Colorectal Polyps Research Articles

The use of artificial intelligence in colonoscopic evaluations.

This review aims to highlight the transformative impact of artificial intelligence in the field of gastrointestinal endoscopy, particularly in the detection and characterization of colorectal polyps. Over the past decade, artificial intelligence has significantly advanced the medical industry, including gastrointestinal endoscopy. Computer aided diagnosis - detection (CADe) systems have shown notable success in increasing ADR. Recent meta-analyses of RCTs have demonstrated that patients undergoing colonoscopy with CADe assistance had a higher ADR compared with conventional methods. Similarly, computer aided diagnosis - characterization (CADx) systems have proven effective in distinguishing between adenomatous and nonadenomatous polyps, enhancing diagnostic confidence and supporting cost-saving measures like the resect-and-discard strategy. Despite the high performance of these systems, the variability in real-world adoption highlights the importance of integrating artificial intelligence as an assistive tool rather than a replacement for human expertise. Artificial intelligence integration in colonoscopy, through CADe and CADx systems, marks a significant advancement in gastroenterology. These systems enhance lesion detection and characterization, leading to improved diagnostic accuracy, training outcomes, and clinical workflow efficiency. While artificial intelligence offers substantial benefits, the optimal approach involves using artificial intelligence to augment the expertise of endoscopists, ensuring that clinical decisions remain under human oversight.

Clinical Assessment and Genetic Testing for Hereditary Polyposis Syndromes in an Italian Cohort of Patients with Colorectal Polyps.

Background: Hereditary polyposis syndromes are clinically and genetically heterogeneous conditions associated with increased colorectal cancer risk. They are classified based on polyp histology, inheritance mode, causal gene, and colonic and extracolonic manifestations. Their diagnosis is challenging due to overlapping and heterogeneous clinical presentations. Methods: A multigene next-generation sequencing panel was used to screen 75 index cases with colorectal polyps and a personal/family history of cancer for key hereditary polyposis-associated genes (APC, BMPR1A, MUTYH, PTEN, SMAD4, and STK11) in order to identify germline genetic variants. Results: In the screened index cases, we found 14 pathogenic variants involving APC, MUTYH, SMAD4, and STK11 and 6 variants of uncertain significance involving APC, BMPR1A, and SMAD4. In this cohort, four patients not fulfilling the recommended eligibility criteria of current National Comprehensive Cancer Network (NCCN) guidelines for genetic testing were molecularly diagnosed with a hereditary polyposis syndrome. Conclusions: Our findings indicate that stringent NCCN eligibility criteria for molecular screening may lead to missing some of the patients affected by hereditary polyposis syndromes. This highlights the need for a careful evaluation of patients' clinical manifestations, polyp number, age of polyp onset, and family history to select appropriate candidates for molecular diagnosis of these conditions.

A prospective multicenter randomized controlled trial on artificial intelligence assisted colonoscopy for enhanced polyp detection

Colon polyp detection and removal via colonoscopy are essential for colorectal cancer screening and prevention. This study aimed to develop a colon polyp detection program based on the RetinaNet algorithm and verify its clinical utility. To develop the AI-assisted program, the dataset was fully anonymized and divided into 10 folds for 10-fold cross-validation. Each fold consisted of 9,639 training images and 1,070 validation images. Video data from 56 patients were used for model training, and transfer learning was performed using the developed still image-based model. The final model was developed as a real-time polyp-detection program for endoscopy. To evaluate the model’s performance, a prospective randomized controlled trial was conducted at six institutions to compare the polyp detection rates (PDR). A total of 805 patients were included. The group that utilized the AI model showed significantly higher PDR and adenoma detection rate (ADR) than the group that underwent colonoscopy without AI assistance. Multivariate analysis revealed an OR of 1.50 for cases where polyps were detected. The AI-assisted polyp-detection program is clinically beneficial for detecting polyps during colonoscopy. By utilizing this AI-assisted program, clinicians can improve adenoma detection rates, ultimately leading to enhanced cancer prevention.

