Performance of Computer-Aided Detection and Diagnosis of Colorectal Polyps Compares to That of Experienced Endoscopists

• Published in: Digestive diseases and sciences 2022-08, Vol.67 (8), p.3976-3983
• Main Authors: Sakamoto, Taku, Nakashima, Hirotaka, Nakamura, Keiko, Nagahama, Ryuji, Saito, Yutaka
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Biochemistry; Cancer; Colonoscopy; Consent; Endoscopy; Gastroenterology; Hepatology; Image databases; Lasers; Light emitting diodes; Medical centers; Medical diagnosis; Medical screening; Medicine; Medicine & Public Health; Mortality; Oncology; Original Article; Polyps; Polyps (Pathology); Transplant Surgery; Tumors; Validation studies
• ISSN: 0163-2116; 1573-2568
• DOI: 10.1007/s10620-021-07217-6

Background Differential diagnosis of neoplasms and non-neoplasms is crucial in ensuring appropriate and proper medical management for patients undergoing colonoscopy. Diagnostic ability can vary, depending on the colonoscopist’s experience. To overcome this issue, artificial intelligence (AI) may be effective. Aims To assess the performance of a computer-aided detection (CADe) and a computer-aided diagnosis (CADx) system for the detection and characterization of colorectal polyps by comparing their data with those of experienced endoscopists. Methods This retrospective, still image-based validation study was conducted at three Japanese medical centers. A total of 579 white-light images (WLIs) and 605 linked color images (LCIs) were used for testing the CADe and 308 WLIs and 296 blue laser/light images (BLIs) for testing the CADx. The performances of the CADe and CADx systems were assessed and compared with the correct answers provided by three experienced endoscopists. Results CADe in WLI demonstrated a sensitivity of 94.5% (95% confidence interval (CI), 92.0–96.9%) and a specificity of 87.2% (84.5–89.9%). CADe in LCI demonstrated a sensitivity of 96.0% (93.9–98.1%) and a specificity of 85.1% (82.3–87.9%). CADx in WLI demonstrated a sensitivity of 95.5% (92.9–98.1%) and a specificity of 84.4% (73.4–91.5%), resulting in an accuracy of 93.2% (90.4–96.0%). CADx in BLI showed a sensitivity of 96.3% (93.9–98.7%) and a specificity of 88.7% (77.1–95.1%), resulting in an accuracy of 94.9% (92.4–97.4%). Conclusions CADe and CADx demonstrated sufficient diagnostic performance to support the use of an AI system.