Gaze-DETR: Using Expert Gaze to Reduce False Positives in Vulvovaginal Candidiasis Screening

TL;DR

Gaze-DETR is a novel approach that uses expert gaze data to improve neural network accuracy in detecting vulvovaginal candidiasis by reducing false positives, demonstrating superior performance over existing methods.

Contribution

The paper introduces Gaze-DETR, a new method that integrates gaze data into detection models to enhance precision and reduce false positives in medical image analysis.

Findings

Gaze-DETR outperforms existing detection methods in accuracy.

Gaze-guided strategies improve model generalizability.

Expert gaze data helps identify false positives effectively.

Abstract

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.