Artificial intelligence for dysplasia detection during surveillance colonoscopy in patients with ulcerative colitis: A cross-sectional, non-inferiority, diagnostic test comparison study

Abstract

Background and study aim

High-definition virtual chromoendoscopy, along with targeted biopsies, is recommended for dysplasia surveillance in ulcerative colitis patients at risk for colorectal cancer. Computer-aided detection (CADe) systems aim to improve colonic adenoma detection, however their efficacy in detecting polyps and adenomas in this context remains unclear. This study evaluates the CADe Discovery™ system's effectiveness in detecting colonic dysplasia in ulcerative colitis patients at risk for colorectal cancer.

Patients and methods

A prospective cross-sectional, non-inferiority, diagnostic test comparison study was conducted on ulcerative colitis patients undergoing colorectal cancer surveillance colonoscopy between January 2021 and April 2021. Patients underwent virtual chromoendoscopy (VCE) with iSCAN 1 and 3 with optical enhancement. One endoscopist, blinded to CADe Discovery™ system results, examined colon sections, while a second endoscopist concurrently reviewed CADe images. Suspicious areas detected by both techniques underwent resection. Proportions of dysplastic lesions and patients with dysplasia detected by VCE or CADe were calculated.

Results

Fifty-two patients were included, and 48 lesions analyzed. VCE and CADe each detected 9 cases of dysplasia (21.4% and 20.0%, respectively; p = 0.629) in 8 patients and 7 patients (15.4% vs. 13.5%, respectively; p = 0.713). Sensitivity, specificity, positive and negative predictive values, and diagnostic accuracy for dysplasia detection using VCE or CADe were 90% and 90%, 13% and 5%, 21% and 2%, 83% and 67%, and 29.2% and 22.9%, respectively.

Conclusions

The CADe Discovery™ system shows similar diagnostic performance to VCE with iSCAN in detecting colonic dysplasia in ulcerative colitis patients at risk for colorectal cancer.

Resumen

Antecedentes y objetivo

La cromoendoscopia virtual (CEV) de alta definición se recomienda para la vigilancia de displasias en pacientes con colitis ulcerosa y riesgo de cáncer colorrectal. Los sistemas de detección por computadora (CADe) buscan mejorar la detección de adenomas colónicos, pero su eficacia en este contexto aún no está definida. Se evalúa la eficacia del sistema CADe Discovery^TM para detectar displasias colónicas en estos pacientes.

Pacientes y métodos

Estudio prospectivo de comparación de pruebas diagnósticas de no inferioridad, transversal, en pacientes con colitis ulcerosa sometidos a colonoscopia de vigilancia entre enero de 2021 y abril de 2021. Se realizó una CEV con iSCAN 1 y 3 con realce óptico. Un endoscopista examinó el colon en secciones, mientras otro revisó las imágenes CADe. Las áreas sospechosas detectadas por ambas técnicas fueron resecadas. Se calcularon las proporciones de lesiones displásicas y de pacientes con displasia detectados por VCE o CADe.

Resultados

Se analizaron 48 lesiones en 52 pacientes. VCE y CADe detectaron 9 casos de displasia cada uno (21,4 y 20,0%, respectivamente; p = 0,629) en 8 y 7 pacientes (15,4 vs. 13,5%, respectivamente; p = 0,713). Sensibilidad, especificidad, valores predictivos positivo y negativo, y precisión diagnóstica para detectar displasia utilizando VCE o CADe fueron del 90 y 90%, 13 y 5%, 21 y 2%, 83 y 67%, y 29,2 y 22,9%, respectivamente.

Conclusiones

El sistema CADe Discovery^TM muestra un rendimiento diagnóstico similar al de CEV con iSCAN en la detección de displasias colónicas en pacientes con colitis ulcerosa de riesgo de cáncer colorrectal.