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

With the improvement of endoscopic resection techniques, there has been recent interest in real-time in vivo characterization of polyp histology. Of all the new imaging technologies for characterizing polyp histology, narrow-band imaging (NBI) has been the most extensively studied and is easy to feasible. Correct histological prediction allows determining the optimal endoscopic technique for resection of lesions with the achievement of R0 resection. The NBI International Colorectal Endoscopic Classification (NICE) and the Japanese NBI Expert Team (JNET) classification are mostly used to predict the depth of invasion. However, the effectiveness of diagnostics using NBI in clinical practice is variable and is associated with low sensitivity for superficial invasive carcinoma.

Aims & Methods

Primary aim was to determine and compare the diagnostic accuracy of NICE and JNET classifications in predicting histology in community practice. Secondary aim was to determine the positive predictive value (PPV) for the NICE and JNET classification.
In this single-center prospective study we have included 211 patients aged 18–75 years (130 men, 62%; 81 women, 38%; mean age 60 years) who underwent colonoscopies with endoscopic resection of advanced colorectal neoplasia (defined by size lesions ≥ 10 mm). The NICE and JNET classifications were used for each lesion. The results were compared with the final histopathological finding to determine and compare NICE and JNET classification accuracy.

Results

257 lesions were analyzed including 8 (3.1 %) hyperplastic polyps, 47 (18.3 %) sessile serrated polyps, 152 (59.1 %) adenomas with low grade dysplasia, 36 (14.0 %) high-grade adenomas, 12 (4,7 %) intramucosal carcinomas, 1 (0.4 %) T1sm1 carcinoma and 1 (0.4 %) T2 carcinoma. A total of 199 lesions (77.4 %) were correctly classified according to the JNET classification and 241 lesions (93.8 %) were correctly classified according to the NICE classification. The PPV for NICE 1 lesion was 95.9 %, NICE 2 97.0 % and NICE 3 22.0 %. The PPV for JNET 1 lesions was 95.9 %, JNET 2A 83.0 %, JNET 2B 52.2 % and JNET 3 22.5 %.

Conclusion

The NICE classification was associated with a higher proportion of correctly classified lesions (93.8 %) compared to the JNET classification (77.4 %). However, NBI virtual chromoendoscopy shows a low PPV for HGD adenomas, intramucosal carcinomas and T1sm1 carcinomas (NICE 2 22.1 %, JNET 2B 52.2 %). Therefore, additional investigations in these lesions are still required with magnifying chromoendoscopy prior a final decision of endoscopic therapy. Improvement of predictive accuracy of these lesions and determining the limiting factors will be the subject of further investigation.
Supported by program projects of the Ministry of Health of the Czech Republic with reg. no. NV18-08-00246, NU22-08-00424, MO1012 and Cooperatio.

References

Kobayashi S et al. Diagnostic yield of the Japan NBI Expert Team (JNET) classification for endoscopic diagnosis of superficial colorectal neoplasms in a large-scale clinical practice database. United European Gastroenterology Journal 2019;7(7):914- 923.
Hayashi N et al. Endoscopic prediction of deep submucosal invasive carcinoma: validation of the narrow-band imaging international colorectal endoscopic (NICE) classification. Gastrointest Endosc 2013;78:625–632.
Sano Y et al. Narrow-band imaging (NBI) magnifying endoscopic classification of colorectal tumors proposed by the Japan NBI Expert Team. Dig Endosc 2016;28:526–533.
Wang Y et al. Diagnostic performance of narrow-band imaging international colorectal endoscopic and Japanese narrow-band imaging expert team classification systems for colorectal cancer and precancerous lesions. World J Gastrointest Oncol 2021;13(1):58-68.

