G-EYE Improves Polyp, Adenoma, and Serrated Polyp Detection Rates in Colonoscopy: A Systematic Review and Meta-analysis.

BACKGROUND: Colonoscopy is the gold-standard test to decrease mortality from colorectal cancer (CRC). G-EYE is an inflated balloon on the bending section of the scope with the ability to flatten the folds to improve the adenoma detection rate (ADR). We performed this meta-analysis to evaluate the efficacy of G-EYE in improving ADR and other quality indicators of colonoscopy. METHODS: A literature search was performed through March 21, 2023, on databases including Embase, Medline, Cochrane Central Register of Controlled Trials, Web of Science Core Collection, KCI-Korean Journal Index, and Global Index Medicus. Core concepts of G-EYE, colonoscopy, ADR, polyp detection rate (PDR), serrated polyp detection rate (SPDR), and withdrawal time were searched. Statistical analysis was performed with OpenMeta[Analyst]. The odds ratio (OR) for the proportional variable and mean difference for the continuous variable along with 95% CI was used with a P-value <0.05 considered statistically significant. We used the DerSimonian-Laird method and random effects model for pooling data. RESULTS: The search strategy yielded a total of 143 articles. Three studies with 3868 total colonoscopies were finalized. The pooled ADR, PDR, and SPDR showed statistical improvement with G-EYE (OR: 1.744, 95% CI: 1.534-1.984, P<0.001; OR: 1.766, 95% CI: 1.547-2.015, P<0.001; and OR: 1.603, 95% CI: 1.176-2.185, P=0.003). The withdrawal time was also noted to be higher in the G-EYE group (mean difference: 0.114, CI: 0.041-0.186, P=0.002). CONCLUSIONS: This meta-analysis suggests that G-EYE can improve ADR, PDR, and SPDR. Further studies are needed to evaluate the effect of G-EYE on interval CRC and mortality rate.

A semantic feature enhanced YOLOv5-based network for polyp detection from colonoscopy images.

Colorectal cancer (CRC) is a common digestive system tumor with high morbidity and mortality worldwide. At present, the use of computer-assisted colonoscopy technology to detect polyps is relatively mature, but it still faces some challenges, such as missed or false detection of polyps. Therefore, how to improve the detection rate of polyps more accurately is the key to colonoscopy. To solve this problem, this paper proposes an improved YOLOv5-based cancer polyp detection method for colorectal cancer. The method is designed with a new structure called P-C3 incorporated into the backbone and neck network of the model to enhance the expression of features. In addition, a contextual feature augmentation module was introduced to the bottom of the backbone network to increase the receptive field for multi-scale feature information and to focus on polyp features by coordinate attention mechanism. The experimental results show that compared with some traditional target detection algorithms, the model proposed in this paper has significant advantages for the detection accuracy of polyp, especially in the recall rate, which largely solves the problem of missed detection of polyps. This study will contribute to improve the polyp/adenoma detection rate of endoscopists in the process of colonoscopy, and also has important significance for the development of clinical work.

Diagnostic performance of the Japanese Narrow-band imaging expert team classification system using dual focus magnification in real-time Vietnamese setting.

The JNET classification, combined with magnified narrowband imaging (NBI), is essential for predicting the histology of colorectal polyps and guiding personalized treatment strategies. Despite its recognized utility, the diagnostic efficacy of JNET classification using NBI with dual focus (DF) magnification requires exploration in the Vietnamese context. This study aimed to investigate the diagnostic performance of the JNET classification with the NBI-DF mode in predicting the histology of colorectal polyps in Vietnam. A cross-sectional study was conducted at the University Medical Center in Ho Chi Minh City, Vietnam. During real-time endoscopy, endoscopists evaluated the lesion characteristics and recorded optical diagnoses using the dual focus mode magnification according to the JNET classification. En bloc lesion resection (endoscopic or surgical) provided the final pathology, serving as the reference standard for optical diagnoses. A total of 739 patients with 1353 lesions were recruited between October 2021 and March 2023. The overall concordance with the JNET classification was 86.9%. Specificities and positive predictive values for JNET types were: type 1 (95.7%, 88.3%); type 2A (81.4%, 90%); type 2B (96.6%, 54.7%); and type 3 (99.9%, 93.3%). The sensitivity and negative predictive value for differentiating neoplastic from non-neoplastic lesions were 97.8% and 88.3%, respectively. However, the sensitivity for distinguishing malignant from benign neoplasia was lower at 64.1%, despite a specificity of 95.9%. Notably, the specificity and positive predictive value for identifying deep submucosal cancer were high at 99.8% and 93.3%. In Vietnam, applying the JNET classification with NBI-DF demonstrates significant value in predicting the histology of colorectal polyps. This classification guides treatment decisions and prevents unnecessary surgeries.

