OBJECTIVE: There is growing evidence for the role of cold piecemeal endoscopic mucosal resection (C-EMR) in the treatment of colorectal lesions ≥10mm. However, it is unclear if it is equally efficacious for all histologic subtypes and sizes. This retrospective study compares the efficacy and safety of C-EMR in the resection of medium (10-19mm) and large (≥20mm) serrated and adenomatous lesions.
METHODS: A retrospective analysis was performed of Paris IIa colonic lesions resected utilising a C-EMR technique over a 3.5 year period at our center.
RESULTS: C-EMR was performed for 242 lesions in 151 patients. Lesion size ranged between 10mm to 50mm, with median size of 20mm. Ninety-five polyps were adenomatous, with 147 sessile serrated lesions (SSLs). At six month surveillance colonoscopy, the combined recurrence rate was 6.2%. Adenomas ≥20mm demonstrated a higher rate of recurrence (16.1%) compared to large SSLs (4.1%), medium adenomas (3.0%), and medium SSLs (1.4%). There were no adverse events reported following C-EMR.
CONCLUSIONS: C-EMR seems to be less effective for the resection of large adenomas when compared to medium adenomas or large SSLs. C-EMR is equally safe for all lesion size and histology.

Objective: This investigation sought to delineate the associations among colorectal adenomatous polyps, diabetes, and biomolecules involved in glucose metabolism. Method: Data were collected from 40 patients who underwent endoscopic polypectomy at the Endoscopy Department of Shandong Cancer Hospital between June 2019 and September 2021. This cohort included 27 patients with inflammatory polyps and 13 with adenomatous polyps. We assessed fasting insulin (Fins), fasting blood glucose (FBG), and the mRNA expressions of fibroblast growth factor 19 (FGF-19) and insulin-like growth factor 1 (IGF-1) in the polyp tissues. Both univariate and multivariate logistic regression analyses were employed to ascertain the determinants influencing the emergence of adenomatous polyps. From these analyses, a predictive nomogram was constructed to forecast the occurrence of adenomatous polyps, and evaluations on the discriminative capacity, calibration, and clinical utility of the model were conducted. Results: The adenomatous polyp group exhibited markedly elevated levels of glucose, insulin, FGF-19, and IGF-1, with respective concentrations of (8.67±2.70) mmol/L, (12.72±7.69) μU/L, 2.20±1.88, and 1.36±0.69. These figures were significantly higher compared to the inflammatory polyp group, which showed levels of (5.51±0.72) mmol/L, (5.49±2.68) μU/L, 0.53±0.97, and 0.41±0.46, respectively, P=0.001. Multivariate logistic regression revealed that the relative expression of IGF-1 served as an independent risk factor for the development of colorectal adenomatous polyps (OR=5.622, 95% CI:1.085-29.126). The nomogram displayed a C-index of 0.849, indicating substantial discriminative capability. The calibration curve affirmed the model\'s accuracy in aligning predicted probabilities with actual outcomes, and the clinical decision curve demonstrated thepractical clinical applicability of the model. Conclusions: There was a significant correlation between the occurrence of colorectal adenomatous polyps and glucose metabolic pathways. Individuals with diabetes showed a higher propensity to develop such polyps.
目的： 探讨结直肠腺瘤性息肉与糖尿病及糖代谢相关分子的关系。 方法： 收集2019年6月到2021年9月山东省肿瘤医院内镜科进行内镜下息肉切除术的40例患者，其中炎症性息肉27例，腺瘤性息肉13例。测量这些患者的空腹胰岛素、空腹血糖以及息肉组织中成纤维细胞生长因子19（FGF-19）和胰岛素样生长因子1（IGF-1）mRNA的表达。采用单因素和多因素logistic回归分析明确腺瘤性息肉发生的影响因素，基于多因素logistic回归分析结果构建预测腺瘤性息肉发生的列线图模型，并对模型进行区分度、校准度和临床适用性评价。 结果： 腺瘤性息肉组患者的血糖、胰岛素、FGF-19和IGF-1的相对表达量分别为（8.67±2.70）mmol/L、（12.72±7.69）μU/L、2.20±1.88和1.36±0.69，均高于炎症性息肉组［分别为（5.51±0.72）mmol/L、（5.49±2.68）μU/L、0.53±0.97和0.41±0.46，均P=0.001］。多因素logistic回归分析显示，IGF-1的相对表达量为结直肠腺瘤性息肉发生的独立危险因素（OR=5.622，95% CI：1.085～29.126）。根据多因素logistic回归分析结果成功构建腺瘤性息肉的预测列线图模型。列线图模型的C指数为0.849，表明列线图模型的区分度较好。校准曲线显示，列线图模型的预测概率与实际观测结果的一致性尚可。临床决策曲线显示，列线图模型有一定的临床适用性。 结论： 结直肠腺瘤性息肉的发生与糖代谢有关，糖尿病患者容易发生结直肠腺瘤。.