Colon polyp detection based on multi-scale and multi-level feature fusion and lightweight convolutional neural network

Early diagnosis and treatment of colorectal polyps are crucial for preventing colorectal cancer. This paper proposes a lightweight convolutional neural network for the automatic detection and auxiliary diagnosis of colorectal polyps. Initially, a 53-layer convolutional backbone network is used, incorporating a spatial pyramid pooling module to achieve feature extraction with different receptive field sizes. Subsequently, a feature pyramid network is employed to perform cross-scale fusion of feature maps from the backbone network. A spatial attention module is utilized to enhance the perception of polyp image boundaries and details. Further, a positional pattern attention module is used to automatically mine and integrate key features across different levels of feature maps, achieving rapid, efficient, and accurate automatic detection of colorectal polyps. The proposed model is evaluated on a clinical dataset, achieving an accuracy of 0.9982, recall of 0.9988, F1 score of 0.9984, and mean average precision (mAP) of 0.9953 at an intersection over union (IOU) threshold of 0.5, with a frame rate of 74 frames per second and a parameter count of 9.08 M. Compared to existing mainstream methods, the proposed method is lightweight, has low operating configuration requirements, high detection speed, and high accuracy, making it a feasible technical method and important tool for the early detection and diagnosis of colorectal cancer.

Real-time and programmable transcriptome sequencing with PROFIT-seq

The high diversity and complexity of the eukaryotic transcriptome make it difficult to effectively detect specific transcripts of interest. Current targeted RNA sequencing methods often require complex pre-sequencing enrichment steps, which can compromise the comprehensive characterization of the entire transcriptome. Here we describe programmable full-length isoform transcriptome sequencing (PROFIT-seq), a method that enriches target transcripts while maintaining unbiased quantification of the whole transcriptome. PROFIT-seq employs combinatorial reverse transcription to capture polyadenylated, non-polyadenylated and circular RNAs, coupled with a programmable control system that selectively enriches target transcripts during sequencing. This approach achieves over 3-fold increase in effective data yield and reduces the time required for detecting specific pathogens or key mutations by 75%. We applied PROFIT-seq to study colorectal polyp development, revealing the intricate relationship between host immune responses and bacterial infection. PROFIT-seq offers a powerful tool for accurate and efficient sequencing of target transcripts while preserving overall transcriptome quantification, with broad applications in clinical diagnostics and targeted enrichment scenarios.

Large nonpedunculated colorectal polyp management through the lens of an interventional endoscopist.

SummaryMinimally invasive endoscopic resection techniques are now the first-line management strategy for most large (> 20 mm) nonpedunculated colorectal polyps (LNPCPs). Appropriate technique selection depends on optical evaluation to predict lesion histopathology alongside the presence of and depth of malignant invasion. We review the indications and performance of endoscopic mucosal resection, cold snare resection, and endoscopic submucosal dissection. These complementary techniques, bolstered by site-specific technical modifications and ancillary techniques, are an effective, efficient, and safe alternative to surgery. An understanding of the role of minimally invasive endoscopic resection techniques is crucial for all endoscopists and surgeons involved in LNPCP management.

Advancements in the use of AI in the diagnosis and management of inflammatory bowel disease.

Inflammatory bowel disease (IBD) causes chronic inflammation of the colon and digestive tract, and it can be classified as Crohn's disease (CD) and Ulcerative colitis (UC). IBD is more prevalent in Europe and North America, however, since the beginning of the 21st century it has been increasing in South America, Asia, and Africa, leading to its consideration as a worldwide problem. Optical colonoscopy is one of the crucial tests in diagnosing and assessing the progression and prognosis of IBD, as it allows a real-time optical visualization of the colonic wall and ileum and allows for the collection of tissue samples. The accuracy of colonoscopy procedures depends on the expertise and ability of the endoscopists. Therefore, algorithms based on Deep Learning (DL) and Convolutional Neural Networks (CNN) for colonoscopy images and videos are growing in popularity, especially for the detection and classification of colorectal polyps. The performance of this system is dependent on the quality and quantity of the data used for training. There are several datasets publicly available for endoscopy images and videos, but most of them are solely specialized in polyps. The use of DL algorithms to detect IBD is still in its inception, most studies are based on assessing the severity of UC. As artificial intelligence (AI) grows in popularity there is a growing interest in the use of these algorithms for diagnosing and classifying the IBDs and managing their progression. To tackle this, more annotated colonoscopy images and videos will be required for the training of new and more reliable AI algorithms. This article discusses the current challenges in the early detection of IBD, focusing on the available AI algorithms, and databases, and the challenges ahead to improve the detection rate.

