Introduction

Capsule endoscopy (CE) is a minimally invasive and essential tool for assessing small bowel disorders, especially Crohn’s disease. Accurate detection of ulcers and erosions is vital for evaluating disease activity, guiding treatment, and monitoring therapeutic response. Although CE has revolutionized lesion detection, its manual interpretation remains time-consuming and subject to interobserver variability. Recent advances in artificial intelligence (AI), particularly convolutional neural networks (CNNs), offer promising solutions by enhancing diagnostic accuracy, reducing variability, and improving workflow efficiency. This study aimed to develop and validate a robust AI model capable of detecting and distinguishing small bowel ulcers and erosions across multiple CE platforms and clinical centers.

Aims & Methods

In a prospective, multicenter study conducted between January 2021 and April 2024, data were collected from centers in Portugal, Spain, and the United States. Two CE devices—PillCamSB3 and Olympus EC-10—were used to analyze 137 anonymized exams. The AI-assisted readings generated by a deep learning model were compared to standard-of-care (SoC) interpretations, with an expert consensus panel serving as the reference standard. Performance metrics included sensitivity, specificity, positive and negative predictive values (PPV, NPV), and area under the receiver operating characteristic curve (AUROC).

Results

Expert consensus identified ulcers and erosions in 56 patients (40.9%). Compared to the reference standard, SoC readings achieved 60.7% sensitivity, 98.8% specificity, 97.1% PPV, 78.4% NPV, and 83.2% accuracy. In contrast, the AI-assisted model achieved 94.6% sensitivity, 80.2% specificity, 76.8% PPV, 95.6% NPV, and 86.1% accuracy. The AI model was found to be both non-inferior (p < 0.001) and statistically superior (p < 0.001) to SoC. Notably, it identified 68 lesions, nearly double those detected by SoC (35), and demonstrated consistent performance across devices and centers. The mean AI-assisted reading time was 239 seconds (SD 138 seconds) per exam.

Conclusion

The AI-assisted model significantly outperformed conventional SoC in the detection of small bowel ulcers and erosions, achieving higher sensitivity and overall accuracy while substantially reducing reading time. This is the first multicenter validation of an interoperable AI solution for CE, capable of high diagnostic performance across different devices and clinical environments. These findings highlight the potential of AI to transform endoscopic evaluation and management in inflammatory bowel disease.

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

Current therapies for inflammatory bowel disease (IBD) suppress inflammation rather than inhibiting underlying microbial drivers. Treatment failures of frontline interventions, including corticosteroids, can lead to dose escalation and risk of adverse effects.^1,2 Bacteria with pro-inflammatory potential, like adherent-invasive Escherichia coli (AIEC), have been postulated as a possible microbial driver in Crohn’s disease (CD), however, targeting these bacteria with precision in IBD remains challenging.^3,4 Most antibiotics have broad-spectrum activity and disturb the background microbiome, which may exacerbate inflammation.⁵ Attention has shifted towards bacteriophages, yet their underlying mechanisms of treating IBD, and how they may work as an adjunctive therapy, remains elusive.

Aims & Methods

We aimed to assess whether and how phage therapy, specific for a CD-associated bacterium, reduces colitis severity using gnotobiotic mouse models.
In vitro kill curves and biofilm challenges were used to identify lytic phage candidates. Adult germ-free C57BL/6 mice were colonized with altered Schaedler-flora (ASF) and E. coli NRG857c (NRG), a CD-associated isolate. After 3 weeks, mice were treated with an NRG-specific lytic phage (1x10⁹ PFU/dose; daily or TIW) or vehicle (PBS) for 2 weeks (n=6/group) and then exposed to 1 cycle of dextran sulfate sodium (2%; DSS) in drinking water. PBS-treated mice (n=6) not exposed to DSS served as controls. Phage treatment was also tested in a spontaneous model of colitis using C57BL/6NTac-Il10^em8Tac (IL-10^-/-) mice, treated weekly. Mice were monitored daily for weight, stool consistency, and occult blood. Fecal contents were cultured to determine bacterial load, and the expression of NRG fimS was quantified using qPCR as an assessment of virulence. At endpoint, colon tissues were collected for histological and immunohistochemistry analysis to quantify colitis severity and NRG infiltration, respectively. Additional C57BL/6 mice were colonized and treated as previously described. During colitis induction, mice received a low-dose of budesonide (2μg/day)⁶ (n=5) or vehicle (n=5) until endpoint. Mice were monitored daily for disease activity and colon tissues were collected for histological analysis. HPLC was used to determine active budesonide levels.

Results

HER259 was identified as a lytic phage against CD-associated AIEC NRG. In ASF and NRG colonized mice, HER259 reduced clinical symptoms (p< 0.001, p< 0.001) and histological scores (p< 0.0001, p< 0.001) in chemical induced and spontaneous colitis, respectively. A 1-log reduction in NRG bacterial load was observed in HER259-treated mice (p< 0.001). Reisolated NRG exhibited a reduced FimS ON/OFF ratio (p-value < 0.01). Immunohistochemistry revealed reduced infiltration of NRG into the lamina propria following HER259 treatment, with greater accumulation in the epithelium. HER259 treatment increased the efficacy of a sub-therapeutic dosing regimen of budesonide (p< 0.001), which was independent of microbial-based drug metabolism as determined by HPLC.

Conclusion

Our results demonstrate that lytic phage targeting a CD-associated bacterium attenuates colitis in two gnotobiotic mouse models. The intervention did not lead to complete eradication of the disease-driving agent, but instead modulated bacterial virulence mechanisms and enhanced responses to corticosteroid therapy. The data suggests that alternative mechanisms should be considered when translating phage therapy to treat IBD in clinical trials.

References

1. Yan, Y. et al. Commensal bacteria promote azathioprine therapy failure in inflammatory bowel disease via decreasing 6-mercaptopurine bioavailability. Cell Rep Med 4, 101153 (2023).
2. Nagayama, M., Gogokhia, L. & Longman, R. S. Precision microbiota therapy for IBD: premise and promise. Gut Microbes 17, 2489067 (2025).
3. Darfeuille-Michaud, A. et al. High prevalence of adherent-invasive Escherichia coli associated with ileal mucosa in Crohn’s disease. Gastroenterology 127, 412–421 (2004).
4. A, D.-M. et al. Presence of adherent Escherichia coli strains in ileal mucosa of patients with Crohn’s disease. Gastroenterology 115, 1405–1413 (1998).
5. Nelson, R. L., Suda, K. J. & Evans, C. T. Antibiotic treatment for Clostridium difficile-associated diarrhoea in adults. Cochrane Database Syst Rev 3, (2017).
6. Bercik, P. et al. Chronic gastrointestinal inflammation induces anxiety-like behavior and alters central nervous system biochemistry in mice. Gastroenterology 139, (2010).