Unmasking early colorectal cancer clues: in silico and in vitro investigation of downregulated IGF2, SOCS1, MLH1, and CACNA1G in SSA polyps.

BACKGROUND AND AIM: Colorectal cancer (CRC) originates from pre-existing polyps in the colon. The development of different subtypes of CRC is influenced by various genetic and epigenetic characteristics. CpG island methylator phenotype (CIMP) is found in about 15-20% of sporadic CRCs and is associated with hypermethylation of certain gene promoters. This study aims to find prognostic genes and compare their expression and methylation status as potential biomarkers in patients with serrated sessile adenomas/polyps (SSAP) and CRC, in order to evaluate which, one is a better predictor of disease. METHOD: This study employed a multi-phase approach to investigate genes associated with CRC and SSAP. Initially, two gene expression datasets were analyzed using R and Limma package to identify differentially expressed genes (DEGs). Venn diagram analysis further refined the selection, revealing four genes from the Weissenberg panel with significant changes. These genes, underwent thorough in silico evaluations. Once confirmed, they proceeded to wet lab experimentation, focusing on expression and methylation status. This comprehensive methodology ensured a robust examination of the genes involved in CRC and SSAP. RESULT: This study identified cancer-specific genes, with 8,351 and 1,769 genes specifically down-regulated in SSAP and CRC tissues, respectively. The down-regulated genes were associated with cell adhesion, negative regulation of cell proliferation, and drug response. Four highly downregulated genes in the Weissenberg panel, including CACNA1G, IGF2, MLH1, and SOCS1. In vitro analysis showed that they are hypermethylated in both SSAP and CRC samples while their expressions decreased only in CRC samples. CONCLUSION: This suggests that the decrease in gene expression could help determine whether a polyp will become cancerous. Using both methylation status and gene expression status of genes in the Weissenberg panel in prognostic tests may lead to better prognoses for patients.

[Standardized diagnosis and treatment of colorectal polyps].

This article explores the standardized management of colorectal polyps, including classification, treatment, follow-up, and preventive control. Corresponding treatment strategies, including endoscopic resection and surgical intervention, are employed for different types of polyps. Currently, there is debate over whether to choose endoscopic resection or surgical intervention for malignant polyps at pT1 stage. Drawing on the latest literature and guidelines, the article elaborates on polyp classification, treatment modalities, follow-up, and preventive measures. Standardized management of colorectal polyps is important for reducing the incidence of colorectal cancer and improving the cure rate of early-stage colorectal cancer.

APOE genotype, eicosapentaenoic acid (EPA) supplementation and n-3 highly unsaturated fatty acid (HUFA) levels in patients with multiple colorectal polyps: A secondary analysis of the seAFOod polyp prevention trial.

INTRODUCTION: We examined the relationship between Apolipoprotein E (APOE) genotype and n-3 highly unsaturated fatty acid (HUFA) levels in participants of the seAFOod trial, who were undergoing colonoscopy surveillance after removal of colorectal polyps. METHODS: Baseline and on-treatment (eicosapentaenoic acid [EPA] 2 g daily or placebo for 6 months) levels of n-3 HUFAs, and plasma 18-hydroxyeicosapentaenoic acid (HEPE), were analysed according to APOE genotype (based on polymorphisms rs429358 and rs7412) in 584 participants. RESULTS: Before treatment, APOE2/2 individuals had lower levels, and APOE4/4 participants had higher levels, of n-3 HUFAs, including EPA, than APOE3/3 counterparts (P < 0.01 for the APOE2/2 versus APOE4/4 comparison). After EPA supplementation, n-3 HUFA levels were not significantly different when stratified by APOE genotype, although APOE4 carriers displayed lower plasma 18-HEPE levels than individuals without an APOE4 allele (P = 0.002). CONCLUSIONS: APOE genotype is associated with differential n-3 HUFA and 18-HEPE levels in individuals with multiple colorectal polyps.