Tranexamic acid to prevent bleeding after endoscopic resection of large colorectal polyps: a pilot project.

Delayed post-polypectomy bleeding (DPPB) can occur up to a month following the procedure but is typically seen within the first week. Tranexamic acid (TXA) is a member of a class of drugs called antifibrinolytic agents. It reduces fibrinolysis by slowing down the conversion of plasminogen to plasmin, which may prevent bleeding. The goal of this pilot study is to assess the feasibility of using tranexamic acid after endoscopic mucosal resection (EMR) of large (≥2 cm) non-pedunculated colorectal polyps (LNPCPs) to prevent DPPB. This was a single centre feasibility study conducted at the Kingston Health Sciences Centre in 2021. After the polypectomy was completed, IV tranexamic acid was given [1 gram of TXA in 100 mL of normal saline] and infused over a 10-min interval. The participants received tranexamic acid 1 gram PO TID to be taken for 5 days. A total of 25 patients were enrolled with a mean polyp size of 3 cm. Intraprocedural bleeding occurred in 7 patients (28%) and all of these were treated with soft coagulation. Two patients had clipping for suspected muscle injury. All 25 patients received IV TXA post-procedure. Sixteen patients (64%) took every dose of the prescribed pills. One patient presented with post-polypectomy bleeding. All patients completed the day 30 follow-up phone call. There were no major adverse events. TXA to prevent delayed post-polypectomy bleeding (DPPB) was feasible to use with no major adverse events reported. A randomized controlled study will be needed to see if TXA can significantly reduce DPPB.

Characteristics and risk factor analyses of high-grade intraepithelial neoplasia in older patients with colorectal polyps.

According to the degree of intradermal neoplasia in the colorectal exhalation, it can be divided into two grades: Low-grade intraepithelial neoplasia (LGIN) and high-grade intraepithelial neoplasia (HGIN). Currently, it is difficult to accurately diagnose LGIN and HGIN through imaging, and clinical diagnosis depends on postoperative histopathological diagnosis. A more accurate method for evaluating HGIN preoperatively is urgently needed in the surgical treatment and nursing intervention of colorectal polyps. To explore the characteristics and risk factors of HGIN in older patients with colorectal polyps. We selected 84 older patients diagnosed with HGIN as the HGIN group (n = 95 colonic polyps) and 112 older patients diagnosed with LGIN as the LGIN group (n = 132 colonic polyps) from Shandong Provincial Hospital Affiliated to Shandong First Medical University. The endoscopic features, demographic characteristics, and clinical manifestations of the two patient groups were compared, and a logistic regression model was used to analyze the risk factors for HGIN in these patients. The HGIN group was older and had a higher number of sigmoid colon polyps, rectal polyps, pedunculated polyps, polyps ≥ 1.0 cm in size, polyps with surface congestion, polyps with surface depression, and polyps with villous/tubular adenomas, a higher proportion of patients with diabetes and a family history of colorectal cancer, patients who experienced rectal bleeding or occult blood, patients with elevated carcinoembryonic antigen (CEA) and cancer antigen 199 (CA199), and lower nutritional levels and higher frailty levels. The polyp location (in the sigmoid colon or rectum), polyp diameter (≥ 1.0 cm), pathological diagnosis of (villous/tubular adenoma), family history of colorectal cancer, rectal bleeding or occult blood, elevated serum CEA and CA199 levels, lower nutritional levels and higher frailty levels also are independent risk factors for HGIN. The occurrence of high-grade neoplastic transformation in colorectal polyps is closely associated with their location, size, villous/tubular characteristics, family history, elevated levels of tumor markers, and lower nutritional levels and higher frailty levels.

