Introduction

A reduction of bowel wall thickness (BWT) on intestinal ultrasound (IUS) is an early predictor of endoscopic response in ulcerative colitis (UC).¹ Shear-wave elastography (SWE) may offer additional prognostic information.

Aims & Methods

We aimed to identify early IUS parameters predicting treatment response to filgotinib, a selective JAK-1 inhibitor. This prospective observational study included UC patients with endoscopically active disease starting on filgotinib 200 mg daily. IUS parameters, including SWE, were assessed at baseline (T0), week 4 (T1) and at second endoscopy (T2). The endoscopic Mayo score (EMS) was assessed at T0 and at T2 in both the most-affected segment and the sigmoid. Endoscopic response was defined as a decrease in EMS of at least 1 point.

Results

A total of 23 patients were included. 10 patients were female (10/23, 44%), the mean disease duration was 14.4 years (SD±10.4), and 14 patients (14/23, 61%) had failed 2 or more biologics. Endoscopic response was observed in 6 of the 21 patients (29%) who underwent a second endoscopy after a median of 14 weeks (IQR 12-17). The submucosal thickness in the sigmoid decreased significantly more between T0 and T1 in endoscopic responders compared to non-responders (-40±23.9% vs -11.5±24.5%, p=0.022). At T1, a BWT decrease of ≥1.33 mm or ≥24.7% (OR 32.5 [2.38-443.15], p=0.009 and OR: 13.8 [1.21-156.6], p=0.035) and a submucosal thickness decrease of ≥20.8% (OR: 13.8 [1.21-156.6], p=0.035) predicted endoscopic response at T2. Additionally, improvement in Colour Doppler Signal (CDS) at T1 predicted endoscopic response (OR: 20.0 [1.66-241.7], p=0.018). SWE values in the sigmoid at T0, T1 and T2 were not significantly different between endoscopic responders and non-responders in the sigmoid. While the change in SWE values at T2 compared to baseline was significantly different between the two groups (9.9± 11.5 kPa vs. -8.1 ± 11.4 kPa, p=0.002), the difference at T1 was not significant and did not predict endoscopic response in the sigmoid (OR: 1.07 [0.99-1.16], p=0.088).

Conclusion

On IUS, BWT, submucosal thickness and CDS predict endoscopic response after four weeks of filgotinib treatment. SWE values in the sigmoid changed differently among endoscopic responders and non-responders, but did not predict treatment response.

References

1. de Voogd FA et al. Early Intestinal Ultrasound Predicts Clinical and Endoscopic Treatment Response and Demonstrates Drug-Specific Kinetics in Moderate-to-Severe Ulcerative Colitis. Inflamm Bowel Dis 2023. DOI: 10.1093/ibd/izad274.

Disclosure

MP: none;
CT: none;
FV: received speaker’s fees from AbbVie, Pfizer and Takeda;
RJ: none,
ML: Consultancy/lecture fees from Abbvie, Bristol Myers Squibb, Eli Lilly, Galapagos, Janssen-Cilag, Johnson & Johnson, Medtronic, Pfizer, Takeda, Tillotts. Grants received from Alfasigma, NFU transformation deal, ZonMW and TKI.
RG: received speakers free from Janssen-Cilag BV and Pfizer Inc.
GD: has served as advisor for AbbVie, Abivax, Alimentiv,, Astrazeneca, Bristol Meiers Squibb, Boehringer Ingelheim, Celltrion, Eli Lilly, , GlaxoSmithKline, Johnson and Johnson, Merck Sharp Dome, Pfizer, Polpharm, Sanofi, Takeda, Tillotts, and received speaker fees from AbbVie, Eli Lilly, Johnson and Johnson, Merck Sharp Dome, , Pfizer, Takeda, Tillotts,.
KG: KB Gecse has received grants from AbbVie, Pfizer Inc, Celltrion and Galapagos; consultancy fees from AbbVie, Arena Pharmaceuticals, ImmunicTherapeutics, Janssen Pharmaceuticals, Novartis, Pfizer Inc., and Takeda and speaker’s honoraria from Abbvie, Celltrion, Eli Lilly, Ferring, Janssen Pharmaceuticals, Pfizer Inc, Takeda and Tillotts.

Introduction

Accurate diagnosis and monitoring of inflammatory bowel diseases (IBD) are essential for effective management and reduction of complications. Intestinal ultrasound (IUS) is a non-invasive and cost-effective imaging modality for IBD assessment, yet its widespread adoption is limited by operator dependency and interobserver variability. Artificial intelligence (AI) offers the potential to overcome these limitations by improving diagnostic accuracy and standardizing interpretation.

Aims & Methods

This study aimed to develop an AI-assisted model for the automatic detection of active inflammation in IUS images, using bowel wall thickness (BWT) as a key marker. We further aimed to create an automatic tool for detecting bowel segments within ultrasound images and to extend its application from single images to cine loops. Grayscale ultrasound images and cine-loops of the terminal ileum were collected from Crohn’s disease patients undergoing IUS at a tertiary center. The dataset included both normal and abnormal BWT and was annotated by an experienced operator. Preprocessing involved anonymization and normalization. Automated segmentation algorithms were used to isolate bowel wall structures, and deep learning techniques, including convolutional neural networks (CNNs) and YOLO (You Only Look Once) object detection, were employed to analyze the images.

Results

The study included 2,735 grayscale ultrasound images and cine-loops of the terminal ileum from patients with Crohn's disease. The dataset was divided into three sets: a training set of 1980 images, a validation set of 220 images, and a test set of 515 images. Our model achieved robust performance metrics, including sensitivity, specificity, and accuracy of 99.1%, 94.6%, and 91.5%, respectively, for BWT detection, with an area under the receiver operating characteristic curve (AUC) of 0.85. Our model was validated on 10 independent cine-loops, comprising 7 abnormal and 3 normal cases. It accurately identified bowel wall thickening (BWT) in all seven abnormal cases, correctly classifying them as abnormal. Additionally, the model successfully confirmed the absence of BWT in all three normal cine-loops, categorizing them appropriately as normal.

Conclusion

This study represents a significant advancement in the application of artificial intelligence to intestinal ultrasound interpretation by integrating automated segmentation, automatic analysis capabilities, and cine-loop evaluation. Our model extends beyond traditional static image analysis, paving the way for real-time and dynamic assessments of bowel inflammation. This approach highlights the potential of our AI tools to reduce operator dependency, improve diagnostic accuracy, and enhance clinical workflows, making IUS more accessible and reliable for clinicians with varying levels of expertise.

Disclosure

Prof. Dan Carter has received speaker’s fees, research support, or consultancy fees from Takeda, Janssen, AbbVie, and Taro