preparation and withdrawal time were not different. ADR among all subgroups was 39.4% using HD-WLC, but only 29.1% were using 190-NBI (P = .02). Number of polyps per patient was lower using 190-NBI than with HD-WLC (0.58 vs 0.86; P = .02). Subgroup analysis revealed that 190-NBI was inferior to HD-WLC only in unexperienced endoscopists.

CONCLUSION

In our stud,y ADR was lower by use of 190-NBI. These differences persisted only in unexperienced investigators. 190-NBI seems to be more challenging regarding ADR, requiring more intensive training prior to implementing this technology in daily clinical care.

REGISTRATION

ClinicalTrials.gov (identifier: NCT03081975).

MiWEndo: Evaluation of a Microwave Colonoscopy Algorithm for Early Colorectal Cancer Detection in Ex Vivo Human Colon Models

This study assesses the efficacy of detecting colorectal cancer precursors or polyps in an ex vivo human colon model with a microwave colonoscopy algorithm. Nowadays, 22% of polyps go undetected with conventional colonoscopy, and the risk of cancer after a negative colonoscopy can be up to 7.9%. We developed a microwave colonoscopy device that consists of a cylindrical ring-shaped switchable microwave antenna array that can be attached to the tip of a conventional colonoscope as an accessory. The accessory is connected to an external unit that allows successive measurements of the colon and processes the measurements with a microwave imaging algorithm. An acoustic signal is generated when a polyp is detected. Fifteen ex vivo freshly excised human colons with cancer (n = 12) or polyps (n = 3) were examined with the microwave-assisted colonoscopy system simulating a real colonoscopy exploration. After the experiment, the dielectric properties of the specimens were measured with a coaxial probe and the samples underwent a pathology analysis. The results show that all the neoplasms were detected with a sensitivity of 100% and specificity of 87.4%.

Comparing endoscopic interventions to improve serrated adenoma detection rates during colonoscopy: a systematic review and network meta-analysis of randomized controlled trials

OBJECTIVE

Serrated lesions (sessile serrated adenomas/polyps and traditional serrated adenomas) owing to their subtle appearance and proximal location have a high miss rate. The objective of this study is to compare all the available endoscopic interventions for improving serrated adenoma detection rate (SADR) through a network meta-analysis.

METHODS

We conducted a systematic review of the available literature (PubMed, Embase, Cochrane and WoS) from inception to 29 November 2019 to identify all the relevant randomized controlled trials. A total of 28 trials with 22 830 patients were included. The studies compared the efficacy of add-on devices (endocap, endocuff, endocuff vision, G-EYE, endorings, AmplifEYE), electronic chromoendoscopy (linked-color imaging, blue laser imaging, narrow band imaging), dye-based chromoendoscopy, full-spectrum endoscopy (FUSE) and water-based techniques (WBT) with each other or high-definition colonoscopy. Both pairwise and network meta-analysis was conducted using the random-effects model. Risk ratios (RR) with 95% confidence intervals (CI) and P-values were calculated.

RESULTS

Direct meta-analysis demonstrated superiority for WBT (RR: 1.41, CI: 1.01-1.98), add-on devices (RR: 1.53, CI: 1.13-2.08), narrow band imaging (RR: 1.93, CI: 1.12-3.32) and endocuff vision (RR: 1.87, CI: 1.13-3.11) compared to high-definition colonoscopy. The results were consistent on network meta-analysis with chromoendoscopy as an additional modality for improving SADR (RR: 1.74, CI: 1.03-2.93).

CONCLUSION

In a network meta-analysis, add-on devices (particularly endocuff vision), narrow band imaging, WBT and chromoendoscopy were comparable to each other and improved SADR compared to high-definition colonoscopy.

Effectiveness of a Deep-learning Polyp Detection System in Prospectively Collected Colonoscopy Videos With Variable Bowel Preparation Quality

BACKGROUND

Colonoscopy is the gold standard for polyp detection, but polyps may be missed. Artificial intelligence (AI) technologies may assist in polyp detection. To date, most studies for polyp detection have validated algorithms in ideal endoscopic conditions.

AIM

To evaluate the performance of a deep-learning algorithm for polyp detection in a real-world setting of routine colonoscopy with variable bowel preparation quality.

