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 Poster

Standard Poster

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.

Introduction

Endoscopic ultrasound (EUS) is an essential tool in the evaluation of lymph nodes (LNs), especially for oncologic staging and guiding therapeutic decisions. Characteristics such as hypoechoic appearance, well-defined borders, round shape, and a size exceeding 10 mm are typically associated with malignancy, offering 80–100% accuracy when observed collectively—though this ideal combination is rare. While EUS-guided tissue acquisition (EUS-TA) contributes to diagnosis, its reliability can be limited.

Aims & Methods

This multicenter study aimed to assess the performance of a novel artificial intelligence (AI) model in predicting LN malignancy based on EUS images.
The study involved EUS images from nine centers across Spain, Portugal, Brazil, the United Kingdom, and the United States. Lesions were annotated as “malignant” or “benign” and outlined using bounding boxes. Final diagnoses were established through positive fine-needle aspiration or biopsy (FNA/FNB), or, when negative, confirmed with a minimum of six months of clinical follow-up. A convolutional neural network (CNN) was created using the YOLO (“You Only Look Once”) architecture, incorporating both detection and classification components. Key performance indicators included detection rate (DR), sensitivity, specificity, overall accuracy, and the area under the curve (AUC).

Results

The model was trained on 59,992 images derived from 82 EUS procedures. The CNN achieved a sensitivity of 98.8% (95% CI: 98.5–99.2%), a specificity of 99.0% (95% CI: 98.3–99.7%), and a precision of 99.0% (95% CI: 98.4–99.7%) in differentiating malignant from benign LNs. The negative predictive value (NPV) was 98.8% (95% CI: 98.4–99.2%) for malignant and 97.0% (95% CI: 95.0–98.9%) for benign nodes. The overall diagnostic accuracy for both malignant and benign findings reached 96.99% (95% CI: 87.8–96.2%).

Conclusion

This is the first study to explore the application of deep learning for LN analysis through EUS imaging. Reliable LN characterization is vital in determining disease stage and informing treatment pathways, with direct implications for patient management. The AI-based model demonstrated strong performance in both detection and classification tasks, highlighting its potential to enhance LN evaluation with EUS and contribute to more individualized, effective care.

Disclosure

No co

ARTIFICIAL INTELLIGENCE IN ENDOSCOPIC ULTRASOUND FOR LYMPH NODE DETECTION AND MALIGNANCY ASSESSMENT: A MULTICENTER TRANSATLANTIC STUDY

Tiago Ribeiro 1, Miguel Mascarenhas-Saraiva 1, António Miguel Martins Pinto da Costa 2, Francisco Mendes 1, Belén Agudo Castillo 2, Miguel Martins 1, João Afonso 1, Maria Almeida 1, Joana Mota 1, Pedro Cardoso 1, Matheus Carvalho 3, Maria Moris 4, Ana Garcia Garcia de Paredes 5, Daniel De la Iglesia-García 6, Carlos Esteban Fernández-Zarza 6, Ana Pérez González 6, Khoon Sheng Kok 7, Jessica Widmer 8, Laleh Omrani 8, Grace Kim 9, Susana Lopes 1, Pedro Moutinho-Ribeiro 1, Filipe Vilas-Boas 1, Eduardo De Moura 10, Uzma D. Siddiqui 9, Guilherme Macedo 1, Mariano Ganzalez- Haba Ruiz 6

1 Centro Hospitalar Universitário de São João, Porto, Portugal

2 Hospital Universitario Puerta de Hierro Majadahonda (Madrid), Madrid, Spain

3 Hospital das Clínicas da Faculdade de Medicina da USP, São Paulo, Brazil

4 Hospital Universitario Marqués de Valdecilla, Santander, Spain

5 Hospital Universitario Ramon y Cajal, Madrid, Spain

6 Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Spain

7 Royal Liverpool Hospital, Liverpool, United Kingdom

8 NYU Langone Health, New York, United States

9 Center for Endoscopic Research and Therapeutics (CERT) and Advanced Endoscopy Training, University of Chicago, Chicago, United States

10 University of Sao Paulo Medical School, Sao Paulo, Brazil

Conference

UEG Week Berlin 2025

Topics

Oesophagus

Submission format

Abstract

Session

EUS-guided interventions in upper GI (Posters)

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.

Time management: How can we save time?

Deepa Jegadish Gandhi 1

1 Mater Misericordiae University Hospital, Dublin, Ireland

Event

UEG Week Berlin 2025

Topics

Nurses

Session

Staff safety and management

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Poster

Standard Poster

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.

Introduction

Although traditionally regarded as a vestigial organ, the appendix is increasingly recognized for its potential role in modulating gut immunity and contributing to the development of significant inflammatory or neoplastic intestinal diseases [1]. However, the underlying mechanisms linking the appendix to these immune and pathological processes remain poorly understood. This study aimed to investigate the relationship between the local immune microenvironment and the mutational landscape of rectal carcinomas in the context of prior or progressive appendectomy status.

