Search Results (850)

Background/Objectives: Colorectal cancer is a leading cause of cancer-related mortality worldwide, and early detection of gastrointestinal (GI) polyps through endoscopy is critical for improving patient outcomes. However, access to specialist gastroenterology care remains severely limited in Federal Health Professional Shortage Areas (HPSAs), particularly for high-acuity geriatric patients. This study proposes GeriAIGastroNet, a clinically oriented deep learning framework designed to support AI-assisted tele-gastroenterology workflows in resource-limited settings, with the primary objective of enabling AI-powered risk stratification and colonoscopy referral triage for elderly patients who lack on-site gastroenterology access. Methods: The framework integrates an EfficientNet-B4 backbone with multi-scale attention fusion and a geriatric severity-aware classification head to enable accurate GI polyp segmentation and automated clinical risk stratification from endoscopic images. Patients identified as high-risk are referred to colonoscopy-capable centers; such centers typically offer diagnostic colonoscopy with polypectomy capability for smaller and intermediate-complexity polyps, while patients with larger, sessile, or morphologically complex lesions requiring advanced endoscopic resection (e.g., endoscopic mucosal resection or endoscopic submucosal dissection) are further referred to tertiary endoscopy centers with specialized expertise. The model was trained and evaluated on the publicly available HyperKvasir dataset (1000 annotated polyp images). Results: GeriAIGastroNet achieved a classification accuracy of 96.77%, F1-score of 96.90%, Dice coefficient of 89.18%, and Intersection over Union (IoU) of 80.80%, outperforming established baselines, including U-Net, Attention U-Net, TransUNet, and Hybrid CNN-Transformer architectures. The integrated tele-gastroenterology decision support layer enables severity-based patient triage and automated referral triggering. Conclusions: These results demonstrate the potential of AI-powered polyp analysis to strengthen equitable access to GI care by facilitating risk stratification and specialist referral in HPSAs where direct endoscopy is unavailable, making the system deployable in telehealth infrastructures serving underserved elderly populations. Full article

Background: Detection of colorectal cancer (CRC) currently relies mainly on invasive procedures such as colonoscopy. In experimental models, tumor hypoxia induces epigenetic, metabolic, and immune changes via hypoxia-inducible factor (HIF) signaling. Building on these published insights, this study evaluated whether a panel of biomarkers previously associated with hypoxia-related processes, plasma methylated SEPT9 (mSEPT9), urinary N¹, N¹²-diacetylspermine (DiAcSpm), and systemic inflammatory indices (NLR, PLR, and LMR)—could be combined into a non-invasive diagnostic panel and compared with standard serum tumor markers. This study focused solely on diagnostic performance; it did not directly assess tumor hypoxia or HIF expression in patients. This study was conducted in a clinical diagnostic setting (patients with confirmed CRC, polyps, or benign surgical conditions) and does not represent a population-based screening cohort. Limitations include the lack of an external validation cohort; all analyses were performed on a single dataset, and the reported performance metrics may be optimistic. Independent validation is required before clinical implementation. Methods: This prospective single-center study enrolled 382 participants: 142 with CRC, 62 with colorectal polyps, and 178 non-malignant controls. Plasma mSEPT9 was quantified by real-time PCR, urinary DiAcSpm by ELISA, and inflammatory indices from blood counts. Serum tumor markers (CEA, CA19-9, CA125, and AFP) were measured by immunoassay. Diagnostic accuracy was assessed using ROC analysis and multivariable logistic regression. Results: mSEPT9 (AUC 0.843) and DiAcSpm (AUC 0.831) demonstrated significantly higher diagnostic accuracy than CEA (AUC 0.660) and CA19-9 (AUC 0.649). A combined panel including mSEPT9, DiAcSpm, NLR, PLR, and LMR achieved an AUC of 0.947, with 85.9% sensitivity and 92.9% specificity. This panel also showed strong performance for early-stage CRC (AUC 0.905). Conclusions: A multimarker panel of biomarkers (mSEPT9, DiAcSpm, NLR, PLR, and LMR) provides a non-invasive diagnostic approach for CRC detection in a clinical case–control setting. Validation in asymptomatic screening populations is required before any screening claim can be made. These findings are associative; direct evidence that tumor hypoxia drives these biomarker changes was not obtained and requires future investigation. Full article

