Current Approaches in Managing Colonic Serrated Polyps and Serrated Polyposis

Artificial Intelligence-assisted colonoscopy and colorectal cancer screening: Where are we going?

Colorectal cancer is a significant global health concern, necessitating effective screening strategies to reduce its incidence and mortality rates. Colonoscopy plays a crucial role in the detection and removal of colorectal neoplastic precursors. However, there are limitations and variations in the performance of endoscopists, leading to missed lesions and suboptimal outcomes. The emergence of artificial intelligence (AI) in endoscopy offers promising opportunities to improve the quality and efficacy of screening colonoscopies. In particular, AI applications, including computer-aided detection (CADe) and computer-aided characterization (CADx), have demonstrated the potential to enhance adenoma detection and optical diagnosis accuracy. Additionally, AI-assisted quality control systems aim to standardize the endoscopic examination process. This narrative review provides an overview of AI principles and discusses the current knowledge on AI-assisted endoscopy in the context of screening colonoscopies. It highlights the significant role of AI in improving lesion detection, characterization, and quality assurance during colonoscopy. However, further well-designed studies are needed to validate the clinical impact and cost-effectiveness of AI-assisted colonoscopy before its widespread implementation.

Effect of an E-learning resource on endoscopists' proximal serrated polyp detection rate: a randomized controlled trial

BACKGROUND

Recent studies demonstrated that a higher proximal serrated polyp detection rate (PSPDR) among endoscopists is associated with a lower risk of post-colonoscopy colorectal cancer (PCCRC) incidence and death for their patients. Our objective was to evaluate the effect of an e-learning resource on PSPDR.

METHODS

We performed a multicenter randomized controlled trial within the Dutch fecal immunochemical test-based colorectal cancer screening program. Endoscopists were randomized using block randomization per center to either receive a 60-minute e-learning resource on serrated polyp detection or not. PSPDR was calculated based on all colonoscopies performed during a 27-month pre-intervention and a 17-month post-intervention period. The primary end point was difference in PSPDR between intervention and control arms (intention to treat) using mixed effect logistic regression modeling, with time (pre-intervention/post-intervention) and interaction between time and arm (intervention/control) as fixed effects, and endoscopists as random effects.

RESULTS

116 endoscopists (57 intervention, 59 controls) were included, and performed 27494 and 33888 colonoscopies, respectively. Median PSPDR pre-intervention was 13.6% (95%CI 13.0-14.1) in the intervention arm and 13.8% (95%CI 13.3-14.3) in controls. Post-intervention PSPDR was significantly higher over time in the intervention arm than in controls (17.1% vs. 15.4%, P=0.01).

CONCLUSION

In an era of increased awareness and increasing PSPDRs, endoscopists who undertook a one-time e-learning course significantly accelerated the increase in PSPDR compared with endoscopists who did not undertake the e-learning. Widespread implementation might reduce PCCRC incidence.

The histologic features, molecular features, detection and management of serrated polyps: a review

The serrated pathway to colorectal cancers (CRCs) is a significant pathway encompassing five distinct types of lesions, namely hyperplastic polyps (HPs), sessile serrated lesions (SSLs), sessile serrated lesions with dysplasia (SSL-Ds), traditional serrated adenomas (TSAs), and serrated adenoma unclassified. In contrast to the conventional adenoma-carcinoma pathway, the serrated pathway primarily involves two mechanisms: BRAF/KRAS mutations and CpG island methylator phenotype (CIMP). HPs are the most prevalent non-malignant lesions, while SSLs play a crucial role as precursors to CRCs, On the other hand, traditional serrated adenomas (TSAs) are the least frequently encountered subtype, also serving as precursors to CRCs. It is crucial to differentiate these lesions based on their unique morphological characteristics observed in histology and colonoscopy, as the identification and management of these serrated lesions significantly impact colorectal cancer screening programs. The management of these lesions necessitates the crucial steps of removing premalignant lesions and implementing regular surveillance. This article provides a comprehensive summary of the epidemiology, histologic features, molecular features, and detection methods for various serrated polyps, along with recommendations for their management and surveillance.

Association between lifestyle and dietary preference factors and conventional adenomas and serrated polyps

Introduction

Both conventional adenoma (AD) and serrated polyp (SP) were known precursor lesions of colorectal cancer (CRC). Modifiable lifestyle factors were significantly associated with CRC risk, but whether these factors were related to the risk of different precursors of CRC needed to be clarified. This study aimed to evaluate the risks of AD and SP caused by lifestyle factors and compare the risk differences between AD and SP.

Methods

The study population was from the CRC screening cohort in Hangzhou, China. A total of 458,457 eligible individuals volunteered to undergo initial screening including the fecal immunochemical test (FIT) and the CRC risk assessment. Finally, 13,993 participants who had undergone colonoscopy tests and had been diagnosed at designated hospitals were selected in this study. All participants were required to fill out a questionnaire during the initial screening for collecting their information. The generalized estimate equation (GEE) model was used to assess the association between lifestyle factors/dietary preferences and AD/SP.

