Novel computer-aided diagnostic system for colorectal lesions by using endocytoscopy (with videos)

Background: Endocytoscopy enables in vivo observation of nuclei at 450x magnification during GI endoscopy, thus allowing precise prediction of lesion pathology. However, because it requires training and experience, it may be beneficial only when performed by expert endoscopists. Objective: To develop and evaluate a novel computer-aided diagnosis system for endocytoscopic imaging (EC-CAD) of colorectal lesions. Design: Pilot study. Setting: University hospital. Patients: One hundred fifty-two patients with small colorectal polyps (<= 10 mm) who had undergone endocytoscopy. Intervention: Test sets of white-light endoscopic images and endocytoscopic images from 176 small colorectal polyps (137 neoplastic and 39 non-neoplastic polyps) were assessed by EC-CAD, 2 expert endoscopists, and 2 trainee endoscopists. Main Outcome Measurement: Sensitivity, specificity, and accuracy in predicting neoplastic change by EC-CAD comparing expert and trainee endoscopists. Results: EC-CAD had a sensitivity of 92.0% and an accuracy of 89.2%; these were comparable to those achieved by expert endoscopists (92.7% and 92.3%; P = .868 and .256, respectively) and significantly higher than those achieved by trainee endoscopists (81.8% and 80.4%; P < .001 and .002, respectively). EC-CAD achieved a specificity of 79.5%; this did not differ significantly from that achieved by the experts and trainees. EC-CAD also enabled instant diagnosis, taking only 0.3 seconds for each lesion with perfect reproducibility. Limitations: No sample size calculation. Conclusions: EC-CAD provides fully automated instant classification of colorectal polyps with excellent sensitivity, accuracy, and objectivity. Thus, it can be a powerful tool for facilitating decision making during routine colonoscopy.