UEG Presentation

COMPUTER AIDED QUALITY CONTROL SYSTEM IMPROVES BARRETT’S NEOPLASIA DETECTION IN AN EX-VIVO SETTING

Log in to continue.

This content is part of Gutflix. Log in with your myUEG account, or create one free, to watch it.

Log In Create a free account

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

COMPUTER AIDED QUALITY CONTROL SYSTEM IMPROVES BARRETT’S NEOPLASIA DETECTION IN AN EX-VIVO SETTING

Martijn R. Jong 1, Tim Jaspers 2, Rixta van Eijck van Heslinga 1, Jelmer Jukema 1, Carolus Kusters 2, Tim Boers 2, Roos E. Pouw 3, Lucas Duits 1, Peter H. N. de With 2, Fons van der Sommen 2, Jeroen de Groof 1, Jacques J. Bergman 1

Affiliations

1 Amsterdam UMC, Amsterdam, Netherlands

2 TU Eindhoven, Eindhoven, Netherlands

3 UMC Utrecht, Utrecht, Netherlands

Summary

AI Generated

A computer-aided quality (CAQ) system for Barrett's esophagus endoscopy improved the sensitivity of an existing computer-aided detection system for neoplasia from 82.2% to 89.9% by automatically filtering low-quality images.

The CAQ system was trained on 4,926 images from 243 BE patients to assess objective quality parameters (blurriness, illumination, specular reflections) and subjective parameters (mucosal cleanliness, esophageal expansion), providing real-time feedback to endoscopists.
As a standalone tool, the CAQ system achieved Cohen's Kappa scores of 0.73, 0.91, and 0.89 for objective quality, mucosal cleanliness, and esophageal expansion, respectively, comparable to inter-annotator agreement.
When used as a preprocessing filter for a CADe system, the CAQ system improved sensitivity from 82.2% to 89.9% and AUC from 87.2% to 91.4%, while specificity remained stable at 74.7%.
Validation was performed on 647 images from 51 non-dysplastic BE patients across eight hospitals for standalone quality assessment, and 956 neoplastic and 557 non-dysplastic frames from 12 referral centers for CADe integration testing.
This is the first CAQ system specifically aimed at automated quality control in BE endoscopy, with potential to improve diagnostic accuracy in BE surveillance.

Download PDF

Was this helpful?

Thanks for your feedback.

This summary was generated by an AI large language model based on the content transcript. It is for informational purposes only and should not be considered a substitute for clinical judgment. Always rely on your professional expertise and the full clinical context when making clinical decisions.

Abstract

Introduction

Early detection of neoplasia in Barrett’s Esophagus (BE) remains challenging. Although computer-aided detection (CADe) systems are increasingly available to support endoscopists, successful CADe implementation largely depends on the quality of endoscopic images, which can vary significantly in clinical practice. This study introduces an innovative computer-aided quality (CAQ) system designed for BE endoscopy, capable of assessing various image quality parameters, providing real-time feedback to the endoscopist, and operating in conjunction with an established CADe system.

Aims & Methods

The CAQ system was trained on 4,926 images from 243 BE patients to assess both objective (e.g., blurriness, illumination, and specular reflections) and subjective (i.e., mucosal cleanliness and esophageal expansion) image quality factors. The system is able to provide real-time feedback on these quality parameters to the endoscopist. Additionally, it is configured to function as a preprocessing filter for a previously developed CADe system, automatically excluding lower-quality images. To validate the CAQ system’s performance as a standalone tool, we constructed an endoscopic image quality test set, which included 647 images from 51 non-dysplastic BE patients across eight hospitals. These images were annotated for objective (e.g. motion blur, lighting) and subjective (i.e. esophageal expansion, mucosal cleanliness) image quality parameters by two experts. Additionally, to evaluate the CAQ system’s role as a preprocessing step for an established CADe system, we created the Barrett CADe test set, containing 956 frames from 62 neoplastic BE patients and 557 frames from 35 non-dysplastic BE patients from 12 Barrett referral centers. Outcome measures included agreement scores with experts for standalone image quality assessment and sensitivity, specificity, and Area-under-the-Curve (AUC) for BE neoplasia detection.

Results

As a stand-alone system, the CAQ system achieved Cohen’s Kappa scores for agreement with expert annotators of 0.73, 0.91, and 0.89 for objective image quality parameters, mucosal cleanliness, and esophageal expansion, respectively—comparable to inter-annotator scores of 0.73, 0.93, and 0.83. When used as a preprocessing filter for the CADe system, the CAQ system improved the CADe's sensitivity from 82% to 90% and the AUC from 87% to 91%, while specificity remained stable at 75% (Table 1).

Table 1. Performance of the CADe system for Barrett’s neoplasia detection with and without the CAQ system.

