What are Microaneurysms (MAs)?
🔻 Try hovering the mouse over the image below and moving it horizontally!
Microaneurysms (MAs), critical early indicators of Diabetic Retinopathy (DR), are tiny, inconspicuous, with variations in brightness, contrast, and shape in fundus images, making manual detection challenging and highlighting the need for accurate automated methods. Current methods, particularly diffusion-based anomaly detection models, face three key limitations. First, these models often fall prey to "identity mapping", where they inadvertently replicate the input image. Second, they struggle to distinguish MAs from other anomalies, leading to high false positives. Third, their suboptimal reconstruction of normal features hampers overall performance. To address these challenges, we propose a Wavelet Diffusion Transformer framework for MA Detection (WDT-MD), which features three key innovations: a noise-encoded image conditioning mechanism to avoid "identity mapping" by perturbing image conditions during training; pseudo-normal pattern synthesis via inpainting to introduce pixel-level supervision, enabling discrimination between MAs and other anomalies; and a wavelet diffusion Transformer architecture that combines the global modeling capability of diffusion Transformers with multi-scale wavelet analysis to enhance reconstruction of normal retinal features. Comprehensive experiments on the IDRiD and e-ophtha MA datasets demonstrate that WDT-MD outperforms state-of-the-art methods in both pixel-level and image-level MA detection. This advancement holds significant promise for improving early DR screening.
