Diagnostic Performance of a Convolutional Neural Network for Diminutive Colorectal Polyp Recognition

NCT ID: NCT03822390

Last Updated: 2021-12-29

Basic Information

• Recruitment Status: COMPLETED
• Total Enrollment: 292 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2018-10-16
• Study Completion Date: 2021-10-16

Brief Summary

Rationale: Diminutive colorectal polyps (1-5mm in size) have a high prevalence and very low risk of harbouring cancer. Current practice is to send all these polyps for histopathological assessment by the pathologist. If an endoscopist would be able to correctly predict the histology of these diminutive polyps during colonoscopy, histopathological examination could be omitted and practise could become more time- and cost-effective. Studies have shown that prediction of histology by the endoscopist remains dependent on training and experience and varies greatly between endoscopists, even after systematic training. Computer aided diagnosis (CAD) based on convolutional neural networks (CNN) may facilitate endoscopists in diminutive polyp differentiation. Up to date, studies comparing the diagnostic performance of CAD-CNN to a group of endoscopists performing optical diagnosis during real-time colonoscopy are lacking.

Objective: To develop a CAD-CNN system that is able to differentiate diminutive polyps during colonoscopy with high accuracy and to compare the performance of this system to a group of endoscopist performing optical diagnosis, with the histopathology as the gold standard.

Study design: Multicentre, prospective, observational trial. Study population: Consecutive patients who undergo screening colonoscopy (phase 2)

Main study parameters/endpoints: The accuracy of optical diagnosis of diminutive colorectal polyps (1-5mm) by CAD-CNN system compared with the accuracy of the endoscopists. Histopathology is used as the gold standard.

Conditions

Artificial Intelligence; Colorectal Polyp

Keywords

Artificial Intelligence; Computer aided diagnosis; Diminutive colorectal polyps; Optical diagnosis

Study Design

• Observational Model Type: COHORT
• Study Time Perspective: PROSPECTIVE

Study Groups

Patients

Patients older than 18 years undergoing colonoscopy in one the participating centres.

CAD-CNN system

Intervention Type: DEVICE

The CAD-CNN system will be trained in predicting the histology of diminutive polyps. Before training, the dataset will be split up into a training set and a test set. To ensure a completely independent test and training set there will be no overlap between patients (i.e. if polyps from a patient A is present in the training set it cannot be in the test set as well).

Interventions

CAD-CNN system

The CAD-CNN system will be trained in predicting the histology of diminutive polyps. Before training, the dataset will be split up into a training set and a test set. To ensure a completely independent test and training set there will be no overlap between patients (i.e. if polyps from a patient A is present in the training set it cannot be in the test set as well).

Intervention Type: DEVICE

Eligibility Criteria

Inclusion Criteria

All patients older than 18 years old undergoing screenings colonoscopy in one of the participating centres.

Exclusion Criteria

• Diagnosis of inflammatory bowel disease, Lynch syndrome or (serrated) polyposis syndrome.
• Boston Bowel Preparation Scale (BBPS) <2 in one of the colon segments
• Patients who are unwilling or unable to give informed consent

• Minimum Eligible Age: 18 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Bergman Clinics

OTHER

Sponsor Role: collaborator

Frisius Medisch Centrum

OTHER

Sponsor Role: collaborator

Academisch Medisch Centrum - Universiteit van Amsterdam (AMC-UvA)

OTHER

Sponsor Role: lead

Responsible Party

Prof. Evelien Dekker, MD, PhD

Prof. E. Dekker, MD, PhD

Responsibility Role: PRINCIPAL_INVESTIGATOR

Principal Investigators

Evelien NA Dekker, Msc

Role: PRINCIPAL_INVESTIGATOR

Amsterdam UMC, location VUmc

Locations

Academic Medical Centre

Amsterdam, North Holland, Netherlands

Countries

Netherlands

References

Houwen BBSL, Hazewinkel Y, Giotis I, Vleugels JLA, Mostafavi NS, van Putten P, Fockens P, Dekker E; POLAR Study Group. Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists. Endoscopy. 2023 Aug;55(8):756-765. doi: 10.1055/a-2009-3990. Epub 2023 Jan 9.

Reference Type: DERIVED

PMID: 36623839 (View on PubMed)

Houwen BBSL, Hartendorp F, Giotis I, Hazewinkel Y, Fockens P, Walstra TR, Dekker E; POLAR study group; *on behalf of the POLAR study group. Computer-aided classification of colorectal segments during colonoscopy: a deep learning approach based on images of a magnetic endoscopic positioning device. Scand J Gastroenterol. 2023 Jun;58(6):649-655. doi: 10.1080/00365521.2022.2151320. Epub 2022 Dec 2.

Reference Type: DERIVED

PMID: 36458659 (View on PubMed)

Other Identifiers

W18_422

Identifier Type: -

Identifier Source: org_study_id