Introduction

Inflammatory Bowel Disease (IBD)^1,2 requires close monitoring to detect flare ups early and guide treatment. While endoscopy is the gold standard, it is invasive, costly, and uncomfortable^1,2. Intestinal Ultrasound (IUS) is a non-invasive alternative with strong correlation to endoscopic findings—especially bowel wall thickness (BWT), a marker of disease activity³. Nevertheless, IUS remains limited due to operator dependence and a steep learning curve⁴.
AI has improved consistency in other domains, e.g. endoscopic evaluation, but its application to IUS in IBD remains underexplored. Prior models lack interpretability and require manual image cropping, or are trained on ideal, selected data, limiting clinical use^5,6.

Aims & Methods

We aim to develop a deep-learning model that automatically identifies and paints the bowel wall and measures BWT directly from raw clinical IUS images.
A training dataset of 570 images from 144 IUS videos and a testing dataset of 55 images from 55 separate exams were created. All images were extracted from previously performed IUS examinations reflecting real-world variation, including e.g. unclear boundaries and artefacts.
All images were annotated by International Bowel Ultrasound Group (IBUS) certified experts, including outline-paintings of the inner and outer bowel wall and two BWT measurements.
The AI consists of a combination of Convolutional neural networks and other image processing algorithms.
Evaluation included BWT error against the expert mean, classification accuracy using the standard IBUS 3 mm threshold³, and a leave-one-out comparison with individual doctors.

Results

The model produced predictions on 54 of 55 test images.
The model deviated from the gold standard mean by 0.98 mm (SD 1.1 mm) per image on the regression task. The average distance to expert-defined bounds was 0.44 mm (SD 0.89 mm), with 59% of predictions inside this range.
For classification (using a 3 mm threshold), the model reached an accuracy of 0.77, sensitivity of 0.69, specificity of 0.94, and Cohen’s Kappa of 0.56.
In the leave-one-out analysis, expert performance ranged from 0.89–0.93 accuracy and 0.79–0.83 Kappa. Depending on which expert was excluded from the gold standard, the model achieved 0.74–0.80 accuracy and 0.49–0.60 Kappa. Experts stayed within expert-defined bounds in 72–81% of cases, while the model did so in 46–55%.

Conclusion

Clinically, the model performed well. An error of 0.5–1 mm is negligible in practice and matches typical variation in manual measurements. Many real-world test images had BWT values near the 3 mm threshold, so small deviations led to misclassifications. In practice, a 2.5 mm reading could still raise concerns based on symptoms³.
While the system alone cannot provide expert-level BWT measurements, it could provide assistance to experts as well as non-expert and junior doctors, especially in locating the bowel, which is an essential part of IUS.
The model works on unprocessed clinical data, with the only selection criteria being that there is an identifiable bowel segment, measurable by an IBUS-certified doctor. Allowing the images to reflect realistic conditions
In summary, we developed an AI model that identifies the bowel and measures BWT with acceptable accuracy. We have already started the processes of collecting video data, to extend the AI’s functionality to a fully clinical setting.

References

1. Torres J, Mehandru S, Colombel JF, Peyrin-Biroulet L. Crohn’s disease. The Lancet. 2017;389(10080):1741-1755. doi:10.1016/S0140-6736(16)31711-1
2. Ungaro R, Mehandru S, Allen PB, Peyrin-Biroulet L, Colombel JF. Ulcerative colitis. Lancet. 2017;389(10080):1756-1770. doi:10.1016/S0140-6736(16)32126-2
3. Novak KL, Group I, Nylund K, et al. Expert Consensus on Optimal Acquisition and Development of the International Bowel Ultrasound Segmental Activity Score [IBUS-SAS]: A Reliability and Inter-rater Variability Study on Intestinal Ultrasonography in Crohn’s Disease. J Crohns Colitis. 2021;15(4):609-616. doi:10.1093/ECCO-JCC/JJAA216
4 Bove L, Meyer J, Collins M, Frampas E, Bourreille A, Le Berre C. Understanding the learning curve of intestinal ultrasound in inflammatory bowel disease: A comparative study between novice, regular, and expert. Clin Res Hepatol Gastroenterol. 2025;49(3):102548. doi:10.1016/J.CLINRE.2025.102548
5. Kumaralingam L, Le May K, Dang VB, Alavi J, Huynh HQ, Le LH. Artificial intelligence-assisted approach to assessing bowel wall thickness in pediatric inflammatory bowel disease using intestinal ultrasound images. J Crohns Colitis. 2025;19(4). doi:10.1093/ECCO-JCC/JJAF037
6. Carter D, Albshesh A, Shimon C, et al. Automatized Detection of Crohn’s Disease in Intestinal Ultrasound Using Convolutional Neural Network. Inflamm Bowel Dis. February 2023:1-6. doi:10.1093/IBD/IZAD014