Background/Objectives: Accurate pT1b diagnosis in colorectal cancer is vital owing to the risk of lymph node metastasis. While Japan NBI (narrow band imaging) Expert Team (JNET) classification is widely applied, accurate diagnosis of type 2B lesions remains challenging, often requiring pit pattern analysis via magnifying chromoendoscopy with crystal violet staining (MCE). However, the clinical application of MCE is limited by potential carcinogenicity and prolonged procedure time. In this study, we aimed to evaluate the diagnostic performance of red dichromatic imaging with indigo carmine (RDI-indigo) in assessing the invasion depth of colorectal tumors. Methods: Ninety images were obtained from 30 colorectal tumor cases using RDI-indigo, NBI, and MCE. Six endoscopists classified images using JNET classification for NBI, and pit pattern classification for RDI-indigo and MCE. JNET type 3 and pit pattern classification V irregular, high grade/V non-structure were correlated with pathological depth ≥pT1b. The primary outcome was the diagnostic accuracy for ≥pT1b. Results: Diagnostic accuracies for ≥pT1b were 85.0% (95% CI: 79.8–90.2%) for RDI-indigo, 79.4% (95% CI: 73.5–85.3%) for NBI, and 82.8% (95% CI: 77.3–88.3%) for MCE. Intraobserver agreement between RDI-indigo and MCE showed fair agreement (Cohen’s kappa = 0.39), while interobserver agreement was moderate for MCE (Fleiss’ kappa = 0.56) and fair for RDI-indigo (Fleiss’ kappa = 0.36). Gwet’s AC1 indicated substantial agreement across all assessments (0.69–0.80). Conclusions: As the first report evaluating RDI-indigo for colorectal tumors, this study suggests that RDI-indigo could serve as a complementary MCE-like tool for the diagnosis of ≥pT1b lesions. Full article

Background/Objectives: The incidence of early-onset colorectal cancer is increasing worldwide. The fecal immunochemical test (FIT) is widely used for screening adults aged 50 and older, but its performance in younger individuals is less understood. Methods: We retrospectively analyzed 202,676 FITs from asymptomatic adults aged 18–49 between 2011 and 2025. FIT results, age categories, and follow-up colonoscopy findings were evaluated. Results: The FIT positivity rate was 4.7%. Among 1973 FIT-positive individuals who underwent colonoscopy, 5.9% had advanced adenoma or sessile serrated lesion and 1.3% had invasive cancer. A total of 143 advanced neoplasms (ANs) were detected, with prevalence increasing with age. Most ANs (79.1%) occurred in those aged 40–49. The prevalence of ANs was higher in the 45–49 than in the 40–44 age group (49.0% vs. 30.1%; OR 1.55, 95% CI 1.04–2.32) and higher in the 40–44 than in the 35–39 age group (30.1% vs. 10.5%; OR 2.20, 95% CI 1.20–4.02). Conclusions: The diagnostic performance of FIT in individuals under 50 years is comparable to that observed in the older population. Given the age-related rise in the prevalence of ANs in young adults, several countries have lowered the screening age to 45 years, and extending screening to individuals aged 40 years may be warranted. Full article

Colorectal cancer (CRC) is responsible for a high cancer burden and a high number of deaths all over the world, although effective screening can make it preventable to a significant extent. Stool-based tests, such as the fecal immunochemical test (FIT) and multitarget stool DNA (mt-sDNA) testing, are gaining considerable popularity as non-invasive procedures that can be a replacement for colonoscopies for people at an average risk for colon cancer. Despite evidence from several randomized controlled trials supporting the use of these tests for colorectal cancer screening, their external validity in a real-world setting is influenced by many factors such as adherence, timely follow-up post testing, the healthcare cost burden, accessibility and the capacity of the health system. In this article, we have performed an extensive narrative literature review of research published between 2020 and 2025 comparing FIT and the mt-sDNA test with reference to diagnostic accuracy, cost-effectiveness, adherence and outcomes of implementation. We discuss the issues of sensitivity and specificity, look at post-test requirements for colonoscopy and check if there is any discrimination in healthcare. These findings suggest that FIT and mt-sDNA tests should not be considered competing technologies but rather complementary screening methods, with their overall effectiveness contingent upon appropriate patient selection and widespread system-level implementation. It is crucial to combine strategic test selection with a robust follow-up infrastructure to ensure that the entire population benefits from the CRC prevention program. Full article