BACKGROUND: This study aimed to compare oral sulfate solution (OSS) with polyethylene glycol (PEG) for bowel preparation before colonoscopy.
METHODS: A literature search was performed on PubMed, Ovid, and Cochrane Databases for randomized clinical trials (RCT) comparing OSS with PEG for bowel preparation before colonoscopy. The last search was performed on 22 August 2023. The primary outcome was the quality of bowel preparation. The outcomes were compared by meta-analysis and trial sequential analysis (TSA).
RESULTS: A total of 14 RCTs with 4526 patients were included. OSS was comparable with PEG regarding adequate bowel preparation [P = 0.16, odds ratio (OR) = 1.19, 95% confidence interval (CI) [0.93, 1.51], I2 = 0%]. However, OSS showed obvious priority in excellent bowel preparation (P < 0.001, OR = 1.62, 95% CI [1.27, 2.05], I2 = 0%) and total Boston bowel preparation scale (BBPS) [P = 0.02, weighted mean difference (WMD) = 0.27, 95% CI [0.05, 0.50], I2 = 84%]. Additionally, the detection rate of polyps (P = 0.001, OR = 1.44, 95% CI [1.15, 1.80], I2 = 0%) and adenoma (P = 0.007, OR = 1.22, 95% CI [1.06, 1.42], I2 = 0%) was significantly higher in the OSS group. The two groups showed comparable incidence of adverse events except for a higher incidence of dizziness (P = 0.02, OR = 1.74, 95% CI [1.08, 2.83], I2 = 11%) was indicated in the OSS group. Moreover, OSS was associated with a higher satisfaction score (P = 0.02, WMD = 0.62, 95% CI [0.09, 1.15], I2 = 70%). In the TSA, the cumulative Z-curve crossed both the conventional boundary and trial sequential monitoring boundary and the required information size has been reached for excellent bowel preparation and total BBPS.
CONCLUSIONS: The current data demonstrated that OSS was associated with better quality of bowel preparation. More clinical trials are still needed to confirm other outcomes.

BACKGROUND: Construct deep learning models for colonoscopy quality control using different architectures and explore their decision-making mechanisms.
METHODS: A total of 4,189 colonoscopy images were collected from two medical centers, covering different levels of bowel cleanliness, the presence of polyps, and the cecum. Using these data, eight pre-trained models based on CNN and Transformer architectures underwent transfer learning and fine-tuning. The models\' performance was evaluated using metrics such as AUC, Precision, and F1 score. Perceptual hash functions were employed to detect image changes, enabling real-time monitoring of colonoscopy withdrawal speed. Model interpretability was analyzed using techniques such as Grad-CAM and SHAP. Finally, the best-performing model was converted to ONNX format and deployed on device terminals.
RESULTS: The EfficientNetB2 model outperformed other architectures on the validation set, achieving an accuracy of 0.992. It surpassed models based on other CNN and Transformer architectures. The model\'s precision, recall, and F1 score were 0.991, 0.989, and 0.990, respectively. On the test set, the EfficientNetB2 model achieved an average AUC of 0.996, with a precision of 0.948 and a recall of 0.952. Interpretability analysis showed the specific image regions the model used for decision-making. The model was converted to ONNX format and deployed on device terminals, achieving an average inference speed of over 60 frames per second.
CONCLUSIONS: The AI-assisted quality system, based on the EfficientNetB2 model, integrates four key quality control indicators for colonoscopy. This integration enables medical institutions to comprehensively manage and enhance these indicators using a single model, showcasing promising potential for clinical applications.

