How to prepare the data?

[YurongChen1998]

Thanks for your inspired work, and I would like to know how to prepare the data, such as BraST datasets.

When I download the BraST dataset, it includes 3 folds: ImageTr, Label, ImageTs. All files are stored as .nii.gz file, and how to use these data?

Thanks for your reply!

[aihamtaleb]

Hi @YurongChen1998 Thanks for your interest in using our code. You need to store the files as numpy files (format ".npy"). And then you should be able to load these files. Check out the loader scripts here: https://github.com/HealthML/self-supervised-3d-tasks/blob/master/self_supervised_3d_tasks/data/segmentation_task_loader.py or here: https://github.com/HealthML/self-supervised-3d-tasks/blob/master/self_supervised_3d_tasks/data/numpy_3d_loader.py

[aihamtaleb]

Btw, there is a helper script here to convert nifti files to npy: https://github.com/HealthML/self-supervised-3d-tasks/blob/master/self_supervised_3d_tasks/data_util/brats_dataset_utils.py for brats

[shabbirshuvo]

Hi Mr. taleb. I would like to use your code for my project. But I am not sure how to prepare my custom data for using with your model. Also I would like to know, if any documentation details on the code implementation is available? Thank you.

[aihamtaleb]

hi @shabbirshuvo ,

please check out the Readme: https://github.com/HealthML/self-supervised-3d-tasks/blob/master/README.md