UEG's educational platform for gastroenterology education bringing recordings, courses, guidelines, and more together in one place.

UEG Week Berlin 2025 Recordings Gut Guide online

Rate for better recommendations!

Your feedback helps us show you more of what you like and less of what you dislike!

More of this!

We will show you more similar content.

Not for me!

We won't suggest this again.

Bookmark!

Save this content for later!

New to myUEG? Create an account! Log In with myUEG account

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Free for all myUEG account holders. Your access level is set automatically based on your occupation. Medical professionals get full access to all content. If you are a non-medical user, you can only access UEG Week content from congresses you attended.

Not sure what you can access? Learn more about account types.

How to define the hot spots?

Marjolijn Duijvestein 1

1 Radboudumc, Nijmegen, Netherlands

Event

UEG Week Berlin 2025

Topics

Endoscopy Nurses

Session

Is your GI-practice sustainable?

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

What can we learn from monogenic IBD

Alexo Muise 1

1 SickKids Research Institute, Toronto, Canada

Event

UEG Week Berlin 2025

Topics

IBD Mechanisms & Personalised Medicine

Session

The art of making clinical research precise: Predicting therapy response in IBD

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

BEYOND ENDOSCOPY: EVALUATING NON-INVASIVE TOOLS FOR MONITORING POSTOPERATIVE CROHN'S DISEASE RECURRENCE

Not sure what you can access? Learn more about account types.

Introduction

Post-operative recurrence (POR) affects a substantial proportion of Crohn's disease (CD) patients following intestinal resection. While ileocolonoscopy remains the gold standard for detecting recurrence, its invasive nature and patient burden have spurred interest in non-invasive monitoring approaches. This study evaluates the performance of faecal calprotectin (FC) and cross-sectional imaging at different timepoints in predicting endoscopic recurrence in postoperative CD patients.

Aims & Methods

In this multicenter retrospective cohort of 895 CD patients who underwent ileocecal resection, we analyzed the diagnostic accuracy of FC measurements at 3, 6-12, and 18-24 months postoperatively for predicting endoscopic recurrence (Rutgeerts score ≥i2 or SES-CD ≥3). Additionally, we assessed the concordance between intestinal ultrasound (IUS) and magnetic resonance imagings (MRI) and endoscopic findings at both 6-12- and 18-24-months using kappa statistics.

Results

FC demonstrated modest discriminatory ability at 3 months (AUC 0.642, 95% CI: 0.530-0.753) and 6-12 months (AUC 0.653, 95% CI: 0.593-0.713), with improved performance at 18-24 months (AUC 0.676, 95% CI: 0.608-0.744). The optimal cutoff values for FC (47.5 μg/g at 3 and 6-12 months; 80.0 μg/g at 18-24 months) were substantially lower than standard thresholds (150-250 μg/g) used in non-operated patients.
At 6-12 months, radiological and endoscopic assessments showed moderate agreement (κ=0.426, p<0.001) with 63.2% concordance. At 18-24 months, IUS demonstrated superior agreement with endoscopic findings (κ=0.531, p<0.001; sensitivity 83.8%, specificity 72.7%) compared to MRI (κ=0.324, p<0.001). Notably, radiological remission at 18-24 months was identified as a significant protective factor against surgical recurrence (OR 0.356, 95% CI: 0.179-0.705, p=0.003).

Table I: Concordance between endoscopic and radiologic findings (IUS and MRI) for inflammation and remission at 18–24 months post-ileocecal resection. Abbreviations: IUS: Intestinal ultrasound, MRI: Magnetic resonance imaging.

Comparison	n	κ	Strength of Agreement	p-value	Condition	Endoscopic Activity	Endoscopic Remission
Endoscopic Remission 18–24m vs. IUS 18–24m	123	0.531	Moderate	<0.001	Active Inflammation	60	7
					Remission	21	35
					Total	81	42
Endoscopic Remission 18–24m vs. MRI 18–24m	140	0.324	Fair	<0.001	Active Inflammation	64	17
					Remission	28	31
					Total	92	48

Conclusion

Non-invasive monitoring with FC shows promise in postoperative CD surveillance, though diagnostic thresholds differ substantially from those established for non-operated patients. IUS demonstrates superior concordance with endoscopic findings compared to MRI, particularly at later timepoints. The protective role of radiological remission against surgical recurrence highlights the importance of transmural healing. Combining FC with radiological assessment, especially IUS, may provide a comprehensive, patient-friendly approach to monitoring postoperative CD, potentially reducing the need for invasive procedures in selected patients but further studies are needed in this direction.

