Colonoscopy, Colorectal Neoplasms, Deep Learning, Intestinal Polyps
Conditions
Keywords
Colonoscopy, Colorectal Neoplasms, Computer aided diagnosis, Deep Learning
Brief summary
Artificial Intelligence (AI) to predict the histology of polyps per colonoscopy, offers a promising solution to reduce variation in colonoscopy performance. This new and innovative non-invasive technology will improve the quality of screening colonoscopies, and reduce the costs of colorectal cancer screening. The aim of the study is to performed a cross-sectional, multi-center study evaluating the diagnostic performance of the CAD EYE automatic characterization system for the histology of colonic polyps in colorectal cancer screening colonoscopy.
Detailed description
Deep learning to predict the histology of polyps per colonoscopy, offers a promising solution to reduce variation in colonoscopy performance. Meanwhile, the concept of 'optical biopsy' where in vivo classification of polyps based on enhanced imaging replaces histopathology has not been incorporated into routine practice, largely limited by inter-observer variability and generally meeting accepted standards only in expert settings. Real-time decision support software has been developed to detect and characterise polyps, whilst also offering feedback on the technical quality of inspection. This study will evaluate the performance of the CAD EYE automatic characterization system for the histology compared to histological analysis. And secondary aims : the diagnostic performance of the CAD EYE automated detection device compared to a standardized video recording with blind independent review. Procedure: The screening colonoscopy will be performed by an investigator. The automatic detection and characterization system will be activated at the time of descent of the colonoscopy (after caecal intubation), with video recording (image without CAD EYE and image with CAD EYE). The investigator performing the colonoscopy will be blinded by the results of the CAD EYE. Follow-up: no specific follow-up is planned after colposcopy
Interventions
DEVICEscreening colonoscopy
The screening colonoscopy will be performed by an investigator. The automatic detection and characterization system will be activated at the time of descent of the colonoscopy (after caecal intubation), with video recording (image without CAD EYE and image with CAD EYE). The investigator performing the colonoscopy will be blinded by the results of the CAD EYE.
Sponsors
University Hospital, Bordeaux
Study design
Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
DIAGNOSTIC
Masking
NONE
Intervention model description
Patients with indication for colonoscopy as part of a screening colonoscopy.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Patients over 18 years of age with indication for colonoscopy as part of a screening colonoscopy, after a positive immunological test, and/or for personal or family history of colon cancer (before 60 years), personal history of colonic adenoma. * Patient with at least one polyp detected, resect and removed during colonoscopy, for histological analysis
Exclusion criteria
* Guardianship or protection, * pregnancy, * not fluent in French or illiterate, * lack of health care
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Estimation of the sensitivity of the automatic characterization system CAD EYE. | Inclusion date (date of the colonoscopy) | Estimation of the sensitivity of the automatic characterization system CAD EYE for the diagnosis of the malignant character of colonic polyps. The sensitivity is calculated as the proportion of polyps detected by the CAD EYE characterization system among all the polyps that will be classified as malignant by the pathological analysis.The sensitivity estimate will be accompanied by its two-sided 95% confidence interval according to the exact binomial distribution. The estimated proportion will be compared with the theoretical value of 85% (minimum level from which this new technique is considered to be of interest) by a unilateral Chi2 test if the validity conditions are met or by an exact Fisher test, at 2.5% alpha threshold. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Estimation of the CAD EYE specificity | Inclusion date (date of the colonoscopy) | proportion of polyps not detected by the CAD EYE characterization system among all polyps that will be classified as benign by pathological analysis calculated, as with two-sided 95% confidence interval according to the exact binomial distribution |
| Comparison of the average number of polyps detected per patient between a colonoscopy assisted by the CAD EYE system and a colonoscopy performed without this assistance. | Inclusion date (date of the colonoscopy) | the average number of polyps detected per patient with the CAD EYE system will be compared to that observed by the investigator performing the colorectal cancer screening colonoscopy using a Student's t test or Wilcoxon rank test according to the distribution of the judgment criterion. |
| Compare the diagnostic performance to determine the malignancy of polyps between the automated colonic polyp detection device by the CAD EYE system, and the investigator performing the colonoscopy for colorectal cancer screening. | Inclusion date (date of the colonoscopy) | the reference test is the pathological examination of colonic polyps. The sensitivity of the CAD EYE system will be compared to that observed with the investigator performing the colonoscopy for colorectal cancer screening using a Chi2 test or Fisher's exact test (depending on the conditions of validity of the tests). |
Countries
France
Outcome results
None listed