Quality indicators during the insertion phase of colonoscopy require exploration. Unsatisfactory insertion experiences cause endoscopist psychophysiological fatigue and affect the quality of their inspection. This comparative study used propensity score matching (PSM) to determine whether endoscopist satisfaction during scope insertion was related to polyp detection rate (PDR). Patients who underwent colonoscopy screening between April 2019 and December 2022 were enrolled in this study. The endoscopist satisfaction score (high and low) during the insertion phase in each examination was recorded based on the level of fatigue and presence of paradoxical scope movement. All examinations were classified into 2 groups: a high and a low satisfaction score group. After PSM with potential confounding factors related to polyp detection (endoscopist, insertion and withdrawal time, and sedative agent use), the PDR and adenoma detection rate (ADR) were compared. Overall, 4142 patients (average age, 54.1 years old; 54.4% male) underwent colonoscopies performed by twelve experienced endoscopists. Analysis using a logistic regression model revealed that a high satisfaction score during the insertion phase was an independent predictor of polyp detection (P < .001, odds ratio 1.79, 95% CI 1.41-2.33), whereas insertion time was not. After PSM, 513 patients from both groups were eligible for comparison. Polyp detection rate and ADR were significantly higher in the high-satisfaction group than in the low-satisfaction group (49.5% vs. 36.6%, P < .001; 35.1% vs. 27.1%, P = .007). The endoscopists\' level of satisfaction with the insertion phase was shown to be a potential predictor of PDR in screening colonoscopy.

OBJECTIVE: Large nonpedunculated colorectal polyps ≥ 20 mm (LNPCPs) comprise 1% of all colorectal lesions. LNPCPs are more likely to contain advanced histology such as high-grade dysplasia and submucosal invasive cancer (SMIC). Endoscopic resection is the first-line approach for management of these lesions. Endoscopic resection options include endoscopic mucosal resection (EMR), cold-snare EMR (EMR), endoscopic submucosal dissection (ESD) and endoscopic full-thickness resection (EFTR). This review aimed to critically evaluate current endoscopic resection techniques.
RESULTS: Evidence-based selective resection algorithms should inform the most appropriate endoscopic resection technique. Most LNPCPs are removed by conventional EMR but there has been a trend toward C-EMR for endoscopic resection of LNPCPs. More high-quality trials are required to better define the limitations of C-EMR. Advances in our understanding of ESD technique, has clarified its role within the colorectum. More recently, the development of a full thickness resection device (FTRD) has allowed the curative endoscopic resection of select lesions.
CONCLUSIONS: Endoscopic resection should be regarded as the principle approach for all LNPCPs. Underpinned by high-quality research, endoscopic resection has become more nuanced, leading to improved patient outcomes.

Article Title: Adenomas and Sessile Serrated Lesions in 45-49-Year-Old Individuals Undergoing Colonoscopy: A Systematic Review and Meta-Analysis.

BACKGROUND: Colorectal polyps that develop via the conventional adenoma-carcinoma sequence [e.g., tubular adenoma (TA)] often progress to malignancy and are closely associated with changes in the composition of the gut microbiome. There is limited research concerning the microbial functions and gut microbiomes associated with colorectal polyps that arise through the serrated polyp pathway, such as hyperplastic polyps (HP). Exploration of microbiome alterations associated with HP and TA would improve the understanding of mechanisms by which specific microbes and their metabolic pathways contribute to colorectal carcinogenesis.
OBJECTIVE: To investigate gut microbiome signatures, microbial associations, and microbial functions in HP and TA patients.
METHODS: Full-length 16S rRNA sequencing was used to characterize the gut microbiome in stool samples from control participants without polyps [control group (CT), n = 40], patients with HP (n = 52), and patients with TA (n = 60). Significant differences in gut microbiome composition and functional mechanisms were identified between the CT group and patients with HP or TA. Analytical techniques in this study included differential abundance analysis, co-occurrence network analysis, and differential pathway analysis.
RESULTS: Colorectal cancer (CRC)-associated bacteria, including Streptococcus gallolyticus (S. gallolyticus), Bacteroides fragilis, and Clostridium symbiosum, were identified as characteristic microbial species in TA patients. Mediterraneibacter gnavus, associated with dysbiosis and gastrointestinal diseases, was significantly differentially abundant in the HP and TA groups. Functional pathway analysis revealed that HP patients exhibited enrichment in the sulfur oxidation pathway exclusively, whereas TA patients showed dominance in pathways related to secondary metabolite biosynthesis (e.g., mevalonate); S. gallolyticus was a major contributor. Co-occurrence network and dynamic network analyses revealed co-occurrence of dysbiosis-associated bacteria in HP patients, whereas TA patients exhibited co-occurrence of CRC-associated bacteria. Furthermore, the co-occurrence of SCFA-producing bacteria was lower in TA patients than HP patients.
CONCLUSIONS: This study revealed distinct gut microbiome signatures associated with pathways of colorectal polyp development, providing insights concerning the roles of microbial species, functional pathways, and microbial interactions in colorectal carcinogenesis.