Malakoplakia, a rare inflammatory condition presenting as a colon polyp

Abstract Introduction/Objective Malakoplakia is a rare histiocytic disease caused by defects in phagocytic or degradative functions of histiocytes in response to gram negative coliforms (E. coli or Proteus) that results in chronic inflammatory state, followed by intracellular deposition of iron and calcium (known as Michaelis-Gutmann bodies). It’s more common in immunocompromised patients and the mean age at diagnosis is fifth decade. It occurs in all organs, common in GU tract, particularly bladder, but also seen in gastrointestinal tract (most commonly colon, followed by stomach and duodenum), central nervous system and female genital tract. In gastrointestinal tract, it can present as a polyp with diffuse mucosal involvement, submucosal thickening, and even may cause mass. Methods/Case Report A 60 -year-old male smoker presented to our hospital with history of colon polyps; colonoscopy revealed a 6 mm sessile polyp at the hepatic flexure. A biopsy was performed which showed numerous epithelioid histiocytes with granular eosinophilic cytoplasm, abundant Michaelis-Gutmann bodies and increased lymphocytes. Immunohistochemical stains showed diffuse positivity for CD68; and PAS stain was positive for histiocytic cytoplasmic granules. Based on this data, the diagnosis of Malakoplakia was confirmed. Malakoplakia is treated with antibiotics that concentrate in macrophages (quinolones or trimethoprim-sulfamethoxazole), antibiotics directed against E. coli, surgery and possibly discontinuation of immunosuppressive drug therapy. Results (if a Case Study enter NA) Malakoplakia, in this case, was presented clinically as a sessile colon polyp and histologically showed numerous epithelioid histiocytes with granular eosinophilic cytoplasm, with Immunohistochemical stains (CD68; and PAS stain) the correct diagnosis was made. Other presentations of Malakoplakia include diffuse mucosal involvement, submucosal thickening, or mass. Histologically, it may rarely be mistaken as signet ring carcinoma. These variable presentations in GU tract or colon can be interpreted as malignancy with consequent unnecessary interventions. Hence, awareness of Malakoplakia with careful histopathologic examination and the use of immunohistochemical studies are advisable in that cases. Conclusion We would like to emphasize that Malakoplakia can be clinically and histologically misdiagnosed as a malignant condition; therefore histopathologic and immunohistochemical studies are needed to correctly diagnose this entity.

Association between Diverticulosis and Colorectal Neoplasia: Analysis from a Large Austrian Database.

Background: Colorectal neoplasia and diverticulosis are common findings on colonoscopies. While adenomas are precursors to colorectal cancer, diverticulosis is usually asymptomatic but can lead to diverticulitis. Despite their prevalence and coexistence, the relationship between these conditions remains unclear. This study investigates whether diverticulosis is associated with adenomas, considering shared risk factors and potential inflammation-driven mechanisms. Methods: We examined 6154 asymptomatic individuals undergoing colorectal cancer screening in Austria. Diverticulosis and colorectal neoplasia were documented during screenings based on macroscopic definitions. Advanced neoplasia was defined as polyps >1 cm or high-grade dysplasia. Associations between diverticulosis and neoplastic findings were assessed using univariate and multivariable logistic regression models. Results: Although the overall incidence of any polypoid lesion was higher in the diverticulosis group (37% vs. 30%), statistical analysis revealed a comparable rate of advanced neoplasms in both groups. Importantly, no significant link between diverticulosis and advanced neoplasms was found (OR 1.125; 95% CI: 0.933 to 1.357, p = 0.218) even after adjusting for confounding factors. In a univariate analysis, a statistically significant association between diverticulosis and the presence of any colorectal polyps was identified (OR 1.388; 95% CI: 1.244-1.549, p < 0.0001). However, after adjusting for confounding factors in model 2 (OR 1.065, 95% CI: 0.942 to 1.204, p = 0.314) and model 3 (OR 1.071, 95% CI: 0.925 to 1.239, p = 0.360), this effect was also not statistically significant. Conclusions: Patients with diverticulosis share demographic and clinical features with those at risk of colorectal neoplasia, such as older age, male gender, and higher cardiometabolic risk. However, diverticulosis does not independently increase the risk of advanced colorectal neoplasia or unspecified polypoid lesions.

The Impact of Endoscopic Mucosal Resection and Endoscopic Submucosal Dissection on Colonic Polyp Resection and Factors Influencing Recurrence.

