Gaze-DETR: Using Expert Gaze to Reduce False Positives in Vulvovaginal Candidiasis Screening
This addresses a critical issue in women's health by enhancing screening precision, though it is an incremental advancement in medical imaging.
The paper tackles the problem of false positives in vulvovaginal candidiasis screening by integrating expert gaze data into neural networks, resulting in Gaze-DETR, which shows remarkable improvements in detection accuracy and generalizability over existing methods.
Accurate detection of vulvovaginal candidiasis is critical for women's health, yet its sparse distribution and visually ambiguous characteristics pose significant challenges for accurate identification by pathologists and neural networks alike. Our eye-tracking data reveals that areas garnering sustained attention - yet not marked by experts after deliberation - are often aligned with false positives of neural networks. Leveraging this finding, we introduce Gaze-DETR, a pioneering method that integrates gaze data to enhance neural network precision by diminishing false positives. Gaze-DETR incorporates a universal gaze-guided warm-up protocol applicable across various detection methods and a gaze-guided rectification strategy specifically designed for DETR-based models. Our comprehensive tests confirm that Gaze-DETR surpasses existing leading methods, showcasing remarkable improvements in detection accuracy and generalizability.