Evaluated by	Sensitivity, %, (95% CI)	Specificity, %, (95% CI)	AUC, %, (95% CI)
CADe	82.2 (79.7 - 84.5)	74.7 (70.9 - 78.1)	87.2 (79.9 - 94.5)
CAQ + CADe	89.9 (87.2 - 92.1)	74.7 (70.0 - 78.9)	91.4 (82.0 - 100)

Conclusion

This study introduces the first CAQ system specifically aimed at automated quality control in BE endoscopy. As a standalone tool, the system effectively distinguishes poorly from well-visualized mucosa. When combined with an established CADe system, it enhances detection rates for neoplasia, highlighting its potential to improve diagnostic accuracy in BE surveillance.

Event

UEG Week Berlin 2025

Topics

Digestive Oncology Endoscopy Oesophagus

Submission format

Abstract

Session

From prediction to detection in upper GI

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

More Like This:

I do underwater resection

Michael John Bourke

Gastric cancer: Individualised surgical and personalised systemic treatment

Aziz Zaanan

10 YEARS OF EUS-GUIDED ENTERO-ENTERAL ENDOSCOPIC BYPASS (EEEB) AND SUBSEQUENT ERC TO TREAT HEPATICO-JEJUNOSTOMY'S ANASTOMOTIC STRICTURES

Marcello Cintolo

Symptomatic gallstones

Philip de Reuver

PROPHYLACTIC ANTIBIOTICS REDUCE POST ENDOSCOPIC RETROGRADE CHOLANGIOPANCREATOGRAPHY INFECTIOUS COMPLICATIONS IN PATIENTS WITH DISTAL MALIGNANT BILIARY OBSTRUCTION: A MULTICENTER PROPENSITY SCORE MATCHED STUDY

Shinya Kawaguchi

TRANSFORMING RADIATION PROCTOPATHY MANAGEMENT: REAL-WORLD EVIDENCE ON PURASTAT FROM A UK TEACHING HOSPITAL

Vinoth Nadesalingam Vinoth Nadesalingam

UEG Presentation

PROPHYLACTIC ANTIBIOTICS REDUCE POST ENDOSCOPIC RETROGRADE CHOLANGIOPANCREATOGRAPHY INFECTIOUS COMPLICATIONS IN PATIENTS WITH DISTAL MALIGNANT BILIARY OBSTRUCTION: A MULTICENTER PROPENSITY SCORE MATCHED STUDY

Log in to continue.

This content is part of Gutflix. Log in with your myUEG account, or create one free, to watch it.

Log In Create a free account

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

PROPHYLACTIC ANTIBIOTICS REDUCE POST ENDOSCOPIC RETROGRADE CHOLANGIOPANCREATOGRAPHY INFECTIOUS COMPLICATIONS IN PATIENTS WITH DISTAL MALIGNANT BILIARY OBSTRUCTION: A MULTICENTER PROPENSITY SCORE MATCHED STUDY

Haruna Takahashi 1, Tatsunori Satoh 1, Yosuke Kobayashi 2, Fumitaka Niiya 3, Junichi Kaneko 4, Kazuma Ishikawa 5, Shinya Kawaguchi 1

Affiliations

1 Shizuoka General Hospital, Shizuoka, Japan

2 Seirei Hamamatsu General Hospital, Shizuoka, Japan

3 Showa University Fujigaoka Hospital, Yokohama, Japan

4 Iwata City Hospital, Shizuoka, Japan

5 Sapporo Medical University, Sapporo, Japan

Summary

AI Generated

Summary is not available for this content yet.

Download PDF

Was this helpful?

Thanks for your feedback.

This summary was generated by an AI large language model based on the content transcript. It is for informational purposes only and should not be considered a substitute for clinical judgment. Always rely on your professional expertise and the full clinical context when making clinical decisions.

Abstract

Introduction

Malignant biliary obstruction (MBO) often necessitates endoscopic retrograde cholangiopancreatography (ERCP) for biliary drainage. Although ERCP is standard treatment, post-procedural infections such as cholangitis and cholecystitis remain clinically important. Current guidelines recommend prophylactic antibiotics only for high-risk cases. Clinically, MBO is categorized into distal malignant biliary obstruction (DMBO) and hilar malignant biliary obstruction (HMBO), depending on whether the obstruction involves the extrahepatic duct or the intrahepatic duct/hilar confluence. While several studies have supported the use of prophylactic antibiotics in HMBO, evidence remains limited for DMBO. This study aimed to evaluate the effect of prophylactic antibiotics on post-ERCP infectious complications in DMBO.

Aims & Methods

We retrospectively reviewed patients who underwent initial ERCP with stent placement for DMBO at five Japanese centers between January 2020 and September 2024. Patients were grouped based on the use or non-use of prophylactic antibiotics for ERCP. Propensity score matching (1:1) was performed using clinically relevant covariates. In addition, a sensitivity analysis was conducted via multivariable logistic regression on the before matched data to further assess the robustness of the findings. The primary outcome was the incidence of infectious complications (cholangitis or cholecystitis) within five days of ERCP.