OBJECTIVE: Colorectal cancer (CRC) is considered one of the most common cancers in the world. Serrated polyps were found to be precursor lesions for CRC. BRAF mutation (V600E) has been strongly linked to the development of these lesions. No previous study concerning BRAF immunohistochemical expression in serrated polyps- was done in Oman. The primary objective of our study was to assess the prevalence of BRAF (V600E) mutation in serrated colorectal polyps in the Omani population. The secondary objectives were to assess the prevalence of serrated polyps and their characteristic features: type, site and size as well as the relationship between BRAF (V600E) mutation and polyp type, site and size.
METHODS: Ninety-one hyperplastic polyps (HP) (76.5%), 24 sessile serrated lesions (SSL) (20.2%) and 4 cases of tubular adenomas with low grade dysplasia (3.4%) were studied for BRAF (V600E) immunohistochemical expression. No case of traditional serrated adenoma (TSA) was present. Control cases of craniopharyngioma and papillary thyroid carcinoma were included.
RESULTS: BRAF (V600E) IHC was positive in 63 of the HP polyps (69.2%), 13 SSLs (54.2%) and none of the adenomatous polyps. The majority of positive polyps (75.0%) were ≤5 mm in size, 17.9% were 5-10 mm and 7.1% were ≥10 mm in size.  The majority of BRAF (V600E) positive polyps (68.1 %) were in the distal colon and 31.9 % were in the proximal colon. The majority of positive cases for BRAF (V600E) were showing multiple polyps (61.8 %). None of the tubular adenomas showed any BRAF (V600E) positivity.
CONCLUSIONS: Serrated polyps are now well known for their potential to develop CRC. Immunohistochemistry is an easy and reproducible way to detect BRAF (V600E) mutation. Our study showed there is high prevalence (64.3%) of BRAF mutation in serrated polyps in the Omani population. The majority of these polyps- were HP and SSL; and ≤5 mm in size and located in the distal colon.

Colorectal polyps serve as potential precursors of colorectal cancer and automating polyp segmentation aids physicians in accurately identifying potential polyp regions, thereby reducing misdiagnoses and missed diagnoses. However, existing models often fall short in accurately segmenting polyps due to the high degree of similarity between polyp regions and surrounding tissue in terms of color, texture, and shape. To address this challenge, this study proposes a novel three-stage polyp segmentation network, named Reverse Attention Feature Purification with Pyramid Vision Transformer (RAFPNet), which adopts an iterative feedback UNet architecture to refine polyp saliency maps for precise segmentation. Initially, a Multi-Scale Feature Aggregation (MSFA) module is introduced to generate preliminary polyp saliency maps. Subsequently, a Reverse Attention Feature Purification (RAFP) module is devised to effectively suppress low-level surrounding tissue features while enhancing high-level semantic polyp information based on the preliminary saliency maps. Finally, the UNet architecture is leveraged to further refine the feature maps in a coarse-to-fine approach. Extensive experiments conducted on five widely used polyp segmentation datasets and three video polyp segmentation datasets demonstrate the superior performance of RAFPNet over state-of-the-art models across multiple evaluation metrics.