Colonic adenomatous polyp with florid presence of monoclonal lambda Russell bodies: Case report and etiopathogenic hypothesis / Pólipo adenomatoso colónico con presencia florida de cuerpos de Russell monoclonales lambda: comunicación de un caso e hipótesis etiopatogénica

Russell bodies (RBs) are round eosinophilic intracytoplasmic inclusions formed by condensed immunoglobulins in mature plasma cells, which are called Mott cells. These cells are rarely found in the gastric tract, with even less cases reported in the colorectal region. There are still many questions about this event, as it is still unknown the relationship between the agents reported of increasing the probability of appearance of these cells and the generation of RBs. In this case report we describe the fifth patient presenting an infiltration of Mott cells in a colorectal polyp, being the second case with a monoclonal origin without a neoplastic cause, and the first one monoclonal for lambda. A comparison with previously similar reported cases is also done, and a possible etiopathogenic hypothesis proposed. (AU)

Los cuerpos de Russell (RB) son inclusiones intracitoplasmáticas eosinofílicas redondas formadas por inmunoglobulinas condensadas en las células plasmáticas maduras, que se denominan células de Mott. Estas células rara vez se encuentran en el tracto gástrico, y son aún más infrecuentes en la región colorrectal. Actualmente hay muchas dudas sobre este evento, ya que se desconoce la relación entre los agentes causantes de aumentar la probabilidad de aparición tanto de estas células como de la de RB. En este caso describimos al quinto paciente con un pólipo colorrectal, localizado en el tracto colorrectal e infiltrado por células de Mott, siendo el segundo caso de origen monoclonal sin causa neoplásica y el primero monoclonal para lambda. También se hace una comparación con casos similares previamente reportados y se propone una hipótesis etiopatogénica. (AU)

Combined endoscopic mucosal resection and full-thickness resection for large colorectal polyps: a systematic review and meta-analysis.

BACKGROUND AND AIMS: Combined endoscopic mucosal resection (EMR) with endoscopic Full thickness resection (EFTR) is an emerging technique that has been developed to target colorectal polyps larger than 2 cm. We performed a systematic review and meta-analysis to evaluate this technique for the resection of large colorectal lesions. METHODS: We conducted a comprehensive search of multiple electronic databases from inception through August 2023, to identify studies that reported on hybrid FTR. A random-effects model was employed to calculate the overall pooled technical success, macroscopic complete resection, free vertical margins resection rate, adverse events, and recurrence on follow up. RESULTS: A total of 8 Study arms with 244 patients (30% women) were included in the analysis. The pooled technical success rate was 97% (95% CI 88%-100%, I2 = 79.93%). The pooled rate of macroscopic complete resection was achieved in 95% (95% CI 90%-99%, I2 = 49.98) with a free vertical margins resection rate 88% (95% CI, 78%-96%, I2 = 63.32). The overall adverse events rate was 2% (95% CI 0%-5%, I2 = 11.64) and recurrence rate of 6% (95% CI 2%-12%, I2=20.32). CONCLUSION: Combined EMR with EFTR is effective and safe for resecting large, and complex colorectal adenomas, offering a good alternative for high surgical risk patients. Regional heterogeneity was observed, indicating that outcomes may be impacted by differences in operator expertise and industry training certification across regions. Comparative studies that directly compare combined EMR with EFTR against alternative methods such as ESD and surgical resection are needed.

Risk of advanced neoplasia after removal of colorectal adenomas with high-grade dysplasia.

BACKGROUND: Many studies reported the presence of adenomas with high-grade dysplasia (HGD) at index colonoscopy increased the incidence of advanced neoplasia (AN) and colorectal cancer (CRC) following. However, the conclusion remains obscure due to lack of studies on the specific population of adenomas with HGD. This study aimed to assess the long-term risk of AN and CRC after removal of adenomas with HGD. METHODS: A total of 814 patients who underwent adenomas with HGD removal between 2010 and 2019 were retrospectively analyzed. The outcomes were the incidences of AN and CRC during surveillance colonoscopy. Cox proportional hazards models were utilized to identify risk factors associated with AN and CRC. RESULTS: During more than 2000 person-years of follow-up, we found that AN and CRC incidence densities were 44.3 and 4.4 per 1000 person-years, respectively. The 10-year cumulative incidence of AN and CRC were 39.1% and 5.5%, respectively. In the multivariate model, synchronous low-risk polyps (HR 1.80, 95% CI 1.10-2.93) and synchronous high-risk polyps (HR 3.99, 95% CI 2.37-6.72) were risk factors for AN, whereas participation in surveillance colonoscopy visits (HR 0.56, 95% CI 0.36-0.88 for 1 visit; HR 0.10, 95% CI 0.06-0.19 for ≥ 2 visits) were associated with decreased AN incidence. Additionally, elevated baseline carcinoembryonic antigen (CEA) level (HR 10.19, 95% CI 1.77-58.59) was a risk factor for CRC, while participation in ≥ 2 surveillance colonoscopy visits (HR 0.11, 95% CI 0.02-0.56) were associated with decreased CRC incidence. Interestingly, for 11 patients who developed CRC after removal of adenomas with HGD, immunohistochemistry revealed that 8 cases (73%) were deficient mismatch repair CRCs. CONCLUSIONS: Patients who have undergone adenoma with HGD removal are at higher risk of developing AN and CRC, while surveillance colonoscopy can reduce the risk. Patients with synchronous polyps, or with elevated baseline CEA level are considered high-risk populations and require more frequent surveillance.