NARROW-BAND IMAGING FOR REAL-TIME HISTOLOGY PREDICTION OF ADVANCED COLORECTAL NEOPLASIA – A PROSPECTIVE STUDY

Tomas Grega 1, Klara Kmochova 2, Katerina Hejcmanova 3, Ondrej Ngo 3, Nadija Brodyuk 2, Ondrej Majek 3, Jan Bures 1, Petr Urbanek 2, Miroslav Zavoral 1, Stepan Suchanek 1

1 First Faculty of Medicine of Charles University and Military University Hospital, Prague, Prague 6, Czechia|||Institute of Gastrointestinal Oncology, Military University Hospital, Prague, Czechia

2 First Faculty of Medicine of Charles University and Military University Hospital, Prague, Prague 6, Czechia

3 Institute of Health Information and Statistics of the Czech Republic, Brno, Czechia

Conference

UEG Week Copenhagen 2023

Topics

Colorectal

Submission format

Abstract

Session

PP 06 Other lower GI disorders (Posters)

Citation

United European Gastroenterology Journal 2023; 11 (Supplement 8)

Published

2023

UEG Podcast Episode

Journal Podcast

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.

Episode 3: UEG Journal July spotlight

Mohsan Subhani, Maria Manuela Estevinho

Published

2025

UEG Online Course

accredited

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.

This comprehensive course introduces participants to the transformative role of artificial intelligence in gastroenterology. Designed for healthcare professionals, the course covers fundamental AI concepts, clinical applications, and research perspectives. Key topics include machine learning techniques, AI-assisted diagnostics, and the integration of AI systems in clinical practice. Participants will explore the benefits and challenges of AI adoption, ethical considerations, and the regulatory landscape, with an emphasis on evidence-based decision-making.

The course includes extensive PowerPoint presentations and tailored video lectures. Examples are used to demonstrate real-world applications of the material. The total duration of the course is approximately 50 minutes, with an estimated completion time of 60 minutes, including the final assessment.

A Primer for Artificial Intelligence in Gastroenterology

Cem Simsek, Giulio Antonelli, Alanna Ebigbo

Event

A Primer for Artificial Intelligence in Gastroenterology

Topics

Endoscopy

Accreditation status

accredited

Duration

1 hour

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

In colonoscopies with colorectal neoplasia, the endoscopy therapy is recommended. The surveillance (follow-up, FU) colonoscopies follow with the aim to diagnose the recurrent and metachronous lesions. Many guidelines recommend the intervals of such procedures based on the number, size and histopathological phenotype of the resected lesions. In clinical practice, the adherence of the recommendations is variable and selection of the high-risk patients who will benefit from shorter intervals might be helpful. Therefore, detailed study focusing on the development and clinical utilization of the new method combining the clinicopathological phenotype and the mutation burden was started in 2017. The interim results of the clinical phase of the prospective study are described.

Aims & Methods

Patients with colorectal lesions ≥ 10 mm removed by advanced therapeutic methods (en-bloc mucosal resection and submucosal dissection) and followed in interval in year 1, 3 and 5 were included. The therapy and surveillance were performed in one tertiary endoscopy center. The main aim was to assess the metachronous lesions (number, size, locality, histopathology characteristics) in relation with the index colonoscopy findings. Secondary aim was evaluation of the local residual neoplasia (LRN) in the scar after previous therapy.

Results

There were 217 patients included in the study in years 2017 – 2020. Eight of them were excluded because they did not meet the inclusion criteria. Results of the index colonoscopy in 209 patients (130 men, 62,2%; 79 women, 37,8%) were analyzed. 275 index lesions were found, majority of them (238 lesions, 86,5 %, low-grade and high-grade adenomas) were benign and there were 12 (4,4%) intramucosal cancers, two T1 cancers, one T2 cancers and one NET. 21 lesions were hyperplastic or others. Follow-up colonoscopy in one year was performed in 178 patients (82,0%) and in 91 of them (51,1 %) metachronous lesions were found, 120 (64,2%) adenomas, 46 (24,6%) hyperplastic and 21 (11.2%) others, with no cancer. LRN was diagnosed in 5,5% patients. In 122 patients with 3-years FU colonoscopy, 59 (48,4%) had metachronous lesions, mostly adenomas (73; 72,3%), no cancer and one LRN found. 45 patients had 5-years FU colonoscopy so far, 22 of them (48,9%) with metachronous lesions, mostly adenomas (25; 54,3%), no cancer, LRN in one case.

Conclusion

In patients after removal of the high-risk colorectal lesions defined by size ≥ 10 mm, high numbers of metachronous lesions were found in the strict surveillance protocol (years 1, 3, and 5). All the lesions were benign, with no cancer found.