This study aims to assess the effectiveness of endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD) in the endoscopic resection of colonic polyps and investigate the factors influencing polyp recurrence. A total of 174 patients with colorectal polyps admitted to the Gastroenterology Department during the same period were included in this prospective randomized controlled study. The patients were randomly allocated to the EMR group and ESD group (72 cases in each group) using a random number table. The clinical efficacy, quality of life, adverse reactions, and 1-year postoperative recurrence rate were compared between the 2 groups. In addition, factors influencing polyp recurrence were analyzed. No significant differences were observed between the EMR and ESD groups in terms of clinical efficacy, postoperative quality of life, and postoperative complications. However, the postoperative recurrence rate in the ESD group was significantly lower than that in the EMR group. Multifactorial logistic regression analysis revealed that the number of polyps ≥3, maximum polyp diameter ≥2cm, and family history of colorectal cancer were independent risk factors for colonic polyp recurrence. ESD and EMR demonstrate similar efficacy and safety in patients with colonic polyps. However, the recurrence rate after ESD is significantly lower than after EMR. Furthermore, multifactorial analysis indicates that a larger polyp diameter, a more significant number of polyps, and a family history of colorectal cancer are independent risk factors for the recurrence of colonic polyps following resection.

Analysis of the outcomes of postdiverticulitis investigations: a multicentre cohort study including 1,120 patients.

The aim of this study was to assess the yield of the endoscopic investigations performed following the resolution of acute diverticulitis. A retrospective multicentre study included patients with multislice computed tomography (MSCT)-proven diverticulitis, in four NHS hospitals, between January 2016 and April 2023. The primary outcome was the rate of colonic cancer in the diseased segment. Secondary outcomes included the rate of malignancy in the nondiseased colonic segments, the benign colonic polyp detection rate, the rate of malignancy in the resected surgical specimens in patients who underwent an emergency surgery on the index admission and the rate of complications in the investigated group. A total of 1,120 patients were included in the study, out of which 604 were females, with a median age of 61 years; 731 patients (65%) had uncomplicated diverticulitis (Hinchey 1A) while 389 (35%) had complicated diverticulitis (Hinchey 1B-4). Following the acute episode, 757 (74%) patients had subsequent endoscopic evaluation. The incidence of colorectal cancer (CRC) or advanced adenomas (AA) in patients with uncomplicated diverticulitis was 0.14%. In the complicated diverticulitis group, the incidence of CRC/AA in patients with Hinchey 1b and Hinchey 2 was 1.4% and 5.4%, respectively. Out of the 102 patients who underwent emergency colonic resection for suspected perforated diverticulitis, 18 (17.6%) had histological evidence of colonic malignancy. Endoscopic investigations following uncomplicated diverticulitis have a low yield for sinister colonic pathology. Colonoscopy should be planned following complicated diverticulitis and in patients with uncomplicated diverticulitis with suspicious radiological finding on index imaging or in patients with ongoing clinical manifestations. In patients who undergo emergency surgery, oncological principles should be applied whenever possible.

Causal links between circulatory inflammatory cytokines and risk of digestive polyps: a Mendelian randomization analysis.

