CHASE_DB1
ImagesMedicalUnknownIntroduced 2012-01-01
CHASE_DB1 is a dataset for retinal vessel segmentation which contains 28 color retina images with the size of 999×960 pixels which are collected from both left and right eyes of 14 school children. Each image is annotated by two independent human experts.
Source: MixModule: Mixed CNN Kernel Module for Medical Image Segmentation Image Source: https://www.mdpi.com/2073-8994/9/11/276
Benchmarks
Medical Image Segmentation/DSCMedical Image Segmentation/AUCMedical Image Segmentation/F1 scoreMedical Image Segmentation/mIOUMedical Image Segmentation/SensitivityMedical Image Segmentation/MCCMedical Image Segmentation/1:1 AccuracyMedical Image Segmentation/AccMedical Image Segmentation/Average IOURetinal Vessel Segmentation/AUCRetinal Vessel Segmentation/F1 scoreRetinal Vessel Segmentation/mIOURetinal Vessel Segmentation/SensitivityRetinal Vessel Segmentation/MCCRetinal Vessel Segmentation/1:1 AccuracyRetinal Vessel Segmentation/AccRetinal Vessel Segmentation/Average IOURetinal Vessel Segmentation/DSC