Background/Objectives: Colorectal cancer (CRC) represents a major cause of cancer-related morbidity and mortality worldwide, particularly in regions with delayed or incomplete implementation of population-based screening programs. Evidence describing the burden and characteristics of colorectal lesions detected through organized screening initiatives in Eastern Europe is still limited. Methods: This retrospective study analyzed data from a regional CRC screening program conducted between November 2020 and December 2023 in South-West Oltenia, Romania. A total of 1550 individuals aged 50–74 years underwent colonoscopic evaluation following fecal immunochemical testing or direct referral based on risk assessment. Lesion characteristics, including size, anatomical distribution, histopathological subtype, dysplasia grade, tumor differentiation, and resection margin status, were systematically analyzed. Associations between demographic variables and lesion characteristics were evaluated using appropriate statistical methods. Results: At least one colorectal lesion was identified in 63.7% of colonoscopies, with a total of 5001 lesions detected. Most lesions measured <10 mm. Serrated lesions (51.4%) and conventional adenomas (42.2%) predominated, while invasive adenocarcinoma was identified in 6.2% of cases. Increasing lesion size was significantly associated with higher-grade dysplasia, incomplete resection margins and advanced histopathological features (p < 0.05). Age showed significant associations with histopathological subtype and resection margin status, whereas male sex was linked to higher-grade dysplasia and adenocarcinoma (p < 0.05). Conclusions: This study revealed a relatively high prevalence of precancerous and malignant colorectal lesions in a previously unscreened population. The strong associations between lesion size, dysplasia severity, and resection completeness underscore the importance of early detection and quality-controlled colonoscopy. These findings support the expansion of organized CRC screening programs and the integration of quality indicators to enhance diagnostic accuracy. Full article

Colonoscopy polyp segmentation is important for colorectal cancer screening, yet it remains challenging because polyps exhibit large morphological variation, weak lesion–background contrast, blurred boundaries, and severe foreground–background imbalance. To address these issues, this paper presents MCM-UNet++, a hybrid U-Net++-based segmentation framework that combines three targeted enhancements. First, a Multi-Axis Transformer Block (MATransformerBlock) is incorporated into convolutional feature blocks to model long-range horizontal and vertical dependencies with lower complexity than dense global self-attention. Second, a Cross-Channel Mixing (CCM) module is used in nested skip fusion paths to recalibrate the channel and spatial responses and reduce redundant feature transmissions. Third, a Multi-Objective Adaptive Loss (MOALoss) combines focal, Dice, and boundary-aware terms with learnable weights to improve supervision for small regions and ambiguous boundaries. Experiments on four public polyp segmentation datasets (Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, and ETIS-Larib) show competitive performance against the selected baseline methods, with Dice/IoU scores of 0.9563/0.9278 on Kvasir-SEG and 0.8593/0.7896 on CVC-ColonDB. These results indicate that the proposed components can improve benchmark-level polyp segmentation performance, while broader validation is still required before clinical deployment. Full article

Colorectal cancer is the third most commonly diagnosed cancer worldwide, and early detection of polyps via colonoscopy is essential for improving patient survival. However, automatic polyp segmentation faces three key challenges: balancing global context with local detail, delineating ambiguous boundaries under low contrast, and handling large variations in polyp size and morphology. To address these challenges, we propose WMA-Net, a Wavelet-Guided Mamba-Attention Network that uses wavelet-domain semantic–boundary separation as the organizing design principle. Rather than introducing a new individual operator, the contribution lies in how existing components—wavelet decomposition, Mamba state space modeling, multi-directional pixel difference convolution, and uncertainty-aware reverse attention—are combined and coordinated within one boundary-aware framework. The architecture integrates pixel difference convolution for multi-directional edge detection, frequency-selective cross-scale fusion with dual-stream wavelet-domain processing, Mamba-based multi-scale aggregation with linear complexity, and uncertainty-aware progressive boundary refinement. Extensive experiments on five public polyp benchmarks demonstrate state-of-the-art performance on four out of five datasets. On the seen datasets, WMA-Net achieves mean Dice scores of 94.4% on CVC-ClinicDB and 93.6% on Kvasir-SEG. On the unseen datasets, WMA-Net attains 91.7% on CVC-300, 82.3% on CVC-ColonDB, and 83.8% on ETIS-LaribPolypDB, demonstrating robust cross-dataset generalization. Comprehensive ablation studies validate the effectiveness and synergy of each proposed module. Full article

