Introduction

Automated identification and discrimination of individual colorectal polyps through artificial intelligence (AI) is a crucial step towards the development of colonoscopy report generation systems. The basic information of a colonoscopy report should contain the total number of identified polyps and characteristic images of the polyps, which will determine the follow-up time and treatment. However, there is no widely adopted solution to accomplish this task.

Aims & Methods

In this study, we propose an AI-based pipeline for automatic individual polyp identification and retrieval of corresponding polyp images to simplify and accelerate colonoscopy report generation. A pipeline consisting of a Siamese Twin Neural Network and a hierarchical density-based spatial clustering method was implemented for individual polyp identification and discrimination. The AI model was trained and validated using frames containing polyps which were extracted from 549 and 61 full-length colonoscopies videos respectively, recorded in 7 different endoscopy centers. The pipeline was tested on frames containing a total of 29 different polyps extracted from 10 colonoscopies. The evaluation metrics were two measures to estimate the quality of clustering ranging from 0 (no correlation) to 1 (perfect correlation): normalized mutual information (NMI) and adjusted rand index (ARI). Additionally, we calculated the precision of corresponding individual polyp images.

Results

Testing on frames with visible polyps obtained from 10 colonoscopy examinations demonstrated that the pipeline achieved an NMI of 0.862 and an ARI of 0.835, indicating that at least 80% of the data can be accurately clustered and identified. The average precision was 0.763, representing the probability of retrieving the correct and corresponding individual polyp images.

Conclusion

We have developed a pipeline that uses artificial intelligence techniques to identify individual polyps and retrieve representative polyp images. These approaches have the potential to simplify and accelerate the process of automatically generating a colonoscopy report, while also providing characteristic images for each detected polyp for future use.

Introduction

Biologic and small-molecule therapies are widely used for ulcerative colitis (UC), but their comparative effectiveness in TNF-exposed patients remains unclear.

Aims & Methods

This study evaluates the clinical and biomarker responses to Vedolizumab, Tofacitinib, and Ustekinumab over 12 months, adjusting for baseline differences using Inverse Probability of Treatment Weighting (IPTW). A multicenter retrospective cohort of TNF-exposed UC patients treated with Vedolizumab (n = 260), Tofacitinib (n = 149), or Ustekinumab (n = 193) was analyzed. Clinical outcomes, including Partial Mayo Score (pMayo), clinical remission, and biomarker response (CRP, ESR, fecal calprotectin), were assessed at baseline (T0), 8 weeks (T1), 24 weeks (T2), and 52 weeks (T3). IPTW balanced baseline characteristics, and longitudinal changes were analyzed using a repeated-measures general linear model (GLM) with post-hoc corrections for multiple comparisons.

Results

Before IPTW, significant baseline differences existed, with Tofacitinib patients being younger (p < 0.001), more frequently female (p = 0.003), and having higher fecal calprotectin levels (p = 0.005). After IPTW, covariate balance was achieved (SMD < 0.10). pMayo scores significantly declined in all treatment groups over time (p < 0.001, η² = 0.469), with no significant main effect of therapy (p = 0.329). A minor time-by-therapy interaction (p = 0.036, η² = 0.026) indicated slight response variations but lacked clinical significance. Before IPTW, Tofacitinib showed superior pMayo improvement versus Ustekinumab (p = 0.008), but this difference lost significance post-IPTW, suggesting baseline confounding. At 52 weeks, clinical remission was highest with Tofacitinib (57%), followed by Vedolizumab (40%) and Ustekinumab (22%) (p = 0.003). Biomarker remission favored Vedolizumab (48.8%) over Tofacitinib (19.5%) and Ustekinumab (21.2%) (p = 0.002). Adverse events were rare but more frequent with Vedolizumab (p < 0.001).

Conclusion

Over 12 months, all therapies significantly improved clinical and biomarker outcomes, with no significant differences in overall pMayo reduction post-IPTW. Tofacitinib achieved the highest clinical remission, while Vedolizumab demonstrated superior biomarker response. These findings highlight the need for individualized treatment selection in TNF-exposed UC patients.