There is a high morbidity of polyps in the digestive tract, and certain subtypes of polyps are thought to induce cancer progression and often recur, which may be associated with chronic inflammation. Mendelian randomization (MR) can help identify potential causative relationships and inform early treatment action. We performed a bidirectional two-sample MR analysis implementing the results from genome-wide association studies for 41 serum cytokines from 8,293 Finnish individuals, and three types of polyps from European ancestry, respectively, including gastric polyp (6,155 cases vs. 341,871 controls), colonic polyp (22,049 cases vs. 332,368 controls) and gallbladder polyp (458 cases vs. 340,083 controls). Inverse-variance weighted (IVW), weight median (WM), and MR-Egger methods were used for calculating causal estimates. Furthermore, Bayesian model averaging MR (MR-BMA) method was employed to detect the dominant causal circulatory cytokines with adjustment for pleiotropy effects. Our univariable MR using inverse-variance weight method identified causal associations of IL-2ra (OR: 0.892, 95%CI: 0.828-0.961, p = 0.003), MIG (OR: 1.124, 95%CI: 1.046-1.207, p = 0.001) and IL-18 (OR: 0.912, 95%CI: 0.852-0.977, p = 0.008) with gastric polyp, MIP1b (OR: 0.956, 95%CI: 0.927-0.987, p = 0.005) and IL-6 (OR: 0.931, 95%CI: 0.870-0.995, p = 0.035) with colonic polyp and IL-9 (OR: 0.523, 95%CI: 0.345-0.794, p = 0.0007) with gallbladder polyp. Finally, our MR-BMA analysis prioritized MIG (MIP = 0.332, MACE = 0.022; PP: 0.264, MSCE = 0.059), IL-18 (MIP = 0.302, MACE = -0.020; PP: 0.243, MSCE = -0.059) and IL-2ra (MIP: 0.129; MACE: -0.005; PP: 0.112, MSCE: -0.031) for gastric polyp, and MIP1b (MIP = 0.752, MACE = -0.033; PP: 0.665, MSCE = -0.044) and IL-6 (MIP: 0.196; MACE: -0.012; PP: 0.140, MSCE: -0.064) for colonic polyp, and IL-9 (MIP = 0.936, MACE = -0.446; PP: 0.781, MSCE = -0.478) for gallbladder polyp as the top-ranked protective factors. Our research advances the current understanding of the function of certain inflammatory biomarker pathways in the genesis and malignant mutation of polyps in the digestive tract. Deeper substantiation is necessary to assess the potential of these cytokines as pharmacological or lifestyle targets for digestive polyps prevention.

Cold versus hot snare endoscopic mucosal resection for large (≥15 mm) flat non-pedunculated colorectal polyps: a randomised controlled trial

Background and aimsConventional hot snare endoscopic mucosal resection (H-EMR) is effective for the management of large (≥20 mm) non-pedunculated colon polyps (LNPCPs) however, electrocautery-related complications may incur significant morbidity. With...

A lighter hybrid feature fusion framework for polyp segmentation

Colonoscopy is widely recognized as the most effective method for the detection of colon polyps, which is crucial for early screening of colorectal cancer. Polyp identification and segmentation in colonoscopy images require specialized medical knowledge and are often labor-intensive and expensive. Deep learning provides an intelligent and efficient approach for polyp segmentation. However, the variability in polyp size and the heterogeneity of polyp boundaries and interiors pose challenges for accurate segmentation. Currently, Transformer-based methods have become a mainstream trend for polyp segmentation. However, these methods tend to overlook local details due to the inherent characteristics of Transformer, leading to inferior results. Moreover, the computational burden brought by self-attention mechanisms hinders the practical application of these models. To address these issues, we propose a novel CNN-Transformer hybrid model for polyp segmentation (CTHP). CTHP combines the strengths of CNN, which excels at modeling local information, and Transformer, which excels at modeling global semantics, to enhance segmentation accuracy. We transform the self-attention computation over the entire feature map into the width and height directions, significantly improving computational efficiency. Additionally, we design a new information propagation module and introduce additional positional bias coefficients during the attention computation process, which reduces the dispersal of information introduced by deep and mixed feature fusion in the Transformer. Extensive experimental results demonstrate that our proposed model achieves state-of-the-art performance on multiple benchmark datasets for polyp segmentation. Furthermore, cross-domain generalization experiments show that our model exhibits excellent generalization performance.

New Approaches Based on Inflammatory Indexes in the Evaluation of the Neoplastic Potential of Colon Polyps