Results

The body mass index (BMI) and smoking were positively associated with the risks of only SP (BMI: OR = 1.50, 95%CI: 1.23-1.84; smoking: OR = 1.29, 95%CI: 1.07-1.55), only AD (BMI: OR = 1.53, 95%CI: 1.28-1.82; OR = 1.24, 95%CI: 1.11-1.39), and synchronous SP and AD (BMI: OR = 1.97, 95%CI: 1.40-2.75; smoking: OR = 1.53, 95%CI: 1.27-1.85). In the case-group comparison, smoking was more strongly associated with the risk of synchronous SP and AD than only AD. Alcohol drinking was positively associated with the risk of AD (OR = 1.28, 95%CI: 1.14-1.44), but no statistically significant difference was observed in risks in the case-group comparison. Furthermore, whole-grain intake was associated with a decreased risk of only AD (OR = 0.78, 95%CI: 0.65-0.93). However, white meat intake was positively associated with risks of only SP when compared with AD cases (OR = 1.60, 95%CI: 1.15-2.23).

Conclusion

The current study identified common risk factors such as BMI and smoking as well as different risks of certain factors (e.g., alcohol drinking and whole-grain intake) for SP and AD. However, there were still some factors, especially diet-related factors, that have not been fully elucidated in their association with the two lesions. Further research is needed in future to confirm and develop prevention strategies for different lesions.

Polyps and Colorectal Cancer in Serrated Polyposis Syndrome: Contribution of the Classical Adenoma-Carcinoma and Serrated Neoplasia Pathways

INTRODUCTION

Patients with serrated polyposis syndrome (SPS) have an increased risk to develop colorectal cancer (CRC). Due to an abundance of serrated polyps, these CRCs are assumed to arise mainly through the serrated neoplasia pathway rather than through the classical adenoma-carcinoma pathway. We aimed to evaluate the pathogenetic routes of CRCs in patients with SPS.

METHODS

We collected endoscopy and pathology data on CRCs and polyps of patients with SPS under treatment in our center. Our primary end point was the proportion of BRAFV600E mutated CRCs, indicating serrated pathway CRCs (sCRCs). CRCs lacking BRAFV600E most likely inferred a classical adenoma-carcinoma origin (aCRCs). We assessed patient, polyp, and CRC characteristics and stratified for BRAFV600E mutation status.

RESULTS

Thirty-five patients with SPS harbored a total of 43 CRCs. Twenty-one CRCs (48.8%) carried a BRAFV600E mutation, 10 of which lacked MLH1 staining and 17 (81%) were located in the proximal colon. Twenty-two CRCs (51.1%) did not carry a BRAFV600E mutation and were MLH1 proficient. Of these 22 putatively aCRCs, 17 (77.3%) were located distally and one-third (36.4%) harbored a pathogenic KRAS or NRAS mutation. In patients with BRAFwt -CRCs, a higher ratio of the median number of conventional adenomas versus serrated polyps was found (4 vs 13) than patients with BRAFV600E -CRCs (1 vs 14).

DISCUSSION

Our study indicates that in patients with SPS, the ratio of sCRCs:aCRCs on average is 50:50. This elevated sCRC:aCRC ratio in patients with SPS, when compared with non-SPS patients, correlates well with the differences in the ratios of the numbers of sessile serrated lesions and conventional adenomas in patients with SPS and non-SPS patients, respectively.

Colorectal cancer risk after removal of polyps in fecal immunochemical test based screening

Background

Colonoscopy surveillance intervals are based on the predicted risk of metachronous colorectal cancer (CRC) after polyp removal. However, risk estimation per polyp subtype is difficult due to the fact that many patients have multiple polyps. To enable risk estimation per polyp subtypes we examined the metachronous CRC risk of subgroups based on presence or absence of co-occurring findings.

Methods

Using high-quality screening colonoscopies performed after a positive fecal immunochemical test between 2014 and 2020 within the Dutch CRC screening program, we applied Cox regression analysis to evaluate the association between findings at baseline colonoscopy and metachronous CRCs. For our primary outcome, we appointed each patient to unique subgroups based on removed polyp subtypes that were present or absent at baseline colonoscopy and used the groups without polyps as reference. High-risk subgroups were individuals with high-risk serrated polyps, defined as serrated polyp ≥10 mm, sessile serrated lesions with dysplasia, or traditional serrated adenomas, as well as high-risk adenomas, defined as adenoma ≥10 mm or containing high-grade dysplasia.