Aims & Methods

This study aimed to investigate the relationship between the local immune microenvironment and the mutational landscape of rectal carcinomas in the context of prior or progressive appendectomy status.
Patients enrolled in the IMMUNOREACT 1 and 2 studies (NCT04915326 and NCT04917263, respectively) were stratified according to appendectomy status. Immunohistochemical analysis was performed to assess a range of immune markers, including CD3, CD4, CD8, CD8β, Tbet, FoxP3, PD-L1, MSH6, PMS2, and CD80. Additionally, flow cytometry was employed to evaluate the percentage of epithelial cells expressing CD80, CD86, CD40, HLA-ABC, or HLA-DR, as well as to quantify activated CD8+ T cells, CD4+ Th1 cells, and regulatory T cells (Tregs). Non-parametric tests were used.

Results

In this cohort, 41 patients out of 163 underwent appendectomy for other causes (e.g. appendicitis) before having been diagnosed with a rectal cancer. When the two groups were compared for microenvironmental features, in the normal mucosa of patients who had a previous appendectomy there was a higher rate of epithelial cells expressing HLA-abc (p=0,04) and a higher expression of CTLA4 on CD3+ T cells (p=0,03) when compared to appendectomy-naive patients. Within the rectal cancer tissue, a higher expression of CD86 on epithelial (cancer) cells expression was found in patients who already had an appendectomy (p=0,03). In therapy naïve patients, previous appendectomy was associated to a higher activation of CD4+ T helpers (expression of CD25), (p=0.04), and to tendency of higher rate of epithelial cells expressing HLA-abc (p=0,06) and of T cells expressing CTLA-4 (p=0.08). In patients who had neoadjuvant therapy, lower level of PD-L1 on the leukocyte surface were observed in patients who had a previous appendectomy (p=0.039).

Conclusion

Our findings suggest that prior appendectomy may be associated with distinct alterations in the local immune microenvironment of rectal carcinomas, including increased expression of antigen-presenting and immune-regulatory molecules such as HLA-BC, CTLA4, and CD86. In therapy naïve patients, appendectomy seem to increase the activation of T helper cells counterbalanced by an increase of the number of T cells expressing CTLA-4. These immune shifts in both tumour tissue and adjacent healthy mucosa support the hypothesis that the appendectomy may in somehow alter the interaction between epithelia cells and intraepithelial T cells. Further trancriptomic analysis will shed light on the effect of appendectomy on mucosal microevironment of rectal cancer patients.

References

1. Collard MK, Tourneur-Marsille J, Uzzan M, Albuquerque M, Roy M, Dumay A, Freund JN, Hugot JP, Guedj N, Treton X, Panis Y, Ogier-Denis E. The Appendix Orchestrates T-Cell Mediated Immunosurveillance in Colitis-Associated Cancer. Cell Mol Gastroenterol Hepatol. 2023;15(3):665-687.

IMMUNOREACT 19: IN RECTAL CANCER PATIENTS, PREVIOUS APPENDECTOMY IS ASSOCIATED TO AN ALTERED ANTIGEN PRESENTATION IN THE NORMAL MUCOSA

Anna Matteazzi 1, Melania Scarpa 2, Andromachi Kotsafti 3, Astghik Stepanyan 4, Gaia Tussardi 1, Antonio Rosato 2, Ottavia De Simoni 2, Francesca Bergamo 2, Valerio Pellegrini 5, Ivana Cataldo 5, Ceccon Carlotta 5, Anna Pozza 5, Roberta Salmaso 6, Federico Scognamiglio 4, Cesare Ruffolo 1, Silvia Negro 4, Isacco Maretto 1, Imerio Angriman 6, Chiara Vignotto 1, Luca Facci 1, Giorgio Rivella 1, Quoc Riccardo Bao 1, Andrea Baldo 1, Giulia Pozza 1, Marco Agostini 1, Maurizio Zizzo 7, Beatrice Salmaso 8, Dario Parini 8, GiovannI Pirozzolo 9, Giovanni Bordignon 10, Roberto Merenda 10, Laurino Licia 10, Isabella Mondi 10, Silvio Guerriero 11, Giuseppe Portale 12, Lavinia Ceccarini 12, Michele Antoniutti 12, Laura Marinelli 13, Mattia Barbareschi 13, Giovanni Bertalot 13, Alberto Brolese 13, Giulia Noaro 9, Giulia Becherucci 14, Andrea Porzionato 6, Francesco Cavallin 15, Barbara Di Camillo 6, Gaya Spolverato 1, Ignazio CASTAGLIUOLO 1, Matteo Fassan 5, Marco Scarpa 1

