Datasets
Standard Dataset
Annotations for Body Organ Localization based on MICCAI LiTS Dataset
- Citation Author(s):
- Submitted by:
- Xuanang Xu
- Last updated:
- Tue, 05/17/2022 - 22:17
- DOI:
- 10.21227/df8g-pq27
- Data Format:
- Research Article Link:
- Links:
- License:
- Categories:
- Keywords:
Abstract
For the development and evaluation of organ localization methods, we build a set of annotations of organ bounding boxes based on the MICCAI Liver Tumor Segmentation (LiTS) challenge dataset. Bounding boxes of 11 body organs are included: heart (53/28), left lung (52/21), right lung (52/21), liver (131/70), spleen (131/70), pancreas (131/70), left kidney (129/70), right kidney (131/69), bladder (109/67), left femoral head (109/66) and right femoral head (105/66). The number in the parentheses indicates the number of the organs annotated in training and testing sets. Note that, all truncated organs, which are not fully contained in the CT images, are considered as background and not annotated. Any advice for improving this dataset is welcome (E-mail: xuang199085@163.com). If it helps in your research, please cite our paper on TMI (http://doi.org/10.1109/TMI.2019.2894854).
The annotations are stored in 201 TXT files (131 for training and 70 for testing), corresponding to the 201 abdominal CT scans in the LiTS dataset. Each TXT file is composed of N lines of records, presenting the N organs appearing in the CT image. The data stored in each line is organized as following formats:
name label x0 x1 y0 y1 z0 z1
where x0 and x1 denote the starting and ending coordinates of the bounding box on X-axis, respectively. And so on, for the Y-axis and Z-axis.
For example, the following record:
liver 1 70 378 143 369 45 73
defines a bounding box of liver starting at (70, 143, 45) and ending at (378, 369, 73). All the coordinates are measured in voxels. The X-axis points from right hand to left hand; the Y-axis points from face to back; the Z-axis points from feet to head.
If it helps in your research, please cite our paper on TMI (http://doi.org/10.1109/TMI.2019.2894854).
@article{xu2019organlocalization,
author = {Xu, Xuanang and Zhou, Fugen and Liu, Bo and Fu, Dongshan and Bai, Xiangzhi},
journal = {IEEE Transactions on Medical Imaging},
title = {Efficient Multiple Organ Localization in CT Image using 3D Region Proposal Network},
year = {2019}
doi = {10.1109/TMI.2019.2894854},
volume = {},
number = {},
pages = {1-1},
ISSN = {0278-0062},
month = {},
}
Comments
How to download it ?
Login the IEEEDataPort website and you will see the download link on the right site.