Iterative feedback-based models for image and video polyp segmentation.

Accurate segmentation of polyps in colonoscopy images has gained significant attention in recent years, given its crucial role in automated colorectal cancer diagnosis. Many existing deep learning-based methods follow a one-stage processing pipeline, often involving feature fusion across different levels or utilizing boundary-related attention mechanisms. Drawing on the success of applying Iterative Feedback Units (IFU) in image polyp segmentation, this paper proposes FlowICBNet by extending the IFU to the domain of video polyp segmentation. By harnessing the unique capabilities of IFU to propagate and refine past segmentation results, our method proves effective in mitigating challenges linked to the inherent limitations of endoscopic imaging, notably the presence of frequent camera shake and frame defocusing. Furthermore, in FlowICBNet, we introduce two pivotal modules: Reference Frame Selection (RFS) and Flow Guided Warping (FGW). These modules play a crucial role in filtering and selecting the most suitable historical reference frames for the task at hand. The experimental results on a large video polyp segmentation dataset demonstrate that our method can significantly outperform state-of-the-art methods by notable margins achieving an average metrics improvement of 7.5% on SUN-SEG-Easy and 7.4% on SUN-SEG-Hard. Our code is available at https://github.com/eraserNut/ICBNet.

High risk features in colorectal adenomatous polyps: A multi-institutional study.

High risk features in colorectal adenomatous polyps include size >1 cm and advanced histology: high-grade dysplasia and villous architecture. We investigated whether the diagnostic rates of advanced histology in colorectal adenomatous polyps were similar among institutions across the United States, and if not, could differences be explained by patient age, polyp size, and/or CRC rate. Nine academic institutions contributed data from three pathologists who had signed out at least 100 colorectal adenomatous polyps each from 2018 to 2019 taken from patients undergoing screening colonoscopy. For each case, we recorded patient age and sex, polyp size and location, concurrent CRC, and presence or absence of HGD and villous features. A total of 2700 polyps from 1886 patients (mean age: 61 years) were collected. One hundred twenty-four (5 %) of the 2700 polyps had advanced histology, including 35 (1 %) with HGD and 101 (4 %) with villous features. The diagnostic rate of advanced histology varied by institution from 1.7 % to 9.3 % (median: 4.3 %, standard deviation [SD]: 2.5 %). The rate of HGD ranged from 0 % to 3.3 % (median: 1 %, SD: 1.2 %), while the rate of villous architecture varied from 1 % to 8 % (median: 3.7 %, SD: 2.5 %). In a multivariate analysis, the factor most strongly associated with advanced histology was polyp size >1 cm with an odds ratio (OR) of 31.82 (95 % confidence interval [CI]: 20.52-50.25, p < 0.05). Inter-institutional differences in the rate of polyps >1 cm likely explain some of the diagnostic variance, but pathologic subjectivity may be another contributing factor.

SimCol3D - 3D reconstruction during colonoscopy challenge.

Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps is challenging. A 3D map of the observed surfaces could enhance the identification of unscreened colon tissue and serve as a training platform. However, reconstructing the colon from video footage remains difficult. Learning-based approaches hold promise as robust alternatives, but necessitate extensive datasets. Establishing a benchmark dataset, the 2022 EndoVis sub-challenge SimCol3D aimed to facilitate data-driven depth and pose prediction during colonoscopy. The challenge was hosted as part of MICCAI 2022 in Singapore. Six teams from around the world and representatives from academia and industry participated in the three sub-challenges: synthetic depth prediction, synthetic pose prediction, and real pose prediction. This paper describes the challenge, the submitted methods, and their results. We show that depth prediction from synthetic colonoscopy images is robustly solvable, while pose estimation remains an open research question.