1 Azienda Ospedaliera Universitaria di Padova, Padova, Italy

2 Veneto Institute of Oncology IOV-IRCCS, Padova, Italy

3 Veneto Institute of Oncology (IOV-IRCCS), Padova, Italy

4 Azienda Ospedaliera Universitaria di Padova, Yerevan, Italy

5 Azienda ULSS n 2 Marca Trevigiana, Treviso, Italy

6 University of Padova, Padova, Italy

7 Arcispedale Santa Maria Nuova IRCCS, Reggio Emilia, Italy

8 Azienda ULSS n 5 Polesana, Rovigo, Italy

9 Azienda ULSS n 6 Euganea, Padova, Italy

10 Azienda ULSS n 3 Serenissima, Venezia, Italy

11 Ospedale di Fermo, ASUR 4, Fermo, Italy

12 Azienda ULSS n 7 Pedemontana, Bassano del Grappa, Italy

13 Azienda Provinciale per i Servizi Sanitari, Trento, Italy

14 Azienda ULSS n 1 Dolomiti, Belluno, Italy

15 Independent Statistician, Solagna, Italy

Conference

UEG Week Berlin 2025

Topics

Colorectal

Submission format

Abstract

Session

Colorectal cancer: Working around genetics and complications (Posters)

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.

Laudatio UEG Lifetime Achievement Awardee

Mario Dinis-Ribeiro 1

1 IPO Porto, Porto, Portugal

Event

UEG Week Berlin 2025

Topics

Immunology

Session

Opening Plenary

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Poster

Standard Poster

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.

Introduction

A large proportion of Inflammatory Bowel Disease (IBD) patients also develop liver diseases, predominantly primary sclerosing cholangitis (PSC), and more than 80% of PSC patients also have IBD. Coexistence of both diseases in patients, increase of five times the risk of developing a colorectal cancer, and causes liver transplantation failure. Both of IBD and PSC have no curative treatment yet, and the impact of IBD on liver homeostasis and reciprocally the impact of PSC on intestinal barrier (IB) remain largely unknown.

Aims & Methods

The aims of the study were to investigate the impact of (1) mouse models of IBD on liver homeostasis and (2) the impact of mouse models of PSC on IB integrity. Two models of colitis have been used. A model was conducted by adding 3% DSS in drinking water for five days, followed by two days of regular water. The second model of colitis was performed using a pre-sensitizing step involving subcutaneous injection of 2% oxazolone and five day later, a rectal injection of 1.5% oxazolone. As PSC mouse models, we used intra-peritoneal injection of 1µL/g mice weight of CCl₄ twice a week for 8 weeks and another model with a 0.1% diethyl 1,4-dihydro-2,4,6-trimethyl-3,5-pyridinedicarboxylate within diet for 3 weeks. Colitis and cholangitis severities were monitored by food consumption, macroscopic observations as well as calculation of Disease Activity Index which sum up scores of weight loss, bleeding and stool consistency. Fecal samples were tested for calprotectin and lipocalin by ELISA to estimate gut inflammation. Intestinal permeability (IP) was investigated in vivo by estimation of FITC-Dextran quantity in mice’s sera after oral administration and at mice sacrifice in ileum and colon tissues by measuring the flux of fluorescein sodium salt in Ussing chamber. To study liver homeostasis, we performed pathological analysis (H&E and Sirius red staining), and real-time PCR with a focus on fibrosis markers, bile acids metabolism and metabolic pathways.

Results

IBD models induced strong alteration of colonic homeostasis including increased fecal markers of inflammation (Calprotectin and Lipocalin-2) and tissues mRNA expression of inflammatory cytokines (Ifng…). These models of colitis were also accompanied by elevated IP and impaired liver genes expression level of fibrosis (Col3a1) and fatty acids metabolism (Fasn…), as well as cholesterol and bile acids transporters (Abcb11…). This was found to be correlated with impaired enterohepatic circulation of bile acids in the gut. Furthermore, an increase expression of mRNA markers of inflammation (Cxcl1…) was only observed in the liver of the DSS colitis model. However, no alteration of liver homeostasis, including infiltrated immune cells or fibrosis was revealed by histological analysis. PSC mouse models induced strong alterations of liver homeostasis and were associated with altered gut homeostasis shown by a strong increased IP.

Conclusion

Our data demonstrate that IBD colitis models impair liver homeostasis, while PSC models disrupt intestinal integrity. The data obtained from both IBD and PSC models demonstrated a significant increase in intestinal permeability, thereby underscoring it’s potential as an association between those diseases. Further investigations are ongoing in ours models as a next step will be to study a combination of both protocols to explore disease progression and severity.

References

Rabiee, Anahita, and Marina G Silveira. “Primary sclerosing cholangitis.” Translational gastroenterology and hepatology vol. 6 29. 5 Apr. 2021, doi:10.21037/tgh-20-266
Kim, You Sun et al. “Primary sclerosing cholangitis (PSC) and inflammatory bowel disease (IBD): a condition exemplifying the crosstalk of the gut-liver axis.” Experimental & molecular medicine vol. 55,7 (2023): 1380-1387. doi:10.1038/s12276-023-01042-9