References

Supported by program projects of the Ministry of Health of the Czech Republic with reg. no. NU22-08-00424, MO1012 and Cooperatio.

EVALUATION OF THE METACHRONOUS AND RESIDUAL LESIONS IN PATIENTS AFTER HIGH-RISK COLORECTAL NEOPLASIA ENDOSCOPY THERAPY – A PROSPECTIVE STUDY

Stepan Suchanek 1, Katerina Hejcmanova 2, Tereza Halkova 3, Tomas Grega 1, Ondrej Ngo 2, Jan Bures 1, Marek Minarik 4, Ondrej Majek 2, Miroslav Zavoral 1, Lucie Benesova 3

1 1st Faculty of Medicine, Charles University, Military University Hospital, Prague, Czechia|||1st Faculty of Medicine, Charles University, Military University Hospital, Prague, Czechia

2 Faculty of Medicine, Masaryk University, Brno, Brno, Czechia|||Institute of Health Information and Statistics of the Czech Republic, Prague, Czechia

3 Genomac Research Institute, Prague, Czechia

4 Genomac Research Institute, Prague, Czechia|||Faculty of Science, Charles University, Praha, Czechia

Conference

UEG Week Berlin 2025

Topics

Colorectal

Submission format

Abstract

Session

LOWER GI (Posters)

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

Artificial Intelligence (AI)-powered Computer-aided diagnosis (CADx) systems provide real-time polyp histology prediction during colonoscopy, potentially improving accuracy in clinical decision-making. We aimed to assess CADx performance and its impact on endoscopist optical diagnosis for sessile serrated polyps (SSPs), traditional serrated adenomas (TSAs), adenomas with advanced histology, and cancers in a pragmatic implementation study.

Aims & Methods

We performed a secondary analysis of a large prospective cohort comprising patients undergoing diagnostic, screening, and surveillance colonoscopies. All patients and polyps with SSPs, TSAs, advanced adenomas and/or cancers detected, and prospectively documented CADx assisted or CADx unassisted optical diagnoses were included in the study. The primary outcome was the sensitivity of CADx assisted and unassisted optical diagnoses for SSP identification. Secondary outcomes included sensitivity for TSA, advanced adenoma, and cancer identification as well as the impact of CADx output on endoscopists’ optical diagnoses.

Results

Within a cohort of 2622 patients with 2456 eligible polyps there were 140 (5.7%) SSPs, 22 (0.9%) TSAs, 213 (8.7%) advanced adenomas, and 13 (0.5%) cancers. Sensitivity for SSP identification of CADx assisted and unassisted optical diagnosis was 53.2% (95% CI 42.3-63.8) and 37.8% (95% CI 24.1-53.9) respectively; p=0.12. In CADx assisted cases, endoscopists correctly identified SSPs more frequently when CADx classified these as non-neoplastic (56/79 cases) compared to neoplastic (23/79 cases), (66.1% [95% CI 53.0-77.1] vs 21.7% [95% CI 9.6-41.9]; p=0.0003). Sensitivity for TSA identification as neoplastic by CADx output was 61.6% (8/13), but CADx assisted and unassisted endoscopist optical diagnosis performed similarly, identifying TSAs as neoplastic in 83.3% and 66.7% of cases respectively; p=0.61. Sensitivity for advanced adenoma identification as adenoma/neoplastic did not differ between CADx assisted and unassisted cases (Table 1). Sensitivity for optical diagnosis of cancer was 50.0% and 42.9% for CADx assisted and unassisted optical diagnosis, with 3/6 and 4/7 of cancers misdiagnosed as adenomas, respectively.