Introduction

Histological assessment in Inflammatory Bowel Disease (IBD) is often required with endoscopic diagnoses to establish disease activity. This is evident in patients where histological healing is a major therapeutic goal and when endoscopic healing can also exhibit microscopic disease. IBD can manifest in numerous landmark features which are structural and inflammatory related. Histological activity is determined through erosion/ulceration, architectural changes in tissue morphology, mucin depletion and presence of varied inflammatory cells the colonic crypts, Muscularis Mucosae (MM) and Lamina Propria (LP). Histological scoring systems vary in complexity and methodology and subject to discrepancies in inter-rater consensus. Our model aims to provide accurate measurements of key histological features in Ulcerative Colitis (UC) used in scoring systems as both a decision support tool for improving pathologist scoring alignment and sensitive quantitative metrics of inflammatory cells to evaluate disease activity.

Aims & Methods

We developed an ensemble of convolutional neural networks to identify cell types, tissue foreground, crypts, MM, and haemorrhage in H&E images of IBD biopsy data. Models were trained with expert-labelled annotations comprising 34,289 image-annotation pairs (80% training, 20% validation) from in-house and publicly available data. Model accuracy was assessed with 6,464 held-out image-annotation pairs from 26 Whole Slide Images (WSIs) from all sites of the large intestine commonly sampled during endoscopic investigation, while ground truth annotations were reviewed by GI-trained pathologists to certify accuracy. We used geospatial methods to derive boundaries of the LP from other predicted domains, associate cells to delineated regions, measure architectural changes and derive spatially differentiated metrics of inflammatory burden in 66 patients with confirmed UC.

Results

The AI model spatially differentiates and segments cell types and tissue compartments. This produces metrics for inflammatory cell counts in regions of interest such as crypts, LP, and MM. Goblet cell segmentation within crypts allows for measurement of mucin depletion. This can be visualized for pathologists where each inflammatory cell type across the WSI is represented as density metrics. Automated quantification of inflammatory cells across AI-identified tissue domains throughout the bowels of UC patients revealed large intra- and inter-patient variability.

Conclusion

Our AI model can measure histological healing by detecting architectural change, inflammatory cell number, goblet cell reduction and erosions and ulceration. This allows for metrics and visual overlays to assist with pathologist reading and quantifying changes in mucosal biopsies in a clinical trial setting which requires extremely sensitive tools only AI can provide.

Disclosure

DW/AM/RL/PA/PW and CL are employees at Perspectum Ltd. EF and RG are consultants for Perspectum Ltd. All other co-authors have no conflicts of interest to declare relevant to this work.

Introduction

Crohn's disease is characterized by patchy, transmural inflammation predominantly affecting the ileum and colon. Ileo-colonoscopy remains the gold standard for assessing mucosal inflammatory activity in clinical trials, and can be quantified using the Simple Endoscopic Score for Crohn’s Disease (SES-CD). However, ileo-colonoscopy is invasive, therefore there has been growing interest in non-invasive imaging modalities such as magnetic resonance imaging (MRI). The Simplified Magnetic Resonance Index of Activity (sMaRIA) is an MRI-based score which provides a standardised approach for evaluating disease activity. Most previous studies investigating the correlation between sMaRIA and SES-CD have been single centre studies with limited numbers of readers and performed only in patients with longstanding disease. While MRI is superior to colonoscopy for assessment of transmural penetrating and stricturing disease, the performance of sMaRIA for assessment of mucosal activity in the post-treatment setting remains unanswered.

Aims & Methods

To evaluate the performance of sMaRIA for detection of mucosal inflammation in patients with recently diagnosed Crohn’s disease using ileo-colonoscopy and SES-CD as the reference standard. We conducted a post-hoc analysis of the PROFILE trial, in which patients had undergone paired ileo-colonoscopy and small bowel MRI at end of trial (week 48). Central reading was performed by validated pools of consultant radiologists (MRI) and gastroenterologists (ileo-colonoscopy), blinded to clinical data. Correlations between SES-CD and sMaRIA scores were assessed, alongside classification performance and remission rates by treatment arm. For this study endoscopic and MRI remission were respectively defined as SES-CD ulcer subscore <1 and sMaRIA ulcer subscore of 0.

