BACKGROUND AND AIMS: Human-computer interaction, particularly the graphical user interface (GUI) for displaying detection results, is an important but underexplored aspect of CADe systems in endoscopy. The aim of this study was to study if the use of a bounding box GUI or a heatmap GUI results in different performance of endoscopists when using CADe for Barrett's neoplasia. METHODS: Thirty-seven endoscopists from six countries with varying expertise assessed 70 Barrett's esophagus videos. All videos were evaluated by our previously developed CADe system and comprised, at some point, a CADe detection, irrespective if the video contained neoplasia or not. The study had two phases: initially, videos were shown with either a bounding box or heatmap
after a two-week wash-out, the same videos were reordered and displayed with the alternate GUI. Endoscopists marked perceived neoplastic lesions and biopsy sites, also noting their subjective GUI preference. Primary endpoints were objective classification and localization performance. Secondary endpoint was the subjective preference. RESULTS: There was no statistically significant difference in classification performance when endoscopists were provided with the bounding box or the heatmap visualization (sensitivity 83% vs. 83%, p = 0.29
specificity 86% vs 86%, p =0.09). Also, the comparison of localization accuracy between the bounding box and heatmap methods showed no significant differences, with both methods yielding a median score of 97%. Subjectively, 23 endoscopists preferred the heatmap and 14 the bounding box (p=0.04). CONCLUSIONS: Although endoscopists expressed a preference for the heatmap GUI, this was not associated with a statistical difference in performance outcomes.