Endoscopic Severity Image Recognition to Advance Research and Training in Inflammatory Bowel Disease (EVEREST - IBD)

Recruiting

• Conditions: Inflammatory Bowel Disease 1

• Registration Number: NCT04867408
• Lead Sponsor: Hull University Teaching Hospitals NHS Trust

Brief Summary

To develop and train a convolutional neural network to detect and characterize disease severity of inflammatory bowel disease during endoscopy

Detailed Description

To develop and train a Convolutional Neural Network to detect and characterize disease severity in inflammatory bowel disease during endoscopy. This initiative will inevitably establish a high-quality large image database. Our secondary study aims are therefore to use the images we collect to advance the field of deep learning and computer aided diagnosis in inflammatory bowel disease by establishing an image database. This will involve developing a framework combining deep learning and computer vision algorithms. The ultimate aim is to use the image database to produce high impact research outcomes and training resources leading to an improvement in the quality of endoscopy performed, reduce inter-observer variability in disease assessment and a reduction in missed bowel cancer rates and associated mortality.

Study Timeline

• Study First Submitted: 2021-04-27
• Study First Submitted QC: 2021-04-27
• Study First Posted: 2021-04-30
• Study Start: 2021-09-17
• Status Verified: 2024-11
• Last Update Submitted: 2024-11-14
• Last Update Posted: 2024-11-15
• Primary Completion: 2031-09
• Study Completion: 2031-09

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 4000

Inclusion Criteria

• • Any adult patient aged 16 years or older who has consented to undergo endoscopic investigation where images are captured as part of routine clinical care.

Exclusion Criteria

• • Any patient under the age of 16

  • Patients who are unable to give informed consent to undergo endoscopic investigation or those who do not wish their pseudo-anonymised images to be used

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
To develop and train a convolutional neural network to detect and characterise disease severity of inflammatory bowel disease during endoscopy	5 years	To develop and train a convolutional neural network to detect and characterise disease severity of inflammatory bowel disease during endoscopy

Secondary Outcome Measures

Name	Time	Method
a) To explore whether Artificial Intelligence can predict response to IBD therapies	5 years	To explore whether Artificial Intelligence can predict response to IBD therapies
b) To develop an endoscopic image repository to advance training and standardisation in endoscopic detection and characterisation of IBD.	5 years	b) To develop an endoscopic image repository to advance training and standardisation
e) To develop deep learning algorithms and computer vision techniques to allow for automated measurement of quality metrics in endoscopy for IBD	5 years	To develop deep learning algorithms and computer vision techniques to allow for automated measurement of quality metrics in endoscopy for IBD
c) To develop and assess methodologies for training and quality assurance of IBD diagnostic endoscopy	5 years	To develop and assess methodologies for training and quality assurance of IBD
d) To evaluate comparisons in endoscopic image interpretation between endoscopist's	5 years	To evaluate comparisons in endoscopic image interpretation between endoscopist's
f) To create a future robust research platform to ensure the above objectives are continuously developed as novel imaging techniques emerge over time.	5 years	To create a future robust research platform to ensure the above objectives are continuously developed as novel imaging techniques emerge over time.

Trial Locations

Locations (1)

Hull Royal Infirmary; 🇬🇧 Hull, East Yorkshire, United Kingdom