A Multi-site Dataset for Prostate MRI Segmentation

This is a well-organized multi-site dataset for prostate MRI segmentation, which contains prostate T2-weighted MRI data (with segmentation mask) collected from six different data sources out of three public datasets. It can support research in various problem settings with need of multi-site data, such as Domain Generalization, Multi-site Learning and Life-long Learning, etc.

(1) Details of data and imaging protocols

The details of sample number and imaging protocols in each site are summarized in the tabel below:
Among these data:

(2) Visualization of sample slices

The appearance and contrast differences across the six sites can be displied in the figure below:

(3) Preprocessing steps

We frist convert data from all six sites uniformly to '.nii' format. For preprocessing, we center-cropped the images from Site C with roughly same view in axial plane as images from other sites (since the raw images of Site C are scanned from whole body rather than prostate surrounding area). After that, we resized all samples in the six sites to size of 384x384 in axial plane.

(4) Dataset Download Links



If this dataset is helpful for your research, please consider citing:
			title={Ms-net: Multi-site network for improving prostate segmentation with heterogeneous mri data},
			author={Liu, Quande and Dou, Qi and Yu, Lequan and Heng, Pheng Ann},
			journal={IEEE Transactions on Medical Imaging},
			title={Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains},
			author={Liu, Quande and Dou, Qi and Heng, Pheng Ann},
			booktitle={International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)},


We sincerely thank the organizers and collaborators of NCI-ISBI13 Challenge [1], I2CVB dataset [2] and PROMISE12 Challenge [3] for sharing the data for public use.


For further question about the dataset, please contact Quande Liu (qdliu@cse.cuhk.edu.hk)


[1] Bloch, N., Madabhushi, A., Huisman, H., Freymann, J., et al.: NCI-ISBI 2013 Challenge: Automated Segmentation of Prostate Structures. (2015)
[2] Lemaitre, G., Marti, R., Freixenet, J., Vilanova. J. C., et al.: Computer-Aided Detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: A review. In: Computers in Biology and Medicine, vol. 60, pp. 8-31 (2015)
[3] Litjens, G., Toth, R., Ven, W., Hoeks, C., et al.: Evaluation of prostate segmentation algorithms for mri: The promise12 challenge. In: Medical Image Analysis. , vol. 18, pp. 359-373 (2014)