Findings

In total 253,833 colonoscopies were included. Over a median follow-up of 36 months (IQR, 21-57), we identified 504 metachronous CRCs. Hazard ratios for metachronous CRC was 1.70 (95% CI, 1.07-2.69) for individuals with high-risk serrated polyps without high-risk adenomas, 1.22 (0.96-1.55) for individuals with high-risk adenomas without high-risk serrated polyps, and 2.00 (1.19-3.39) for individuals with high-risk serrated polyps and high-risk adenomas, compared to patients without polyps.

Interpretation

Accounting for co-occurring findings, we observed an increased metachronous CRC risk for individuals that had high-risk serrated polyps with the presence of high-risk adenomas, or individuals with high-risk serrated polyps without high-risk adenomas. These findings could provide more evidence to support post-polypectomy surveillance guidelines.

Funding

None.

Artificial Intelligence-Aided Endoscopy and Colorectal Cancer Screening

Colorectal cancer (CRC) is the third most common cancer worldwide, with the highest incidence reported in high-income countries. However, because of the slow progression of neoplastic precursors, along with the opportunity for their endoscopic detection and resection, a well-designed endoscopic screening program is expected to strongly decrease colorectal cancer incidence and mortality. In this regard, quality of colonoscopy has been clearly related with the risk of post-colonoscopy colorectal cancer. Recently, the development of artificial intelligence (AI) applications in the medical field has been growing in interest. Through machine learning processes, and, more recently, deep learning, if a very high numbers of learning samples are available, AI systems may automatically extract specific features from endoscopic images/videos without human intervention, helping the endoscopists in different aspects of their daily practice. The aim of this review is to summarize the current knowledge on AI-aided endoscopy, and to outline its potential role in colorectal cancer prevention.

Melanosis coli: a contrast effect or an oncogenic effect? A large-scale retrospective cohort study

BACKGROUND

Melanosis coli is characterized by brown mucosa with pigmentation. Studies have showed an increased adenoma detection rate in melanosis patients, whether it is caused by a contrast effect or an oncogenic effect is still controversial. The detection of serrated polys in melanosis patients remains unknown.

AIMS

The study aimed to clarify the correlation of adenoma detection rate with melanosis coli and discuss outcomes in less-experienced endoscopists. Serrated polyp detection rate was also been investigated.

METHODS

A total of 2150 patients and 39,630 controls were enrolled. A propensity score matching method was used to balance covariates between the two groups. The detection of polyps, adenomas, serrated polyps, and their features was analyzed.

RESULTS

The polyp detection rate (44.65% vs 41.01%, P = 0.005) and adenoma detection rate (30.34% vs 23.92%, P < 0.001) were significantly higher, and the serrated polyp detection rate (0.93% vs 1.58%, P = 0.033) was significantly lower in melanosis coli. The percentage of low-risk adenomas (44.60% vs 39.16%, P < 0.001) and polyps with 6 to 10 mm in size (20.16% vs 16.21%, P < 0.001) were higher in melanosis coli. The detection of large serrated polyps was lower (0.11% vs 0.41%, P = 0.026) in melanosis coli.

CONCLUSION

Melanosis coli correlates with an increased adenoma detection rate. The detection of large serrated polyps was lower in melanosis patients. Melanosis coli may not be considered a precancerous lesion.

Advanced serrated polyps as a target of screening: detection rate and positive predictive value within a fecal immunochemical test-based colorectal cancer screening population

BACKGROUND : Advanced serrated polyps (ASPs) have a comparable risk to advanced adenomas for progression to colorectal cancer (CRC). The yield of most CRC screening programs, however, is based on advanced adenomas and CRC only. We assessed the ASP detection rate, and positive predictive value (PPV) including ASPs in a fecal immunochemical test (FIT)-based screening program. METHODS : We analyzed the findings of follow-up colonoscopies of FIT-positive screenees in the Dutch CRC screening program from 2014 until 2020. Data were retrieved from the national screening and pathology database. An ASP was defined as any serrated polyp of ≥ 10 mm, sessile serrated lesion with dysplasia, or traditional serrated adenoma. The ASP detection rate was defined as the proportion of colonoscopies with ≥ 1 ASP. PPV was originally defined as the proportion of individuals with a CRC or advanced adenoma. The updated PPV definition included CRCs, advanced adenomas, and/or ASPs. RESULTS : 322 882 colonoscopies were included in the analyses. The overall detection rate of ASPs was 5.9 %. ASPs were detected more often in women than men (6.3 % vs. 5.6 %; P < 0.001). ASP detection rates in individuals aged 55-59, 60-64, 65-69, and 70 + were 5.2 %, 6.1 %, 6.1 %, and 5.9 %, respectively (P < 0.001). The PPV for CRCs and advanced adenomas was 41.1 % and increased to 43.8 % when including ASPs. The PPV increase was larger in women than in men (3.2 vs. 2.4 percentage points). CONCLUSIONS : 5.9 % of FIT-positive screenees had ASPs, but half of these were detected in combination with a CRC or advanced adenoma. Therefore, including ASPs results in a small increase in the yield of FIT-based screening.