Results

253 patients had paired ileo-colonoscopy and MRI at end of trial with a median time gap of 22 days between investigations and no treatment change over this period. The overall correlation between SES-CD and sMaRIA scores at week 48 was poor (Spearman’s rank=0.196). [KS(UHNFT1] Overall sMaRIA had low sensitivity (27%) [NN2] for identifying active inflammation evident on ileo-colonoscopy. On segmental analysis MRI detected only 4/146 ulcerated segments (SES-CD ulcer subscore >0). Focusing on patients with ileal involvement, terminal ileal ulcer subscores also showed low correlation (Spearman’s rank=0.11). When using the mucosal component of MRI / sMaRIA to assess ulcer-free remission, no difference in end of trial outcomes was observed for “top-down” vs “accelerated step-up” treatment groups (95% vs 96% remission, p=0.728). Rates of ulcer-free remission assessed by SES-CD were different between treatment groups (86% vs 71% remission, p=0.004).

Conclusion

In this cohort of recently-diagnosed patients with Crohn’s disease and predominantly inflammatory disease phenotype, sMaRIA showed low sensitivity for detecting mucosal inflammation / ulceration. Had sMaRIA been used instead of SES-CD in the PROFILE trial it would have failed to identify the benefit of the “top-down” treatment strategy. These findings suggest that sMaRIA on MRI should not replace SES-CD scoring on ileo-colonoscopy for assessing mucosal inflammatory activity in Crohn’s disease.

References

A biomarker-stratified comparison of top-down versus accelerated step-up treatment strategies for patients with newly diagnosed Crohn's disease (PROFILE): a multicentre, open-label randomised controlled trialNoor, Nurulamin MNoor, Nurulamin et al.
The Lancet Gastroenterology & Hepatology, Volume 9, Issue 5, 415 - 427

Introduction

Paneth cells (PC) are involved in the regulation of intestinal microbiota, and their function in intestinal lymph- and angiogenesis has been recently described. Uptake of dietary lipids is largely dependent on intestinal lymphatic vessels, and impairments in their density or function may result in significant depletion of lipids in the liver. In this study, we assessed the effects of PC deficiency in a model of metabolic dysfunction associated steatotic liver disease (MASLD).

Aims & Methods

We induced functional inactivation of PC in male and female mice (Sox9^lox/loxVilCre^ERT2) by intraperitoneal injection of 1mg/day of tamoxifen for three consecutive days. One week later, all mice, PC-deficient, and control littermates were randomly subjected to a high sucrose/fructose - high fat (60% lard) (HFD) or standard (SD) diet for 16 weeks. Intraepithelial leakage of FITC-albumin was measured in vivo using laser-probe endomicroscopy. Several tissues were harvested for histological examination, molecular biology analyses, and imaging mass cytometry (IMC). Fecal samples were collected at both the start and end of the experiment to assess intestinal dysbiosis and fecal fat content.

Results

All mice fed HFD gained weight compared to SD, but the weight gain in PC-deficient-HFD was significantly lower than in HFD-controls. Consistent with these findings, the severity of hepatic steatosis was significantly lower in PC-deficient mice compared to HFD-control. IMC of liver tissue revealed lower levels of collagen deposition and steatosis associated with fewer macrophages and neutrophils activation/infiltration in PC-deficient-HFD than in control-HFD mice. In vivo, microscopy showed a lower disruption of intestinal vascular barriers in PC deficient-HFD mice than in HFD controls. The intestinal expression of distinct lymphangiogenic genes (VEGFC, VEGFR3, Prox1) was reduced in the PC-deficient HFD or SD. Moreover, PC-deficient-HFD showed a higher level of fecal fat excretion than HFD controls. The alpha diversity of the fecal microbiota showed no significant differences based on gender or PC deficiency in the SD groups. Nevertheless, the beta diversity showed significant differences in PC-deficient fed SD after 16 weeks. Furthermore, we found significant alpha- and -beta diversity associated with decreased Bacteroidota and increased Firmicutes in HFD and PC-deficient mice.

Conclusion

PC deficiency attenuated the severity of steatosis and fibrosis in mice, suggesting their regulatory role on intestinal lymphatics contributing to the pathogenesis of MASLD. Thus, Paneth cells may represent a novel target for intervention in MASLD.