Performance Evaluation of CAD-EYE and SCALE-EYE for Detection, Classification, and Measurement of Colorectal Polyps: a Prospective Study
Study Details
Study Description
Brief Summary
The investigators hypothesize that the clinical implementation of an AI system is an optimal tool to monitor, audit and improve the detection and classification of polyps during colonoscopy. The purpose of this prospective clinical cohort study is to evaluate the performance of the SCALE-EYE virtual scale for measuring polyp size when used during live colonoscopies. The investigators also wish to evaluate CAD-eye for detection and classification of polyp histology. It is hypothesized that CAD-eye and SCALE-EYE can function in real-time practice with high accuracy.
| Condition or Disease | Intervention/Treatment | Phase |
|---|---|---|
|
Phase 1 |
Study Design
Arms and Interventions
| Arm | Intervention/Treatment |
|---|---|
| Experimental: Artificial intelligence for real-time detection and monitoring of colorectal polyps A standard colonoscopy will be performed according to the standard of routine care. Patients will undergo colonoscopies using the CAD-eye and Scale-eye. All optically diagnosed polyps will be removed and sent to the CHUM pathology laboratory for histopathological evaluation according to institutional standards. |
Diagnostic Test: Detection and classification and size measurement of polyp by Artificial Intelligence (Cad eye) and the Scale Eye
This study will be conducted in two phases: phase 1 (pilot phase, n=40 patients) to evaluate the feasibility of applying CAD-eye in real-time practice, training endoscopists to work with this platform, and determining the sample size and reference standard to evaluate SCALE-EYE during the second phase of the study, and phase 2 to evaluate the performance of SCALE-EYE and CAD-eye in real-time practice.
|
| No Intervention: Real time polyp detection using a standard colonoscopy without CAD eye A standard colonoscopy will be performed according to the standard of routine care. Patients will undergo a standard colonoscopy. The polyp detection and classification will be done by endoscopist. All optically diagnosed polyps will be removed and sent to the CHUM pathology laboratory for histopathological evaluation according to institutional standards. |
Outcome Measures
Primary Outcome Measures
- Evaluation of the Scale-Eye [30 days]
mean size difference between SCALE-EYE, visual assessment when compared with the gold standard of caliper measurement of the resected polyp outside the body immediately after resection.
- Evaluation of the Scale-Eye [1 day]
compare the size measured by the endoscopists and the Napoleon endoscopic ruler with the size measured by the microscope reticle scale as the reference.
- Evaluation of the Scale-Eye [30 days]
accuracy of determining large polyp size (<10mm vs ≥10mm) for polyps 1-20mm; accuracy of determining diminutive polyp size (<6mm vs ≥6mm) for polyps 1-10mm
Secondary Outcome Measures
- Evaluation of the Scale-Eye [30 days]
proportion of correct measurement (1mm) between SCALE-EYE, visual assessment when compared with the gold standard of caliper measurement of the resected polyp outside the body immediately after resection (defined as proportion of size measurements that fall within +/- 1mm of gold standard polyp size)
- The evaluation of the artificial intelligence assisted polyp detection [30 days]
polyp detection rate (PDR); Advanced adenoma detection rate (AADR) defined as the proportion of patients where at least one of the following is detected: Adenoma ≥10mm, Tubulovillous adenoma, Villous adenoma, High grade dysplasia
- The evaluation of the artificial intelligence assisted polyp detection [30 days]
Serrated detection rate (SDR): defined as the proportion of patients where at least one serrated polyp (sessile serrated lesion, traditional serrated adenoma, ≥10mm hyperplastic polyp) is detected; mean number of adenoma per patient
- The evaluation of the artificial intelligence assisted polyp detection [30 days]
the proportion of polyps that the CAD-eye could detect and the endoscopists missed. We will calculate the proportion of patients with 10y, 7-10y, 5-10y, 3-5y, and 3y surveillance intervals for each group.
- The evaluation of the artificial intelligence assisted polyp classification [30 days]
the accuracy in distinguishing between adenomas and hyperplastic polyps for the CADx group vs Endoscopist (with awareness of CADx diagnosis) group.
- The evaluation of the artificial intelligence assisted polyp classification [30 days]
diagnostic performance of the CADx (sensitivity, specificity, positive predictive value, negative predictive value) for the diagnosis of adenoma vs hyperplastic polyps for 1-3mm and 1-5mm polyps.
- The evaluation of the artificial intelligence assisted polyp classification [30 days]
the agreement between the surveillance intervals based on the optical diagnosis of polyps with the CADx or endoscopist, and the pathology-based recommendation according to current guidelines
Other Outcome Measures
- A pilot feasibility study using the first 40 recruited patients for determining the best reference for evaluating the SCALE-EYE performance [30 days]
to evaluate the feasibility of the CAD-eye in real-time practice and educating the staff endoscopists to use it; to evaluate the proportion of the polyps that can be excised in whole; this will help calculate the sample size for the second phase of the study, in which the performance of the SCALE-EYE virtual scale will be evaluated; to determine the reference standard for evaluating the SCALE-EYE performance by comparing initial visual assessment performance to caliper measurement of the excised polyp.
Eligibility Criteria
Criteria
Inclusion Criteria:
-
indication of undergoing a screening, surveillance, or diagnostic colonoscopy
-
Age 45-80 years
-
Signed informed consent
Exclusion Criteria:
-
Known inflammatory bowel disease (IBD)
-
Active Colitis
-
Poor general health, defined as an American Society of Anesthesiologists (ASA) physical status class >3
-
Coagulopathy
-
Familial polyposis syndrome
-
Emergency colonoscopies
-
Poor bowel preparation score defined as the total Boston bowel preparation score <6 and the right-segment score <2.
For per-polyp analysis:
-
For optical diagnosis (CADx) we will exclude all polyps >5mm. We will also exclude sessile serrated polyps and traditional serrated adenomas from the analysis as CADx can only differentiate between adenomas and hyperplastic polyps.
-
For polyp size measurement (SCALE-EYE), we will exclude all polyps resected in several pieces (piecemeal resection), or specimens damaged (e.g., fractured) during the suction and retrieval process, submillimeter polyps too small for measurement after resection. Polyps after the 5th resected polyp in a single piece will be excluded to reduce the time associated with the procedure.
-
For polyp detection (CADe) we will not exclude any polyp from the analysis.
Contacts and Locations
Locations
| Site | City | State | Country | Postal Code | |
|---|---|---|---|---|---|
| 1 | Centre Hospitalier Universitaire de Montréal | Montréal | Quebec | Canada |
Sponsors and Collaborators
- Centre hospitalier de l'Université de Montréal (CHUM)
Investigators
None specified.Study Documents (Full-Text)
None provided.More Information
Publications
None provided.- 21.305