Colorectal polyps, precursors to colorectal cancer (CRC), require precise identification for appropriate diagnosis and therapy. This study aims to investigate the differences in hematological and inflammatory markers, specifically the CALLY index, HALP score, and immuno-inflammatory indexes, between neoplastic and nonneoplastic polyps. A retrospective cross-sectional study was conducted on 758 patients aged 61.0 ± 11.8 who underwent polypectomy between June 2021 and May 2024. Patients with colorectal adenocarcinoma (n = 22) were excluded. The polyps were classified into neoplastic and nonneoplastic categories based on histopathological evaluation. The study compared the CALLY index, HALP score, and various inflammatory indexes between neoplastic and nonneoplastic polyps. Out of 758 polyps analyzed, 514 were neoplastic, and 244 were nonneoplastic. Neoplastic polyps exhibited significantly lower CALLY and HALP scores (p &lt; 0.05) and higher immuno-inflammatory indexes (p &lt; 0.05) compared to nonneoplastic polyps. Dysplasia status, polyp diameter, and sigmoid colon localization were significant factors in determining neoplastic growth potential. No significant differences were observed in polyp localization in the proximal and distal colon segments or in solitary versus multiple polyps. The CALLY and HALP scores and immuno-inflammatory indexes can serve as valuable markers for distinguishing neoplastic from nonneoplastic polyps. These indexes reflect underlying inflammatory and immune responses, highlighting their potential utility in the early detection and risk stratification of colorectal polyps. Integrating these markers into clinical practice may enhance diagnostic accuracy and improve patient management, leading to timely interventions and better outcomes for individuals at risk of CRC.

Should Gallbladder Pathologies Be Investigated in Patients With Colon Polyps?

Background Data regarding the frequency of development of gallbladder pathologies in patients with colon polyps are quite limited and heterogeneous. Hence, this study aimed to investigate whether colon polyps cause an increased risk of developing gallbladder pathologies and the necessity of ultrasonographic screening. Methodology This retrospective, cross-sectional study was conducted among adult patients who underwent a colonoscopy and hepatobiliary ultrasound as part of their health check-up from January 2018to January 2023. The frequency, etiological factors, and association of gallbladder pathologies with colon polyps were investigated. Results A total of 128 patients were included in the study. When the distribution of colon polyp pathology was examined, 78.9% (n = 101) were adenomas, 18.8% (n = 24) were non-neoplastic polyps, and 2.3% (n = 3) were adenocarcinomas. The rate of patients with gallbladder stones was 10.9% (n = 14) and the rate of patients with polyps was 18.8% (n = 24). On multivariate logistic regression analysis, variables found to be significant for the development of gallbladder pathologies were determined as obesity, hyperlipidemia, and polyp's distal colon location. Conclusions Obesity and metabolic syndrome were among the etiological factors in this patient group. Hepatobiliary ultrasound, a non-invasive and inexpensive examination, is useful in patients with colon polyps.

S428 Outcome Analysis of Colonoscopic Polypectomy and Strategic Surveillance in Patients With 10 or More Colorectal Polyps

S428 Outcome Analysis of Colonoscopic Polypectomy and Strategic Surveillance in Patients With 10 or More Colorectal Polyps

Improving the endoscopic recognition of early colorectal carcinoma using artificial intelligence: current evidence and future directions.

Background and study aims Artificial intelligence (AI) has great potential to improve endoscopic recognition of early stage colorectal carcinoma (CRC). This scoping review aimed to summarize current evidence on this topic, provide an overview of the methodologies currently used, and guide future research. Methods A systematic search was performed following the PRISMA-Scr guideline. PubMed (including Medline), Scopus, Embase, IEEE Xplore, and ACM Digital Library were searched up to January 2024. Studies were eligible for inclusion when using AI for distinguishing CRC from colorectal polyps on endoscopic imaging, using histopathology as gold standard, reporting sensitivity, specificity, or accuracy as outcomes. Results Of 5024 screened articles, 26 were included. Computer-aided diagnosis (CADx) system classification categories ranged from two categories, such as lesions suitable or unsuitable for endoscopic resection, to five categories, such as hyperplastic polyp, sessile serrated lesion, adenoma, cancer, and other. The number of images used in testing databases varied from 69 to 84,585. Diagnostic performances were divergent, with sensitivities varying from 55.0% to 99.2%, specificities from 67.5% to 100% and accuracies from 74.4% to 94.4%. Conclusions This review highlights that using AI to improve endoscopic recognition of early stage CRC is an upcoming research field. We introduced a suggestions list of essential subjects to report in research regarding the development of endoscopy CADx systems, aiming to facilitate more complete reporting and better comparability between studies. There is a knowledge gap regarding real-time CADx system performance during multicenter external validation. Future research should focus on development of CADx systems that can differentiate CRC from premalignant lesions, while providing an indication of invasion depth.