Artificial-intelligence-based QUAntification of Size measuremeNts of Adenoma in Routine Endoscopy

NCT06040710 | Completed

• 1 other identifier: AI02
• Study Type: observational
• Target: 145
• Locations: 1 country
• Sites: 1

Brief Summary

Polyp size and count determines the follow-up intervals after colonoscopy. However, relying on the endoscopist's optical diagnosis for size estimation has shown considerable variability, leading to erroneous surveillance intervals and increased colorectal cancer risk. This study aims to assess the effectiveness of a new polyp size estimation software, called POSEIDON, which uses the tip of the auxiliary water-jet as reference and is implemented together with the EndoMind polyp detection system.

Conditions

Colorectal Polyp; Colorectal Adenoma

Keywords

Polyp Size; Colorectal Polyp; Artificial Intelligence; Endoscopy; Follow-up interval

Outcome Measures

Primary Outcomes (1)

• Error of size estimation for colorectal polyps using POSEIDON versus physician optical evaluation

  The error between gold standard polyp size and estimation using POSEIDON and optical estimation will be compared in pairs for the same polyps.

  Through study completion, an average of 5 months

Secondary Outcomes (4)

• Error of size estimation for colorectal polyps using POSEIDON versus physician optical evaluation for different size categories

  Through study completion, an average of 5 months

• Error of size estimation for colorectal polyps using POSEIDON versus physician optical evaluation for polyps with different histologies

  Through study completion, an average of 5 months

• Rate of change in guideline-suggested follow-up interval based purely on detected polyp size.

  Through study completion, an average of 5 months

• Percentage of polyps where endoscopists failed to obtain POSEIDON measurement.

  Through study completion, an average of 5 months

Study Arms (1)

Experimental: Intervention arm

All patients within the study are included in the intervention arm: polyp detected within these patients will be measured according to the study protocol using two different methods.

Device: POSEIDON size estimation software with the EndoMind polyp detection system

Interventions

POSEIDON size estimation software with the EndoMind polyp detection system DEVICE

Polyp size estimation using the POSEIDON software and bounding boxes of the EndoMind polyp detection system.

Experimental: Intervention arm

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adult patients (\>18 years), scheduled for screening, surveillance, or diagnostic colonoscopy

You may qualify if:

• Adult patients
• Scheduled for colonoscopy

You may not qualify if:

• Patient Level:
• Inflammatory Bowel Disease
• Familiar Polyposis Syndrome
• Data Level
• Failure to initialize system before examination
• Missing image instrument placed next to polyp to obtain gold standard

Sponsors & Collaborators

• Wuerzburg University Hospital: lead

Study Sites (1)

Universitätsklinikum Würzburg

Würzburg, Bavaria, 97080, Germany

Location

Related Publications (2)

• Lux TJ, Banck M, Sassmannshausen Z, Troya J, Krenzer A, Fitting D, Sudarevic B, Zoller WG, Puppe F, Meining A, Hann A. Pilot study of a new freely available computer-aided polyp detection system in clinical practice. Int J Colorectal Dis. 2022 Jun;37(6):1349-1354. doi: 10.1007/s00384-022-04178-8. Epub 2022 May 11.

  PMID: 35543874 BACKGROUND

• Sudarevic B, Sodmann P, Kafetzis I, Troya J, Lux TJ, Sassmannshausen Z, Herlod K, Schmidt SA, Brand M, Schottker K, Zoller WG, Meining A, Hann A. Artificial intelligence-based polyp size measurement in gastrointestinal endoscopy using the auxiliary waterjet as a reference. Endoscopy. 2023 Sep;55(9):871-876. doi: 10.1055/a-2077-7398. Epub 2023 Apr 20.

  PMID: 37080235 BACKGROUND

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: September 8, 2023
• First Posted: September 15, 2023
• Study Start: February 14, 2024
• Primary Completion: March 28, 2024
• Study Completion: March 28, 2024
• Last Updated: May 23, 2025

Record last verified: 2025-05

Data Sharing

• IPD Sharing: Will not share

Locations

DE (1)