How to Manage the Large Nonpedunculated Colorectal Polyp

Double-nylon purse-string suture technique: Another addition to the endoscopist's toolbox for full-thickness defect closure

Iatrogenic perforation is the most feared adverse event in endoscopy. With the expansion of interventional endoscopy in favor of traditional surgery, it is now more crucial than ever to develop effective defect closure techniques. This has culminated in the dissemination of multiple novel closure technologies, including through-the-scope clips, over-the-scope clips, through-the-scope suturing and over-the-scope suturing devices. In this editorial, we comment on the recent publication by Wang and colleagues discussing the performance of the double-nylon purse-string suture technique in the closure of large (> 3 cm) gastric full-thickness defects. This technique offers a promising, practical and cost-effective approach to closure of large full-thickness defects that can be readily implemented across diverse healthcare settings.

Precision endoscopy in colorectal polyps' characterization and planning of endoscopic therapy

Precision endoscopy in the management of colorectal polyps and early colorectal cancer has emerged as the standard of care. It includes optical characterization of polyps and estimation of submucosal invasion depth of large nonpedunculated colorectal polyps to select the appropriate endoscopic resection modality. Over time, several imaging modalities have been implemented in endoscopic practice to improve optical performance. Among these, image-enhanced endoscopy systems and magnification endoscopy represent now well-established tools. New advanced technologies, such as endocytoscopy and confocal laser endomicroscopy, have recently shown promising results in predicting the histology of colorectal polyps. In recent years, artificial intelligence has continued to enhance endoscopic performance in the characterization of colorectal polyps, overcoming the limitations of other imaging modes. In this review we retrace the path of precision endoscopy, analyzing the yield of various endoscopic imaging techniques in personalizing management of colorectal polyps and early colorectal cancer.

T1 colorectal cancer management in the era of minimally invasive endoscopic resection

T1 colorectal cancer (CRC), defined by tumor invasion confined to the submucosa, has historically been managed by surgery. Improved understanding of recurrence and lymph node metastases risk, coupled with advances in endoscopic resection techniques, have led to an increasing capacity for organ-sparing local excision. Minimally invasive management of T1 CRC begins with optical evaluation of the lesion to diagnose invasive disease and quantify depth of invasion, which informs therapeutic decision making. Modality selection between various available endoscopic resection techniques depends upon lesion characteristics, technique risk-benefit profiles, and location-specific implications. Following endoscopic resection, established histopathology features determine the risk of recurrence and subsequent management including surveillance or adjuvant surgical excision. The management of non-operative candidates deviates from conventional recommendations with emerging treatment strategies in select populations.

Endoscopic Management of Large Non-Pedunculated Colorectal Polyps

Large non-pedunculated colorectal polyps ≥20 mm (LNPCPs) comprise approximately 1% of all colorectal polyps. LNPCPs more commonly contain high-grade dysplasia, covert and overt cancer. These lesions can be resected using several means, including conventional endoscopic mucosal resection (EMR), cold-snare EMR (C-EMR) and endoscopic submucosal dissection (ESD). This review aimed to provide a comprehensive, critical and objective analysis of ER techniques. Evidence-based, selective resection algorithms should be used when choosing the most appropriate technique to ensure the safe and effective removal of LNPCPs. Due to its enhanced safety and comparable efficacy, there has been a paradigm shift towards cold-snare polypectomy (CSP) for the removal of small polyps (<10 mm). This technique is now being applied to the management of LNPCPs; however, further research is required to define the optimal LNPCP subtypes to target and the viable upper size limit. Adjuvant techniques, such as thermal ablation of the resection margin, significantly reduce recurrence risk. Bleeding risk can be mitigated using through-the-scope clips to close defects in the right colon. Endoscopic surveillance is important to detect recurrence and synchronous lesions. Recurrence can be readily managed using an endoscopic approach.

A Rectum-Specific Selective Resection Algorithm Optimizes Oncologic Outcomes for Large Nonpedunculated Rectal Polyps

BACKGROUND AND AIMS

Endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD) are complementary techniques for large (≥20 mm) nonpedunculated rectal polyps (LNPRPs). A mechanism for appropriate technique selection has not been described.

METHODS

We evaluated the performance of a selective resection algorithm (SRA) (August 2017 to April 2021) compared with a universal EMR algorithm (UEA) (July 2008 to July 2017) for LNPRPs within a prospective observational study. In the SRA, LNPRPs with features of superficial submucosal invasive cancer (SMIC) (<1000 μm; Kudo pit pattern Vi), or with an increased risk of SMIC (Paris 0-Is or 0-IIa+Is nongranular, 0-IIa+Is granular with a dominant nodule ≥10 mm) underwent ESD. The remaining LNPRPs underwent EMR. Algorithm performance was evaluated by SMIC identified after EMR, curative oncologic resection (R0 resection, superficial SMIC, absence of negative histologic features), technical success, adverse events, and recurrence at first surveillance colonoscopy.

RESULTS

A total of 480 LNPRPs were evaluated (290 UEA, 190 SRA). Median lesion size was 40 (interquartile range, 30-60) mm. SMIC was identified in 56 (11.7%) LNPRPs. Significant differences in SMIC after EMR (SRA 1 [1.0%] vs UEA 35 [12.1%]; P = .001) and curative oncologic resection (SRA n = 7 [33.3%] vs UEA n = 2 [5.7%]; P = .010) were identified. No significant differences in technical success or adverse events were identified (all P > .137). Among LNPRPs with SMIC amenable to curative oncologic resection and which underwent ESD, 100% (n = 7 of 7) were cured.

CONCLUSIONS

A rectum-specific SRA optimizes oncologic outcomes for LNPRPs and mitigates the risk of piecemeal resection of cancers.

Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm

In this study, we aimed to develop an artificial intelligence clinical decision support solution to mitigate operator-dependent limitations during complex endoscopic procedures such as endoscopic submucosal dissection and peroral endoscopic myotomy, for example, bleeding and perforation. A DeepLabv3-based model was trained to delineate vessels, tissue structures and instruments on endoscopic still images from such procedures. The mean cross-validated Intersection over Union and Dice Score were 63% and 76%, respectively. Applied to standardised video clips from third-space endoscopic procedures, the algorithm showed a mean vessel detection rate of 85% with a false-positive rate of 0.75/min. These performance statistics suggest a potential clinical benefit for procedure safety, time and also training.