BEYOND ENDOSCOPY: EVALUATING NON-INVASIVE TOOLS FOR MONITORING POSTOPERATIVE CROHN'S DISEASE RECURRENCE

Luisa Bertin 1, Benedetta Masoni 2, Silvia Ferretti 2, Alessandro Armuzzi 2, Cristina Bezzio 2, Miriana Zanconato 1, Gianluca Semprucci 1, Davide Giuseppe Ribaldone 3, Adele Capello 3, Giorgia Bodini 4, Francesco Calabrese 4, ANDREA PASTA 4, Linda Ceccarelli 5, Francesco Costa 5, Lorenzo Bertani 6, Marco Marino 7, Luca Navarria 7, Gianluca Benevento 8, Renato Sablich 8, Marta Ascolani 9, Michele Campigotto 9, Andrea Buda 10, Gaia Riguccio 10, Nicoletta Merlini 11, Elisabetta Dal Pont 12, Daniele Canova 13, Fabiana Zingone 1, Edoardo Vincenzo Savarino 1

1 University of Padova, Padova, Italy

2 IBD Center, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy

3 University of Turin, Turin, Italy

4 Policlinico San Martino, Genova, Italy

5 AOU Pisa, Pisa, Italy

6 University of Pisa, Pisa, Italy

7 Azienda Sanitaria Universitaria Friuli Centrale, Udine, Italy

8 Ospedale S.Maria degli Angeli, Pordenone, Italy

9 Ospedale Ca'Foncello, Treviso, Italy

10 Ospedale di Santa Maria del Prato di Feltre, Feltre, Italy

11 Ospedale Vittorio Emanuele III, Montecchio, Italy

12 Ospedale San Martino di Belluno, Belluno, Italy

13 San Bortolo Hospital, Vicenza, Italy

Event

UEG Week Berlin 2025

Topics

IBD

Submission format

Abstract

Session

Predicting clinical outcomes in IBD

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

ARTIFICIAL INTELLIGENCE FOR COMPREHENSIVE PANCREATIC LESION PROFILING: MULTICENTER VALIDATION OF SOLID/CYSTIC LESION DETECTION/CHARACTERIZATION AND IPMN GRADING

Not sure what you can access? Learn more about account types.

Introduction

Endoscopic ultrasound (EUS) is the gold standard for evaluating pancreatic lesions, allowing for real-time imaging and biopsy sampling. Nevertheless, the differentiation between solid pancreatic lesions — such as pancreatic ductal adenocarcinoma (PDAC) and pancreatic neuroendocrine tumors (PNETs) — as well as cystic lesions is often troublesome. Specifically, identifying intraductal papillary mucinous neoplasms (IPMNs) with varying degrees of dysplasia is crucial for guiding clinical management. However, the diagnostic accuracy of current methods remains suboptimal. This multicenter study aimed to develop and validate convolutional neural networks (CNNs) to characterize solid and cystic pancreatic lesions and stratify IPMNs into high-grade dysplasia/carcinoma (HGD/C) and low-grade dysplasia (LGD).

Aims & Methods

This multicenter study included EUS images from 12 centers in Spain, Brazil, the United Kingdom and the United States of America. Solid lesion differentiation (PDAC vs. PNET) was achieved using a CNN trained on 49034 images from 95 patients (n=69 for PDAC and n=26 for PNET), with diagnoses confirmed via EUS-guided fine-needle biopsy or surgical specimen analysis. A second CNN was trained on 79395 images from 82 patients (n=64 for mucinous cystic lesions and n=18 for non-mucinous cystic lesions). Finally, a third model used the subset of IPMNs (n=51046 frames, 30 patients) to distinguish between HGD/C (n=5 patients) and LGD (n=25 patients). Histological confirmation was used as the gold standard. Performance metrics included sensitivity, specificity, accuracy, and area under the precision-recall curve (AUC-PR). To comprehensively determine the model's performance, we evaluated multiple thresholds for the confidence score and the IoU, between 0.45 and 0.55 with a step of 0.02 ([0.45, 0.47, 0.50, 0.52, 0.55]). The datasets were split into training (70%), validation (20%), and testing (10%) subsets.

Results

For solid lesions, the model differentiated PDAC from PNETs with an accuracy of 91.8%, with sensitivities of 96.2% and 97.8%, respectively. The AUC-PR was 0.982 for PDAC and 0.977 for PNET. Regarding cystic lesions the model detected mucinous cystic lesions with a sensitivity of 97.5%, an overall accuracy of 89.7% and an AUC-PR of 0.977. When the subset of IPMNs was specifically analyzed, the model distinguished IPMNs with HGD/C from those with LGD with a sensitivity of 97.5%, specificity of 94.3%, and an overall accuracy of 89.8%. The AUC was 0.988.

Conclusion

This is the first multicenter, transatlantic AI study aiming to provide a holistic approach to both solid and cystic pancreatic lesions, focusing on those with a significantly higher malignant potential. Our models achieved high accuracy in identifying and differentiating these conditions. Furthermore, to our knowledge this is the first integrative model to include the ability to stratify IPMNs into LGD and HGD/C, which has significant clinical implications, potentially reducing unnecessary surgeries and ensuring timely intervention for high-risk patients. The inclusion of data from diverse regions reduces demographic bias and enhances model generalizability. Real-time implementation of these solutions could significantly improve decision-making in EUS and optimize patient outcomes.