METHODS

We performed a prospective, single-center study of 50 consecutive patients referred for colonoscopy. Procedural videos were analyzed by a validated deep-learning AI polyp detection software that labeled suspected polyps. Videos were then re-read by 5 experienced endoscopists to categorize all possible polyps identified by the endoscopist and/or AI, and to measure Boston Bowel Preparation Scale.

RESULTS

In total, 55 polyps were detected and removed by the endoscopist. The AI system identified 401 possible polyps. A total of 100 (24.9%) were categorized as "definite polyps;" 53/100 were identified and removed by the endoscopist. A total of 63 (15.6%) were categorized as "possible polyps" and were not removed by the endoscopist. In total, 238/401 were categorized as false positives. Two polyps identified by the endoscopist were missed by AI (false negatives). The sensitivity of AI for polyp detection was 98.8%, the positive predictive value was 40.6%. The polyp detection rate for the endoscopist was 62% versus 82% for the AI system. Mean segmental Boston Bowel Preparation Scale were similar (2.64, 2.59, P=0.47) for true and false positives, respectively.

CONCLUSIONS

A deep-learning algorithm can function effectively to detect polyps in a prospectively collected series of colonoscopies, even in the setting of variable preparation quality.

Water Exchange (WE) and Quality Improvement-Enhanced Advanced Adenoma Detection: A Pooled Data Analysis of 6 Randomized Controlled Trials

INTRODUCTION

Advanced adenomas (≥10 mm in diameter, >25% villous, or high-grade dysplasia), a marker of colorectal cancer risk, are used to stratify patients for closer surveillance. Modern accessories, endoscopes, and age-adjusted evaluation have variable impacts on the advanced adenoma detection rate (AADR). In 1 randomized controlled trial (RCT) comparing air insufflation (AI) with water exchange (WE), the right colon AADR was significantly increased by WE. Four network meta-analyses reported that WE significantly increased overall adenoma detection rate (ADR), but the impact on AADR was not addressed.

AIM

The aim of this study was to test the hypothesis that WE significantly increased AADR compared with AI.

METHOD

Six Clinicaltrial.gov-registered RCTs were reported by a group of WE investigators. Data including AADR (primary outcome) and overall ADR (secondary outcome) were pooled.

RESULTS

A total of 5407 patients were randomized to AI (2699) and WE (2708). Compared with AI, WE significantly increased AADR (5.7% vs. 8.3%, P=0.001) and overall ADR (20.9% vs. 27.4%, P=0.001).

CONCLUSIONS

In contrast to published reports, which showed variable impacts on AADR, WE was consistent in increasing AADR in 6 reported RCTs. The pooled data confirm that the impact of WE in increasing AADR was significant. The significantly enhanced overall ADR indicated that WE provided a higher quality outcome than AI. The significant improvement in AADR confirmed WE to be clinically relevant and has finally arrived as a timely addition to colorectal cancer prevention programs.

Diagnostic accuracy of i-scan image enhancement for real-time endoscopic diagnosis of small colorectal polyps: a meta-analysis

OBJECTIVE

i-Scan is a digital image enhancement technology, reported to improve diagnostic performance during endoscopy. Previous studies have investigated the accuracy of i-scan for distinguishing between neoplastic and non-neoplastic colonic polyps and suggested diagnostic accuracy close to that required for use in routine clinical practice. The aim of this study was to perform a meta-analysis of the available literature investigating diagnostic accuracy for i-scan optical diagnosis when made in real time for colorectal polyps <10 mm in size.

DATA SOURCES

The databases of Medline, Embase and the Cochrane Library were searched for relevant studies.

METHODS

A bivariate random effects model was used to produce pooled sensitivity and specificity values, and univariable meta-regression was applied for subgroup analysis.

RESULTS

The meta-analysis included 15 studies, and diagnosis of 2817 polyps. The area under the hierarchical summary receiver-operating characteristic curve was 0.96. The pooled sensitivity of i-scan optical diagnosis was 0.92 (95% confidence interval 0.85-0.95). The specificity was 0.90 (95% confidence interval 0.83-0.94).

CONCLUSIONS

This meta-analysis updates and summarizes the available evidence concerning the diagnostic performance of i-scan for small colorectal polyps. An acceptable degree of accuracy was found, showing potential to support a 'resect and discard' strategy for colonic polyps. There was not found to be a significant difference in diagnostic performance between different clinical settings (i.e. teaching hospitals or general hospitals).