Intestinal polyp segmentation dataset

This dataset contains different intestinal polyp datasets, in which the method of dividing test set and training set is the same as that mentioned in most intestinal polyp segmentation methods, where the training set consists of pictures from Kvasir and CVC-ClinicDB, and pictures from the two datasets are mixed into the same training set. The test set clearly indicates the division of the test set from different data sets in the form of folder names, and all images are unified as 352*352. The test set includes test images from the Kvasir, CVC-ClinicDB, CVC-colonDB, ETIS, and CVC-300 data sets. This dataset can be used in image segmentation tasks in intestinal polyps.

本数据集包含多组肠道息肉相关数据集，其训练集与测试集的划分方式与多数肠道息肉分割方法中采用的划分规则一致。训练集由Kvasir与CVC-ClinicDB两个数据集的图像混合组成。测试集以文件夹名称的形式明确标注了各测试子集所属的原始数据集，且所有图像均统一调整至352×352的分辨率。测试集涵盖了来自Kvasir、CVC-ClinicDB、CVC-colonDB、ETIS以及CVC-300五个数据集的测试图像。本数据集可应用于肠道息肉图像分割任务。

搜集汇总

背景与挑战

背景概述

该数据集是一个专门用于肠道息肉图像分割任务的数据集，包含来自多个数据集的训练和测试图像，所有图像统一为352*352分辨率。训练集由Kvasir和CVC-ClinicDB数据集的图片混合而成，测试集则包括来自Kvasir、CVC-ClinicDB、CVC-colonDB、ETIS和CVC-300数据集的测试图像。