BACKGROUND AND AIM: The aim of this randomized trial was to evaluate the performance of self-training versus didactic training in order to increase the diagnostic accuracy of diminutive/small colonic polyp histological prediction by trainees. METHODS: Sixteen trainees reviewed 78 videos (48 iSCAN-OE and 30 NBI) of diminutive/small polyps in a pretraining assessment. Trainees were randomized to receive computer-based self-learning (n = 8) or didactic training (n = 8) using identical teaching materials and videos. The same 78 videos, in a different randomized order, were assessed. The NICE (NBI International Colorectal Endoscopic) and SIMPLE (Simplified Identification Method for Polyp Labeling during Endoscopy) classification systems were used to classify diminutive/small polyps. RESULTS: A higher proportion of high-confidence predictions of polyps was made by the self-training group versus the didactic group using both the SIMPLE classification (77.1% [95% CI 73.4-80.3] vs 69.9% [95% CI 66.1-73.5%] [P = 0.005]) and the NICE classification (77% [95% CI 73.2-80.4%] vs 69.8% [95% CI 66-73.4%] [P = 0.006]). When using NICE, sensitivity of the self-training group compared with the didactic group was 72% versus 83% (P = 0.0005), and the accuracy was 66.1% versus 69.1%. The training improved the confidence of participants and SIMPLE was preferred over NICE. CONCLUSION: Self-learning for the prediction of diminutive/small polyp histology is a method of training that can achieve results similar to didactic training. Availability of adequate self-learning teaching modules could enable widespread implementation of optical diagnosis in clinical practice.