病理图像数据集_classification of breast cancer mammogram images u

数据集

1、Breast Cancer Histopathological Database (BreakHis)
数据集描述：
The Breast Cancer Histopathological Image Classification (BreakHis) is composed of 9,109 microscopic images of breast tumor tissue collected from 82 patients using different magnifying factors (40X, 100X, 200X, and 400X). To date, it contains 2,480 benign and 5,429 malignant samples (700X460 pixels, 3-channel RGB, 8-bit depth in each channel, PNG format).
Each image is labeled with two main-classes including benign and malignant as well as eight sub-classes including four histological distinct types of benign breast tumors: adenosis (A), fibroadenoma (F), phyllodes tumor (PT), and tubular adenoma (TA); and four malignant tumors (breast can- cer): ductal carcinoma (DC), lobular carcinoma (LC), mucinous car- cinoma (MC), and papillary carcinoma (PC).
获取教程： 链接

2、ACDC-LungHP
数据集描述：
150 WSIs within lung cancer regions annotated by pathologists. 2 In the evaluation, 30 WSIs were randomly selected as the testing dataset, and the re- mainders were used to train the retrieval models and establish the retrieval database.
https://acdc- lunghp.grand- challenge.org

3、prostate adenocarcinoma (PRAD)
Paper：
Cancer incidence and mortality worldwide: Sources, methods and major patterns in GLOBOCAN 2012

4、PLOSONE dataset
Paper：
Classification of breast cancer histology images using convolutional neural networks
数据集描述：
285 H&E microscopy images captured at 200 × magnification. All images are captured with the resolution of 2048 ×1536, and are labeled with four classes including normal tissue, benign lesion, in situ carcinoma and invasive carcinoma .