This pilot study will test a new imaging system that uses fluorescent dye and artificial intelligence (AI) during colonoscopy to measure how "leaky" the lining of the colon is in people with inflammatory bowel disease (IBD). The study will include 70 adults at 3 Canadian hospitals: 60 people with ulcerative colitis or Crohn's disease affecting the colon, and 10 people without IBD who are having colonoscopy for routine colorectal cancer screening or surveillance. During the colonoscopy, participants will receive intravenous fluorescein, and the imaging system will record fluorescence in the colon as the scope is withdrawn. The main goal is to find out whether this method can be used safely during routine colonoscopy and whether it can produce usable measurements of mucosal permeability. The study will also examine whether these measurements are related to standard measures of inflammation seen during endoscopy, in biopsy samples, and in ex vivo Ussing chamber testing at the McMaster site. The control group will help define what normal fluorescence and permeability look like. This study is intended to provide early data on whether this approach could become a useful new way to assess barrier dysfunction in IBD.
This multi-center pilot study will evaluate the feasibility, safety, and clinical relevance of an investigational AI-assisted wide-field fluorescence endoscopy system for assessment of colonic mucosal permeability in inflammatory bowel disease (IBD). The study will enroll 70 adults across 3 Canadian academic centers, including 60 patients with ulcerative colitis or Crohn's disease involving the colon who are undergoing clinically indicated colonoscopy, and 10 non-IBD controls undergoing routine colorectal cancer screening or surveillance. Impaired intestinal barrier function is an important feature of IBD, but current permeability tests do not provide direct, segment-specific, real-time information during colonoscopy. In this study, standard colonoscopy will be supplemented by intravenous fluorescein and fluorescence imaging during scope withdrawal, together with scope-position tracking and AI-assisted video analysis. The investigational system is designed to generate regional permeability measurements based on fluorescence leakage patterns along the colonic mucosa. The primary objective is to determine whether this imaging approach can be safely and feasibly integrated into routine colonoscopy and produce interpretable permeability data. Secondary objectives are to evaluate whether fluorescence-derived permeability measurements correlate with regional endoscopic disease activity, matched histopathology, and ex vivo Ussing chamber permeability measurements at the McMaster site. Non-IBD controls are included to provide reference fluorescence and permeability data for non-inflamed mucosa. This is a non-randomized, observational study in which all participants will undergo the same investigational imaging procedure in addition to standard care. The study is intended to generate preliminary data to support future trials of fluorescence-based permeability mapping as a tool for assessing mucosal barrier dysfunction in IBD.
Study Type
OBSERVATIONAL
Enrollment
70
This is an observational study, and participants are not assigned a therapeutic intervention as part of the research. All participants will undergo a clinically indicated colonoscopy as part of routine care. As part of the study procedures, colonoscopy will be supplemented with intravenous sodium fluorescein, wide-field fluorescence imaging during scope withdrawal, and AI-assisted video recording and analysis to assess mucosal permeability. In addition, targeted research biopsies will be collected from selected colonic regions for histologic assessment, and at the McMaster site a subset of biopsies will also undergo ex vivo Ussing chamber permeability testing.
• Feasibility of Procedure
• Feasibility of Procedure: The proportion of enrolled patients in whom the full fluorescence mapping procedure is successfully completed as intended. This will include metrics such as ability to intubate the colon and obtain fluorescence images from cecum to rectum; any significant technical difficulties encountered (and their nature); additional procedure time added by the imaging (in minutes); and whether the resulting fluorescence data was of analyzable quality. We will define success as achieving a usable permeability map of the colon surface. Feasibility will also be described by qualitative feedback from endoscopists on workflow integration.
Time frame: From enrollment to end of study = one patient visit
• Safety of the Imaging System
Incidence and severity of adverse events related to the investigational aspects (fluorescein and AI system). This includes any allergic reactions to fluorescein, any hemodynamic instability during the procedure attributable to the dye, any complications from prolonged procedure time (e.g. hypoxia from sedation), or any device malfunctions leading to patient risk. Adverse events will be categorized as mild, moderate, severe, and their relationship to the study intervention will be adjudicated. The primary safety endpoint is the absence of any Serious Adverse Effect. We hypothesize that the rate of serious complications will be \<5%, with the expectation of 0% severe allergic reactions in a 60 patient sample (based on fluorescein's known \<1/1000 severe reaction rate). We will specifically report the number of patients with any fluorescein-related reaction (and details if so).
Time frame: From enrollment to end of study = one patient visit
• Correlation with Endoscopic Severity:
We will assess whether fluorescence permeability at each biopsy site correlates with endoscopic inflammation in that same anatomical region. Fluorescence metrics (e.g., normalized peak intensity, number of leak foci) from each biopsy site - high-fluorescence and low-fluorescence regions - will be compared with the corresponding local endoscopic severity score (Mayo endoscopic subscore for UC; the segmental SES-CD subscore for CD). Because biopsies are obtained from specific marked locations rather than from every colonic segment, analyses will be performed at the biopsy-site level rather than the segment level. Correlation coefficients (Spearman or Pearson) will quantify the association between fluorescence signal and endoscopic activity. We will also compare mean fluorescence values between biopsy sites taken from endoscopically inflamed vs non-inflamed regions. Controls will typically score as non-inflamed (Mayo = 0; SES-CD = 0).
Time frame: From enrollment to end of study = one patient visit
• Correlation with Histopathology
Fluorescence permeability measurements at each biopsy site will be correlated with histologic inflammation scored using disease-appropriate indices (Nancy Index for UC; GHAS for CD and controls). Because each participant provides a paired set of biopsies (one high-fluorescence and one low-fluorescence site from the same anatomical region), comparisons will occur at the biopsy-site level. We will analyze: * correlation between fluorescence intensity and histology score across all biopsy sites * differences in histologic scores between high- and low-fluorescence sites within each participant * exploratory pooled analyses using a unified ordinal inflammation scale Controls are expected to score as non-inflamed on GHAS.
Time frame: From enrollment to end of study = one patient visit
• Correlation with Ussing ex vivo permeability (Performed at McMaster only)
For each participant, fluorescence metrics at the specific biopsy sites will be correlated with matched ex vivo ⁵¹Cr-EDTA flux from the same locations. Analyses will again be at the biopsy-site level. Additionally, we will perform within-patient gradient analysis, comparing the difference between high- and low-fluorescence sites: * Δ fluorescence (high - low) * Δ Ussing flux (high - low) A positive association between Δ fluorescence and Δ Ussing flux will indicate that higher in vivo leak corresponds to higher physiologic permeability.
Time frame: From enrollment to end of study = one patient visit
• Accuracy of AI Detection
Using the initial manual annotations and multidisciplinary review as the reference, we will calculate how accurately the AI algorithm identifies high-permeability regions. Metrics like sensitivity, specificity, and predictive values for AI-detected "leak sites" against human-identified or biopsy-proven inflammation sites will be reported. Including control participants (non-IBD) will help ensure that the AI model correctly identifies normal mucosa as low-permeability, improving specificity.
Time frame: From enrollment to end of study = one patient visit
• Inter-Observer Consistency
Although the AI provides an objective measure, we will check consistency by having multiple investigators review a subset of the fluorescence videos independently to mark obvious leak spots. The AI's output will be compared to each reviewer's marks (and reviewers to each other) to ensure the AI reduces inter-observer variability. High agreement would support reproducibility.
Time frame: From enrollment to end of study = one patient visit
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.