A dataset of A 3D Computed Tomography (CT) image dataset, ImageChD, for classification of Congenital Heart Disease (CHD) is published.
ImageCHD contains 110 3D Computed Tomography (CT) images covering most types of CHD, which is of decent size compared with existing medical imaging datasets. Classification of CHDs requires the identification of large structural changes without any local tissue changes, with limited data. It is an example of a larger class of problems that are quite difficult for current machine-learning based vision methods to solve.
Our dataset includes 110 CT images with labels. The label includes left ventricle (label: 1), right ventricle (label: 2), left atrium (label: 3), right atrium (label: 4), myocardium (label: 5), aorta (label: 6), and pulmonary artery (label: 7). You notice other labels such 14 etc., you can just ignore them as they are labels corresponding to airways etc.
If you used our dataset, please consider to cite our paper in MICCAI 2020, Xiaowei Xu, Tianchen Wang, Haiyun Yuan, Qianjun Jia, Jianzheng Ceng, Yuhao Dong, Meiping Huang, and Jian Zhuang, Yiyu Shi, "ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease," in Proc. of Medical Image Computing and Computer Assisted Interventions (MICCAI), Online, 2020.
Update May 10th 2021: The diagnosis info of the dataset is updated (thanks to the help of Kadirbarut from Bilgiuzayi). Please check the xlsx file in the download dataset for more details.
HIGHLIGHT 20231101: We have deployed the dataset on Kaggle! https://www.kaggle.com/xiaoweixumedicalai/datasets
Please send emails to xiao.wei.xu@foxmail.com for any questions.