Classification of Fundus Images into 5 stages of Diabetic Retinopathy, and segmentation of blood vessels in fundus images

A Python package for computing the recall and precision scores specifically on thin vessels in retinal images and generating weight masks for BCE Loss to enhance models perfomance on segmenting these fine structures, as detailed in the paper "Vessel-Width-Based Metrics and Weight Masks for Retinal Blood Vessel Segmentation".

Retina Preprocessing with CLAHE (Contrast limited adaptive histogram equalization)

DEFFA-UNet: PyTorch implementation for retinal vessel segmentation with dual encoding and attention mechanisms. Outperforms existing methods on DRIVE, CHASE_DB1, and STARE datasets for automated ophthalmology diagnosis.

Matlab code for the validation of the tortuosity of retinal vessels, as described in: