Polyp Histology Prediction by Artificial Intelligence

Colorectal Polyp Histology Prediction by Artificial Ingelligence Method Based on NBI Colonoscopy Images.

We have been developing artificial intelligence based polyp histology prediction (AIPHP) method to classify Narrow Band Imaging(NBI) colonoscopy images to predict the hyperplastic or neoplastic histology of polyps.

We plan to study colonoscopy polyp samples taken by polypectomy from 1200 patients.The documented NBI still images will be analyzed by the AIPHP method and by the NICE classification parallel.Our aim is to analyze the accuracy of AIPHP and NBI classification based histology predictions and also compare the results of the two methods.

Study Overview

• Status: Not yet recruiting
• Conditions: Colorectal Polyp
• Intervention / Treatment: Diagnostic test: colonoscopy,polypectomy

Detailed Description

Background:

Colonoscopy with polypectomy or early colorectal neoplastic lesions (polyp) is a proven and widely accepted method of reducing colorectal cancer mortality rates.

Predicting histology prior to endoscopic colorectal polyp removal is useful especially for diminutive (1-5mm) and small (6-10mm ) polyps.

Evaluation of colorectal polyps using the narrow-band imaging (NBI) technique and the NBI International Colorectal Endoscopic (NICE) classification are useful to predict the histology during endoscopy.However, NBI and magnification based polyp histology prediction needs training and endoscopic experience. Morever , the final and objective diagnosis still requires histology.

Therefore,we have been developing arteficial intelligence-based polyp histology prediction (AIPHP) software to automatically evaluate the magnified NBI colonoscopy images aiming the histology prediction of polyps.

Materials and methods:

We plan to examine 1200 colorectal polyps obtained from patients. Polyps will be removed by traditional polypectomy or with mucosectomy.Endoscopic procedures and histological examinations performed at the participation hospitals. Colonoscopy will be performed with Olympus EXERA III CFHQ190I (Olympus ,Tokyo,Japan) high reolution NBI colonoscopes providing 65x optical magnification. Colorectal polyps will be detected first by high definition colonoscopy then by NBI at the optical maximum magnification (65x). All studied polyps will be photo-documented. The stored NBI photos were anelyzed by the NICE classification and AIPHP parallel system.

Histological examination methods:

We use WHO classification of colorectal polyps. The two -class classification will considere hyperplastic or neoplastic ((SSLs,tubular or villous adenomas, and invasive adenocarcinomas).

AIPHP software systtem:

The AIPHP software is based on the categorization of the vascular pattern and color of the polyps.The main steps of AIPHP software development will be the following: 1) feature vector calculation 2) training of classifier module, and 3) AIPHP classifier testing. Five features will be used by our AIPHP software.

• Study Type: Observational
• Enrollment (Anticipated): 1200

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 85 years (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

patients with colorectal polyps detected by colonoscopy

Description

Inclusion Criteria:

• colorectal polyps removed by polypectomy

Exclusion Criteria:

• colorectal polyps with IBD

Study Plan

How is the study designed?

Number of groups / cohorts

6

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
colonoscopy group1; Polypectomy, histological examination, NICE classification and AIPHP analyzis will be performed 200 patients.	Diagnostic test: colonoscopy,polypectomy; polyp removal during colonoscopy
colonoscopy group 2; Polypectomy, histological examination, NICE classification and AIPHP analyzis will be performed 200 patients	Diagnostic test: colonoscopy,polypectomy; polyp removal during colonoscopy
colonoscopy group 3; Polypectomy, histological examination, NICE classification and AIPHP analyzis will be performed 200 patients	Diagnostic test: colonoscopy,polypectomy; polyp removal during colonoscopy
colonoscopy group 4; Polypectomy, histological examination, NICE classification and AIPHP analyzis will be performed 200 patients	Diagnostic test: colonoscopy,polypectomy; polyp removal during colonoscopy
colonoscopy group 5; Polypectomy, histological examination, NICE classification and AIPHP analyzis will be performed 200 patients	Diagnostic test: colonoscopy,polypectomy; polyp removal during colonoscopy
colonoscopy group 6; Polypectomy, histological examination, NICE classification and AIPHP analyzis will be performed 200 patients	Diagnostic test: colonoscopy,polypectomy; polyp removal during colonoscopy

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Polyp histology accuracy by AI method	polyp histology prediction by AI	two weeks

Collaborators and Investigators

• Sponsor: Petz Aladar County Teaching Hospital

Study record dates

Study Major Dates

• Study Start (ANTICIPATED): October 31, 2022
• Primary Completion (ANTICIPATED): December 31, 2023
• Study Completion (ANTICIPATED): March 31, 2024

Study Registration Dates

• First Submitted: September 14, 2022
• First Submitted That Met QC Criteria: September 14, 2022
• First Posted (ACTUAL): September 19, 2022

Study Record Updates

• Last Update Posted (ACTUAL): September 22, 2022
• Last Update Submitted That Met QC Criteria: September 20, 2022
• Last Verified: September 1, 2022

More Information

Terms related to this study

• Keywords: colorectal polyp,histology,artificial intelligence
• Additional Relevant MeSH Terms: Pathological Conditions, Anatomical; Polyps
• Other Study ID Numbers: PetzACTH2

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No