Results

A total of 508 patients (304 in the antibiotic group, 204 in the non-antibiotic group) were included in the study. After PSM, 165 patients were selected for each group. Characteristics of the antibiotic vs. non-antibiotic groups included: median age 74 years in both groups; sex 92 (55.8%) males vs. 94 (57.0%) males; pancreatic cancer 129 (77.2%) cases vs. 133 (79.6%) cases; plastic stents 72 (43.6%) cases vs. 69 (41.8%) cases.
In the matched population, the incidence of overall infectious complications (cholangitis or cholecystitis) was significantly lower in the prophylactic antibiotic group than in the non-antibiotic group (3.6% vs. 10.3%; risk difference (RD), 6.7%; p=0.029), corresponding to a number needed to treat (NNT) of 14.9. No significant difference was observed in the rate of post-ERCP pancreatitis: 10 patients (6.1%) in the non-antibiotic group and 16 patients (9.7%) in the antibiotic group (p = 0.307). Sensitivity analysis using multivariable logistic regression confirmed that absence of prophylactic antibiotics was independently associated with a higher risk of infectious complications (odds ratio: 2.45, 95% confidence interval: 1.22–4.92).

After mating cohort	Without antibiotics (n = 165)	With antibiotics (n=165)	Risk difference (%)	NNT	Risk ratio	P value
Infectious complications	17 (10.3)	6 (3.6)	6.7 (1.2 - 12.1)	14.9 (8.3-83.3)	2.83 (1.15 - 7.01)	0.029
mild/ moderate	9/8	3/3
Cholangitis	13 (7.9)	4 (2.4)	5.5 (0.7 - 10.2)	18.2 (9.8-142.9)	3.25 (1.08 - 9.76)	0.043
mild/ moderate	9/4	3/1
Cholecystitis	4 (2.4)	2 (1.2)	1.2 (-1.7 - 4.1)	83.3 (24.4-∞)	2.00 (0.37 - 10.77)	0.685
mild/ moderate	0/4	0/2

Conclusion

Prophylactic antibiotics significantly reduce post-ERCP infectious complications in patients with DMBO.

Event

UEG Week Berlin 2025

Topics

Endoscopy Hepatobiliary

Submission format

Abstract

Session

Endoscopic solutions to malignant biliary obstruction

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

More Like This:

I do underwater resection

Michael John Bourke

Gastric cancer: Individualised surgical and personalised systemic treatment

Aziz Zaanan

10 YEARS OF EUS-GUIDED ENTERO-ENTERAL ENDOSCOPIC BYPASS (EEEB) AND SUBSEQUENT ERC TO TREAT HEPATICO-JEJUNOSTOMY'S ANASTOMOTIC STRICTURES

Marcello Cintolo

Symptomatic gallstones

Philip de Reuver

PROPHYLACTIC ANTIBIOTICS REDUCE POST ENDOSCOPIC RETROGRADE CHOLANGIOPANCREATOGRAPHY INFECTIOUS COMPLICATIONS IN PATIENTS WITH DISTAL MALIGNANT BILIARY OBSTRUCTION: A MULTICENTER PROPENSITY SCORE MATCHED STUDY

Shinya Kawaguchi

TRANSFORMING RADIATION PROCTOPATHY MANAGEMENT: REAL-WORLD EVIDENCE ON PURASTAT FROM A UK TEACHING HOSPITAL

Vinoth Nadesalingam Vinoth Nadesalingam

Group	n	Symptom Relief	Mean Repeat Sessions
De novo PuraStat	50	100%	1.3
APC→PuraStat	50	100%	1.5

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

Most popular content

Rate for better recommendations!

COMPUTER AIDED QUALITY CONTROL SYSTEM IMPROVES BARRETT’S NEOPLASIA DETECTION IN AN EX-VIVO SETTING

I do underwater resection

Gastric cancer: Individualised surgical and personalised systemic treatment

10 YEARS OF EUS-GUIDED ENTERO-ENTERAL ENDOSCOPIC BYPASS (EEEB) AND SUBSEQUENT ERC TO TREAT HEPATICO-JEJUNOSTOMY'S ANASTOMOTIC STRICTURES

Symptomatic gallstones

PROPHYLACTIC ANTIBIOTICS REDUCE POST ENDOSCOPIC RETROGRADE CHOLANGIOPANCREATOGRAPHY INFECTIOUS COMPLICATIONS IN PATIENTS WITH DISTAL MALIGNANT BILIARY OBSTRUCTION: A MULTICENTER PROPENSITY SCORE MATCHED STUDY

TRANSFORMING RADIATION PROCTOPATHY MANAGEMENT: REAL-WORLD EVIDENCE ON PURASTAT FROM A UK TEACHING HOSPITAL