6 datasets found

Ridge-based vessel segmentation in color images of the retina.

The DRIVE dataset contains the curvilinear-shaped vessel. This dataset consists of 40 565 × 584 color retinal images, which are split into 20 training images and 20 test images.

Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension.

The HRF dataset contains 45 images, which is divided into 15/15/15 images for healthy patients, patients with diabetic retinopathy and glaucomatous patients.

The CHASE_DB1 dataset is a publicly available dataset for retinal vessel segmentation.

The proposed SA-UNet is evaluated on two publicly available retinal fundus image datasets: DRIVE and CHASE_DB1.