In terms of the detection of colorectal polyps during a colonoscopy, the accuracy of the diagnosis is key to effective prevention and treatment, and can be hindered by manual identification. Colorectal polyps are abnormal tissue growths in the colon or rectum, and their sizes, shapes and textures can make them difficult to find. Researchers have now turned to deep learning techniques and the YOLOv11 detection framework in particular to provide a method to automate the recognition and accurate identification of these abnormal growths. Specifically, the proposed method modifies the conventional YOLOv11 detection workflow by generating bounding box annotations from polyp segmentation masks, applying region-aware data preprocessing and augmentation, and training the detector under region-guided supervision to enhance localization precision and detection robustness. polyp segmentation masks are utilized to generate bounding box annotations which not only contribute exact spatial supervision but also avoid manual box labeling inconstancy. Region-aware data preprocessing and augmentation pay more attention to polyp-relevant regions and suppress background noise, which leads to clearer feature discrimination for small or irregular polyps. Additionally, region-guided supervision serves as explicit guidance for localizing objects with the anatomical polyp regions, which largely helps achieve accurate boundaries and prevent false detections. The proposed YOLOv11-based polyp detection system was tested and evaluated on the publicly available Kvasir-SEG dataset, which is comprised of annotated colonoscopy images. Enhanced data pre-processing and exhaustive training with appropriate choice of hyper-parameters fortified the reliability and useability of the model. The results confirmed high-grade results, and gave an Intersection over Union score of 0.9764, and an overall correctness rate of 99.00%, with well-balanced precision, recollection and F1-scores. Coming in with a mean Average Precision (mAP) of 0.9937 at a Intersection over Union threshold of 0.5 and 0.9935 over the full spectrum of thresholds from 0.5 to 0.95, this shows that the model is able to consistently and reliably detect polyps. The proposed system was also compared with Segment Anything Model, YOLO-Seg, and SAM2 and confirmed the efficacy of its method. Full article

Background and Clinical Significance: Cutaneous paraneoplastic phenomena are infrequently characterised in colorectal cancer (CRC), and chronic pruriginous inflammatory eruptions in particular have received limited attention. In older adults, persistent treatment-resistant dermatoses of unclear aetiology may represent overlooked extraintestinal diagnostic clues to occult malignancy, including potentially curable CRC. Faecal immunochemical testing (FIT) for occult bleeding is a low-cost, non-invasive tool whose role outside conventional alarm-symptom triage remains underexplored. Case presentation: A 72-year-old woman presented for outpatient evaluation with several months of pruriginous, pustular, and crusted symmetric eruption involving the dorsal aspects of the limbs, refractory to standard dermatologic treatment, and without gastrointestinal symptoms. A non-invasive systemic stool-based work-up demonstrated detectable faecal haemoglobin (iFOBT), mildly elevated faecal calprotectin (51.6 mg/kg, ULN 50 mg/kg), markedly elevated faecal alpha-1-antitrypsin (631 µg/mL; 2.3× ULN), and predominance of Escherichia coli on stool culture. Colonoscopy revealed a locally advanced rectal adenocarcinoma; staging classified the lesion as cT3N1M0. The patient received long-course neoadjuvant chemoradiotherapy (50 Gy, concurrent capecitabine) followed by low anterior resection with total mesorectal excision and pathological complete response (ypT0N0, R0), and adjuvant capecitabine. The cutaneous eruption resolved progressively in parallel with antineoplastic therapy without specific dermatologic intervention. The patient remains in remission at over 36 months. Conclusions: Persistent, unexplained, treatment-resistant pruriginous/pustular cutaneous eruptions may, in selected patients, coincide with an underlying malignancy, including colorectal cancer, and should prompt careful individualised clinical assessment, including review of age-appropriate colorectal cancer screening status. This single case raises the hypothesis that quantitative faecal immunochemical testing (FIT) may be prospectively evaluated as a low-cost, non-invasive triage tool in carefully selected patients aged ≥50 years with persistent dermatoses of unclear aetiology, even in the absence of gastrointestinal symptoms. Positive FIT results should be managed according to established local colorectal referral pathways. NICE diagnostics guidance DG56 supports FIT use in symptomatic adults with suspected lower gastrointestinal pathology; however, any extension of FIT to extraintestinal presentations remains investigational and requires formal validation through prospective studies assessing diagnostic yield, cost-effectiveness, and stage distribution. Full article

Background: Persistent histologic inflammation may remain present in patients with inflammatory bowel disease (IBD) despite endoscopic remission. This study evaluated a clinically interpretable cytokine-based framework for risk stratification of residual histologic activity. Methods: In this prospective cohort study, 59 patients with IBD undergoing colonoscopy were included. Primary analyses were restricted to patients with ulcerative colitis (UC) in endoscopic remission (n = 31). Histologic activity was assessed using the Geboes score. Serum interleukin-10 (IL-10), interleukin-23 (IL-23), and C-reactive protein (CRP) were measured prior to endoscopy. Receiver operating characteristic (ROC) analysis and ROC-derived thresholds were used to evaluate biomarker performance and construct a cytokine-based risk stratification framework. Results: Among patients with UC in endoscopic remission, 14/31 (45.2%) demonstrated persistent histologic activity. IL-10 showed the strongest discriminatory performance for histologic activity (AUC 0.850), with a threshold < 3.9 pg/mL associated with sensitivity of 84.6% and specificity of 77.8%. Similar performance was observed using raw assay-reported IL-10 values (AUC 0.906). IL-23 showed limited overall discrimination (AUC 0.615). A combined IL-10/IL-23 framework stratified patients into progressively higher-risk subgroups, with histologic activity observed in 1/14 patients (7.1%) in the low-risk subgroup, 1/2 patients (50.0%) in the Intermediate A subgroup, 9/12 patients (75.0%) in the Intermediate B subgroup, and 3/3 patients (100%) in the high-risk subgroup (p < 0.001), although estimates for smaller subgroups should be interpreted cautiously. Reduced IL-10 levels were independently associated with histologic activity, whereas IL-23 primarily refined subgroup classification without substantially improving discrimination. Conclusions: An exploratory cytokine-based framework incorporating IL-10 and IL-23 may support risk stratification of residual histologic activity in UC during endoscopic remission. Larger multicenter studies are required to validate these findings and define their clinical utility. Full article

Introduction: Obesity and colorectal cancer risk relationship is well-documented and bariatric surgery has become one of the most common surgical operations for losing weight. There is no guideline suggestion for the candidates of bariatric surgery for routine screening of colorectal cancer. The aim of this systematic review is to evaluate the place and necessity of screening colonoscopy before weight loss surgery under the light of published articles. Methods: A systematic literature review was conducted in accordance with PRISMA guidelines using electronic databases of PubMed and Google Scholar. The protocol was registered in the International Platform of Registered Systematic Review and Meta-analysis Protocols (INPLASY; registration number: INPLASY202630078). No restrictions were applied regarding the publication dates of the articles. We performed the PRISMA guidelines for systematic review and the PICOS framework was employed. Results: A total of 623 patients, 365 women and 258 men, underwent routine colonoscopy before bariatric surgery in three cohort studies. The average age and body mass index of the patients were 47.4 ± 10.4 (range 14–87) and 43.7 ± 7.1 kg/m², respectively. A total of 57 (9.1%) histologically confirmed pathologies were found during colonoscopy, 51 adenomatous polyps (8.1%) and six (1.0%) colorectal cancers. Five of the six CRC patients (83%) were over 45 years of age and three (50%) of them were over 60 years of age. Conclusions: The decision to screen bariatric surgery candidates for colorectal cancer should be individualized, based on age (≥45 years), family history, symptomatology, and comorbidities (inflammatory bowel disease). Bariatric surgeons should strongly consider colorectal cancer screening as part of preoperative workup in eligible patients. Full article