Table 1. Diagnostic performance of CADx assisted and unassisted optical diagnosis

	SSP		TSA		Advanced adenomas*		Cancers
	CADx assisted	CADx unassisted	CADx assisted	CADx unassisted	CADx assisted	CADx unassisted	CADx assisted	CADx unassisted
Polyps, n	79	37	12	9	71	83	6	7
Sensitivity, % (95% CI)	53.2 (42.3-63.8)	37.8 (24.1-53.9)	83.3 (54.0-97.0)	66.7 (34.7-88.4)	100.0 (95.0-100)	96.4 (89.3-98.9)	50.0 (11.8-88.2)	42.9 (9.9-81.6)
PPV, %	27.8	20.0	-	-	-	-	23.1	33.3
Incorrect endoscopist diagnoses
Hyperplastic, n	17	4	1	2	0	0	0	0
Adenoma, n	20	19	-	-	-	-	3	4
SSP, n	-	-	1	1	0	0	0	0
Cancer, n	0	0	0	0	0	3	-	-

*Adenomas with villous component or high grade dysplasia

Conclusion

In our study, CADx use did neither harm nor improve optical diagnostic performance in polyps with SSP, TSA, advanced adenoma, or cancerous histology. Sensitivity for identification of these lesions trended universally higher with CADx assisted optical diagnosis, though statistical significance was not achieved at the present sample size. Whilst both CADx assisted and unassisted optical diagnosis reliably identified advanced adenomas as adenomas, optical diagnosis sensitivity to recognize SSPs and cancerous lesions was low.

Disclosure

Daniel von Renteln has received research funding from ERBE Elektromedizin GmbH, Ventage, Pendopharm, Fujifilm, and Pentax, and has received consultant or speaker fees from Boston Scientific Inc., ERBE Elektromedizin GmbH, and Pendopharm. The remaining authors declare that they have no conflict of interest.

ARTIFICIAL INTELLIGENCE FOR REAL-TIME HISTOLOGY PREDICTION OF COLORECTAL POLYPS WITH SERRATED OR ADVANCED HISTOLOGY

Megan Oleksiw 1, Douglas Kevin Rex 2, Cesare Hassan 3, Roupen Djinbachian 1, Daniel von Renteln 1

1 Montreal University Hospital Research Center, Montreal, Canada

2 Indiana University School of Medicine, Indianapolis, United States

3 IRCCS Humanitas University, Pieve Emanuele MI, Italy

Conference

UEG Week Berlin 2025

Topics

Colorectal

Submission format

Abstract

Session

Colorectal polyp detection and characterisation (Posters)

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Online Course

accredited

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.

Acute severe ulcerative colitis (ASUC) remains the most severe form of UC and is sometimes associated with mortality. Adequate evaluation, early and correct intervention, and follow-up with a multidisciplinary approach are crucial in management. A comprehensive approach to ASUC, epidemiology, definition, diagnosis, evaluation, and medical and surgical management are all discussed in this online course by Haluk Tarik Kani, Irene Marafini, Joana Roseira, Wilhelmus A. Bemelman and Fernando Magro.

Target audience
We believe both gastroenterology trainees and early career gastroenterologists and surgeons will find in this online course a thorough and updated review on ASUC management.

Acute Severe Ulcerative Colitis

Fernando Magro, Haluk Tarik Kani, Joana Roseira, Irene Marafini, Wilhelmus A. Bemelman

Event

Acute Severe Ulcerative Colitis

Topics

IBD

Accreditation status

accredited

Duration

1 hour

Published

2025

UEG Online Course

accredited

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.

This interactive course explores why optimising polyp detection is central to high-quality colonoscopy and its direct impact on morbidity and mortality. Designed for general gastroenterologists and young endoscopists, the course addresses key quality indicators, bowel preparation, scoping techniques, and the integration of AI for improved detection. Participants will learn to interpret and apply optical diagnosis systems (NICE, WASP, LST-classification, BLINC) and to choose appropriate therapeutic strategies tailored to polyp type and patient context. Surveillance intervals and outcome factors, including family history and syndromes, will be discussed in line with ESGE guidelines. Case-based discussions will focus on communication with patients regarding diagnosis and management. By combining expert testimony, videos, and practical strategies, the course aims to improve participants’ endoscopic practice, ensuring earlier detection, appropriate treatment, and better long-term outcomes.

Target Audience:

Gastroenterologists (in training)
Other physicians and surgeons
Nurses
Medical students

Impact of Polyp Detection in Colonoscopy

Raf Bisschops, Manuele Furnari, Veronique Van der Voort, Pieter Sinonquel

Event

Impact of Polyp Detection in Colonoscopy

Topics

Endoscopy Colorectal

Accreditation status

accredited

Duration

1 hour

Published

2025

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

Most popular content

Rate for better recommendations!