结直肠癌图像分析数据集

该数据集为结直肠癌组织病理学苏木精-伊红染色图像数据集（EBHI-Seg），包含2,855张内窥镜活检组织图像及对应真实标签，涵盖正常、息肉、低级别/高级别上皮内瘤变、锯齿状腺瘤和腺癌六类病变，适用于图像分割任务。数据按4:4:2划分为训练、验证和测试集，支持传统机器学习与深度学习实验。数据集规模适中，标注准确，可用于开发和验证结直肠癌自动识别算法，助力医疗大模型训练与临床辅助诊断。

This dataset is a hematoxylin-eosin (H&E) stained histopathological image dataset for colorectal cancer, designated as EBHI-Seg. It comprises 2,855 endoscopic biopsy tissue images along with their corresponding ground-truth labels, covering six categories of lesions: normal tissue, polyp, low-grade/high-grade intraepithelial neoplasia, serrated adenoma, and adenocarcinoma. This dataset is suitable for image segmentation tasks, and is split into training, validation, and test sets at a ratio of 4:4:2, supporting experiments in both traditional machine learning and deep learning. With a moderate scale and precise annotations, it can be used to develop and validate automated colorectal cancer recognition algorithms, and facilitate the training of medical large language models and clinical auxiliary diagnosis.