Background and Objectives: Bowel bubble formation during colonoscopy can impair mucosal visualization and reduce procedural efficiency. However, its clinical significance remains incompletely characterized. This study aimed to evaluate the prevalence of severe bowel bubbles in the proximal colon and their impact on colonoscopic quality in patients undergoing bowel preparation with oral sulfate solution (OSS), using either a same-day regimen (SAR) with 480 mL OSS or a split-day regimen (SPR) with 960 mL OSS. Methods: This retrospective study was conducted between October 2024 and December 2025 across two affiliated institutions. Patients who underwent colonoscopy with OSS-based bowel preparation were included. SAR was used for screening, symptomatic evaluation, and surveillance colonoscopy. SPR was applied exclusively to patients with a prior history of sodium picosulfate-related abdominal pain or inadequate bowel preparation with SAR. Sodium picosulfate was prescribed on the day before colonoscopy in the SAR group and a low-residual diet was administered in both the SAR and SPR groups. The prevalence of severe bubbles in the proximal colon was evaluated, and their impact on colonoscopic quality was examined. Results: A total of 176 SAR cases and 51 SPR cases were analyzed. The rate of severe bubbles in the proximal colon was identical between both regimens (17.6%). Compared with cases without severe bubbles, those with severe bubbles had significantly longer cecal insertion times (median [IQR]: 7.0 [5.0–10.0] vs. 9.0 [7.0–13.0] min, p = 0.018) and total procedure time (20.0 [16.0–25.0] vs. 24.0 [19.0–30.0] min, p = 0.024). Preparation-to-colonoscopy time was also longer in cases with severe bubbles (5.0 [4.0–5.5] vs. 5.0 [5.0–6.0] h, p = 0.041). Adenoma detection rates were 73.2% in cases without severe bubbles and 67.5% in those with severe bubbles (p = 0.571). Conclusions: Severe bowel bubble formation tended to be associated with longer cecal insertion and total procedure times, and was more frequently observed with a longer preparation-to-colonoscopy interval. Full article

Colorectal cancer screening is challenged by variations in polyp morphology, indistinct polyp boundaries, and the high computational costs associated with current models. To address these issues, a lightweight medical image segmentation model, WCEDSAM, has been developed. WCEDSAM is based on a modified, compact version of MedSAM, which incorporates a Wavelet Transform-based component to extract and separate overlapping features at the pixel level. Additionally, a DSConv-ECA module is positioned before the ViT encoder to capture local features efficiently while reducing parameter count and enhancing inter-channel communication. Experimental results demonstrate that WCEDSAM achieves top performance on five public datasets, including Kvasir-SEG and CVC-ClinicDB, with 15.38 million parameters, achieving mean Dice (mDice) scores of 0.9383 on Kvasir-SEG and 0.9376 on CVC-ClinicDB. Cross-domain evaluations yield mDice scores of 0.9189 on CVC-ColonDB, 0.8961 on CVC-300, and 0.7765 on ETIS datasets, respectively, substantially outperforming other methods such as UNet++ and TransUNet. Full article

Background: Terminal ileal ulcers (TIUs) are frequently identified during colonoscopy but are often attributed to nonspecific etiologies, potentially delaying the diagnosis of Crohn’s disease (CD). This study aimed to evaluate the utility of TIU as an early diagnostic marker and to determine whether diagnosis at the isolated TIU stage impacts long-term surgical outcomes. Methods: In this single-center, retrospective cohort study, consecutive adult patients with TIU detected via colonoscopy over a 10-year period were analyzed. Patients were stratified into CD-TIU and non-CD-TIU cohorts based on longitudinal follow-up. Clinical, endoscopic, and laboratory parameters were compared. Long-term surgical outcomes of patients diagnosed at the isolated TIU stage (Montreal classification L1) were compared with those of patients with established ileocolonic disease (Montreal classification L3). Results: Of the 66 patients included in the final analysis, 18 (27.3%) were ultimately diagnosed with CD. Specific endoscopic features—including longitudinal or fissuring ulcers (50.0% vs. 6.3%, p < 0.001), ileocecal valve deformity (50.0% vs. 18.8%, p = 0.011), and increased ulcer dimensions (9.11 mm vs. 4.60 mm, p = 0.002)—were significantly associated with a CD diagnosis. Notably, patients diagnosed at the TIU stage (CD-L1) exhibited a significantly lower surgical rate compared to those with established ileocolonic disease (CD-L3) (5.6% vs. 70.2%, p < 0.001). Conclusions: TIU, particularly when characterized by longitudinal morphology or ileocecal valve involvement, constitutes a critical early manifestation of CD. Diagnosis at the isolated TIU stage is associated with a lower long-term surgical risk compared to established ileocolonic disease, likely reflecting the influence of disease phenotype. These findings underscore the imperative for meticulous endoscopic evaluation to identify early-stage disease. Full article