polyp segmentation datasets

It stores the largely used testing protocoll for polyp segmentation:

The training set includes 900 images from Kvasir-SEG and 550 images from CVC-ClinicDB. The testing set is made of the remaining images from the above cited datasets: 100 images from Kvasir-SEG, 62 images from CVC-ClinicalDB, 380 from CVC-ColonDB, 196 from ETIS-Larib and 60 from CVC-T, which is testing set for EndoScene. 

The test sets are stored in the folder TestDataset.

There are three versions of the training set:

NewTRimage, original training set without data augmentation

NewTRimageDA, data augmentation proposed in "Data augmentation for deep ensembles in polyp segmentation"

OLDTRimage, data augmentation used in https://arxiv.org/abs/2104.00850

The names  with "mask" stores the binary mask of the related images.