Prevention of delayed bleeding after resection of large colonic polyps.

A significant problem encountered in the resection of large, complex colonic polyps is delayed bleeding. This can occur up to two weeks after the procedure and is a significant source of comorbidity. Untreated it can prove life threatening. It is therefore a priority of modern endoscopy to develop and employ techniques to minimaize this. In this article we will review and discuss the evidence base and controversies in this field, with cold EMR technique, Post-EMR clip closure, and topical haemostatic agents.

Serrated polyposis syndrome: defining the epidemiology and predicting the risk of dysplasia.

BACKGROUND: Serrated polyposis syndrome is the most common polyposis syndrome that has neoplastic potential. However, the natural history, genetic basis, and risk of dysplasia and neoplasia of serrated polyposis syndrome are incompletely understood. The objective of this study is to define the epidemiology of serrated polyposis syndrome. Using this data, we aim to evaluate candidate variables for predicting the risk of dysplasia and neoplasia in sessile serrated lesions found in serrated polyposis syndrome patients. Finally, we aim to use this data to create and evaluate clinical prediction models for accuracy in predicting dysplastic sessile serrated lesions in serrated polyposis syndrome patients. METHODS: This was a regional Australian single-centre retrospective cohort study. Data was prospectively collected data from the clinical record database of a regional Australian gastroenterology practice. All patients undergoing colonoscopy at Port Macquarie Gastroenterology between January 2015 and September 2021 were screened for this study. Collected data included patient demographic, endoscopic, and histopathological findings. Clinical and endoscopic multivariate logistic regression models were created to predict dysplastic sessile serrated lesions. Model performance was examined using the area under the receiver operating curve. RESULTS: In total 8401 patients underwent a colonoscopy procedure during the study period. Serrated polyposis syndrome was diagnosed in 247, representing a prevalence of 2.94% (mean age 67.15 years, 62.75% female). Logistic regression identified; older age at serrated polyposis syndrome diagnosis, a personal history of colorectal cancer, size of the largest sessile serrated lesions removed, and total sessile serrated lesions count as predictors of dysplastic sessile serrated lesions. The clinical and endoscopic model had an area under the receiver operating curve of 0.75. CONCLUSION: Serrated polyposis syndrome is more common than previously described. The clinical and endoscopic variables identified in logistic regression have acceptable accuracy in predicting the risk of dysplasia, however other populations need to be studied to achieve generalisability and improve model performance.

Colonic lymphomatous polyposis mantle cell lymphoma: a case report and review of literature.

INTRODUCTION: Mantle cell lymphoma is a rare lymphoma of the gastrointestinal tract that may present as multiple lymphomatous polyposis. We report a case of lymphomatous polyposis with a review of the literature. CASE REPORT: A 56-year-old man of Black ethnicity and Ivorian nationality with no relevant past medical history, consulted for a sudden onset symptoms of gastrointestinal obstruction, which evolved over 2 days. Macroscopic examination revealed the presence of multiple polyploid formations of the colonic mucosa. Histology showed diffuse lymphomatous proliferation of submucosa consisting off small lymphoid cells with a hyperchromatic crenelated nucleus, suggesting lymphomatous polyposis. Immunohistochemical examination showed expression by the tumor cells of antibodies to CD20, CD5, Bcl2, and cyclin D1. They did not express antibodies to CD10 and CD23. The Ki67 proliferation index was 25%. We have thus retained the diagnosis of mantle cell lymphomatous polyposis. CONCLUSION: Multiple lymphomatous polyposis is a rare entity characterized by the presence of numerous gastrointestinal polyploid lesions sometimes involving several segments of the gastrointestinal tract. Typical lymphoma presenting as lymphomatous polyposis is mantle cell lymphoma; although, other tumors may have this aspect.

Genetic prediction of micronutrient levels and the risk of colorectal polyps: A mendelian randomization study.

