SkinCancer数据集专为皮肤病理图像分类设计,包含常见皮肤肿瘤和非肿瘤解剖组织的高分辨率标注图像。该数据集包含386个病例,涵盖最常见的皮肤肿瘤类型:基底细胞癌(Basal Cell Carcinoma, BCC)、鳞状细胞癌(Squamous Cell Carcinoma, SqCC)和黑色素瘤(Melanoma),以及各种非肿瘤组织。病理切片图像经过严格的多级人工标注,识别出16种不同的组织类别,包括表皮、真皮、皮下组织、毛囊、神经和汗腺等结构。
pifu维度 | 2D |
模态 | pathology |
任务类型 | classification |
解剖结构 | 皮肤 |
解剖区域 | 皮肤 |
类别数 | 16 |
数据量 | 129,364 |
文件格式 | JPG |
data
│
├── class_dict.json
├── tiles_v2.csv
├── tiles/
├── nontumor_skin_chondraltissue_chondraltissue
├── nontumor_skin_dermis_dermis
├── nontumor_skin_elastosis_elastosis
├── nontumor_skin_chondraltissue_chondraltissu
└── ...
统计类型 | 间距 (mm) | 尺寸 |
---|---|---|
最小值 | (0.1, 0.1) |
(395, 395) |
中位值 | (0.1, 0.1) |
(395, 395) |
最大值 | (0.1, 0.1) |
(395, 395) |
@article{kriegsmann2022deep,
title={Deep learning for the detection of anatomical tissue structures and neoplasms of the skin on scanned histopathological tissue sections},
author={Kriegsmann, Katharina and Lobers, Frithjof and Zgorzelski, Christiane and Kriegsmann, J{\"o}rg and Jan{\ss}en, Charlotte and Meli{\ss}, Rolf R{\"u}dinger and Muley, Thomas and Sack, Ulrich and Steinbuss, Georg and Kriegsmann, Mark},
journal={Frontiers in Oncology},
volume={12},
pages={1022967},
year={2022},
publisher={Frontiers Media SA}
}