Clinical Case Summary

Case 1: A 38-year-old male with stricturing ileocolic Crohn’s disease on adalimumab underwent a colonoscopy, which revealed active disease (SES-CD: 8) where biopsies were taken. The procedure was uneventful. However, the following day, he developed severe right upper quadrant (RUQ) pain, prompting emergency evaluation. He was afebrile but exhibited RUQ tenderness. Blood tests revealed leukocytosis (21.0×10⁹/L) and elevated CRP (4.26mg/dL). CT scan revealed pericolic fat stranding at the hepatic flexure extending to the gallbladder. Due to diagnostic uncertainty, observation with antibiotics was initiated. Clinical deterioration and worsening inflammatory markers led to an ultrasound, which confirmed an acute cholecystitis. Patient underwent laparoscopic cholecystectomy, revealing gangrenous cholecystitis with perforation. He was discharged on postoperative day 3 with full recovery.
Case 2: A 63-year-old female with a history of stricturing ileocolic Crohn’s disease (ileocecal resection in 2001) and ascending colon adenocarcinoma (right hemicolectomy in 2009) underwent a colonoscopy, which was uneventful. The next day, she developed RUQ pain and vomiting, prompting emergency evaluation. She was febrile with RUQ tenderness. Laboratory results showed leucocytosis (10.6×10⁹/L) and elevated CRP (9.11mg/dL). Ultrasound confirmed acute cholecystitis. She underwent urgent laparoscopic cholecystectomy and was discharged two days later without complications.
Conclusions: We report two cases of acute cholecystitis occurring within 24 hours of colonoscopy. Sixteen similar cases exist in the literature, most presenting within 72 hours¹. Crohn's disease activity does not appear to be a contributing factor, as one patient had no active inflammation. Proposed mechanisms include dehydration, bacterial translocation, trauma and inflammatory response². Finally, given the high frequency of colonoscopy and the prevalence of cholecystitis, a coincidental association cannot be excluded.

References

1. Neubeck KM, Mwagiru D, Boseto EF Acute cholecystitis following elective colonoscopy BMJ Case Reports CP 2023;16:e257166.
2. Shaikh D H, Kumar K, Patel H, et al. (October 10, 2020) Acute Cholecystitis, A Rare Complication Following Routine Colonoscopy: Case Series and Literature Review. Cureus 12(10): e10877.

Introduction

During the COVID-19 pandemic the British Society of Gastroenterology (BSG) introduced interim guidelines supporting a non-biopsy pathway for the diagnosis of coeliac disease. These guidelines reflect the current recommendations of the American Gastroenterological Association (AGA). According to these guidelines, symptomatic or high risk adults with anti-Tissue transglutaminase (TTG) IgA titres ≥10× the upper limit of normal (ULN) and a positive endomysial antibody (EMA) on a repeat sample can be diagnosed without endoscopy and referred directly to a specialist coeliac clinic. Patients who do not meet these criteria should be referred for a gastroscopy (OGD) with biopsy for the confirmation of coeliac, prior to starting a gluten free diet.

Aims & Methods

To assess whether general practitioners (GPs) in the community appropriately referred patients with suspected coeliac disease in line with the AGA and BSG interim non-biopsy diagnostic criteria.
A retrospective review was conducted of all new patients referred to the Coeliac clinic in Galway university hospital between January 2023 and December 2024. Data regarding TTG level at diagnosis, EMA result, and compliance with the diagnostic pathway outlined above was collected for each new referral. This data was collected via Evolve - the hospital's electronic based patient record system.

Results

• There were 119 “new” referrals to our Coeliac Service between January 2023 and December 2024. Of these, 44 cases were known coeliac who were referred by primary care for re-engagement with the clinic, 18 were referred from secondary or tertiary care including GI surgery, Dermatology, Paediatrics, etc. 4 coincidental diagnoses (i.e. OGD performed for indications other than coeliac disease), and 5 outliers (i.e. with incomplete data or incorrectly referred to coeliac clinic) leaving 48 new coeliac cases referred from primary care.
• 18 of these referrals met the non-biopsy criteria for diagnosis (TTG ≥100 + positive EMA)
  • Within this cohort 66% (n=12) were incorrectly referred directly for an OGD which may have delayed the diagnosis of coeliac disease while the remaining 33% (n=6) were correctly referred for direct review at the coeliac clinic.
• The remaining 29 patients all had TTG values less that 10x ULN. 48% (n=14) of these patients were incorrectly referred to clinic prior to endoscopy and of greater concern, 45% (n=13) were recommended by their primary care physician to start a gluten free diet prior to any review or endoscopic procedure.
• Overall, only 44% (n=21) of referrals were compliant with the AGA/BSG guidance.

Conclusion

There is a notable gap in adherence to AGA and BSG non-biopsy coeliac diagnostic guidance in community settings. Half of patients eligible for a non-biopsy diagnosis underwent unnecessary endoscopy, and the majority of ineligible patients were commenced on a gluten free diet prior to, or without, referral for endoscopy. Further GP education is warranted to align referral practices with evidence-based pathways. Dedicated streamlined referral pathways for coeliac disease should ensure a timely diagnosis without mandatory endoscopy in those fulfilling the criteria for a non-biopsy diagnosis and facilitate a timely endoscopy prior to gluten elimination in those who require histological diagnosis.

References

Husby, S., Murray, J.A. and Katzka, D.A. (2019) ‘AGA clinical practice update on diagnosis and monitoring of celiac disease—changing utility of serology and histologic measures: Expert review’, Gastroenterology, 156(4), pp. 885–889. doi:10.1053/j.gastro.2018.12.010.
Tashtoush, L.B. et al. (2021) ‘Letter: The BSG covid‐19 interim coeliac disease guidance no‐biopsy approach is safe in adults’, Alimentary Pharmacology &amp; Therapeutics, 54(8), pp. 1090–1092. doi:10.1111/apt.16553.

Disclosure

No conflict of interest