OBJECTIVE: Previous epidemiological and experimental studies have yielded conflicting results regarding the influence of human micronutrient levels on the risk of colorectal polyps (CP). In our study, we conducted a two-sample Mendelian randomization (MR) investigation to probe the link between 13 human micronutrients (calcium, selenium, magnesium, phosphorus, folate, vitamins B-6, B-12, C, D, beta-carotene, iron, zinc, and copper) and the genetic susceptibility to CP. METHODS: Summary statistics for CP (n = 463,010) were obtained from pan-European genome-wide association studies, and instrumental variables for 13 micronutrients were screened from published genome-wide association studies (GWAS). After selecting suitable instrumental variables, we performed a two-sample MR study, deploying sensitivity analyses to judge heterogeneity and pleiotropy, using inverse variance weighted methods as our primary estimation tool. RESULTS: Our study identified that a genetic predisposition to elevated toenail and circulating selenium or serum ß-carotene concentrations lowers the risk of CP occurrence. However, no statistically significant association was observed between the other 11 micronutrients and the risk of CP. CONCLUSION: The study findings provide evidence that the micronutrient selenium and ß-carotene may confer protective effects against the development of CP.

REAL-Colon: A dataset for developing real-world AI applications in colonoscopy.

Detection and diagnosis of colon polyps are key to preventing colorectal cancer. Recent evidence suggests that AI-based computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems can enhance endoscopists' performance and boost colonoscopy effectiveness. However, most available public datasets primarily consist of still images or video clips, often at a down-sampled resolution, and do not accurately represent real-world colonoscopy procedures. We introduce the REAL-Colon (Real-world multi-center Endoscopy Annotated video Library) dataset: a compilation of 2.7 M native video frames from sixty full-resolution, real-world colonoscopy recordings across multiple centers. The dataset contains 350k bounding-box annotations, each created under the supervision of expert gastroenterologists. Comprehensive patient clinical data, colonoscopy acquisition information, and polyp histopathological information are also included in each video. With its unprecedented size, quality, and heterogeneity, the REAL-Colon dataset is a unique resource for researchers and developers aiming to advance AI research in colonoscopy. Its openness and transparency facilitate rigorous and reproducible research, fostering the development and benchmarking of more accurate and reliable colonoscopy-related algorithms and models.

Integrating artificial intelligence techniques for advancements in colorectal cancer management: navigating past and predicting future direction.

Artificial Intelligence (AI) in the last few years has emerged as a valuable tool in managing colorectal cancer, revolutionizing its management at different stages. In early detection and diagnosis, AI leverages its prowess in imaging analysis, scrutinizing CT scans, MRI, and colonoscopy views to identify polyps and tumors. This ability enables timely and accurate diagnoses, initiating treatment at earlier stages. AI has helped in personalized treatment planning because of its ability to integrate diverse patient data, including tumor characteristics, medical history, and genetic information. Integrating AI into clinical decision support systems guarantees evidence-based treatment strategy suggestions in multidisciplinary clinical settings, thus improving patient outcomes. This narrative review explores the multifaceted role of AI, spanning early detection of colorectal cancer, personalized treatment planning, polyp detection, lymph node evaluation, cancer staging, robotic colorectal surgery, and training of colorectal surgeons.

Establishment and validation of an artificial intelligence-based model for real-time detection and classification of colorectal adenoma.

Colorectal cancer (CRC) prevention requires early detection and removal of adenomas. We aimed to develop a computational model for real-time detection and classification of colorectal adenoma. Computationally constrained background based on real-time detection, we propose an improved adaptive lightweight ensemble model for real-time detection and classification of adenomas and other polyps. Firstly, we devised an adaptive lightweight network modification and effective training strategy to diminish the computational requirements for real-time detection. Secondly, by integrating the adaptive lightweight YOLOv4 with the single shot multibox detector network, we established the adaptive small object detection ensemble (ASODE) model, which enhances the precision of detecting target polyps without significantly increasing the model's memory footprint. We conducted simulated training using clinical colonoscopy images and videos to validate the method's performance, extracting features from 1148 polyps and employing a confidence threshold of 0.5 to filter out low-confidence sample predictions. Finally, compared to state-of-the-art models, our ASODE model demonstrated superior performance. In the test set, the sensitivity of images and videos reached 87.96% and 92.31%, respectively. Additionally, the ASODE model achieved an accuracy of 92.70% for adenoma detection with a false positive rate of 8.18%. Training results indicate the effectiveness of our method in classifying small polyps. Our model exhibits remarkable performance in real-time detection of colorectal adenomas, serving as a reliable tool for assisting endoscopists.