Input Data

Data Format

Brainchop is designed with current version (v1.0.0) to support T1 weighted MRI volumes segmentation. The input must be a T1 brain volume in the Nifti format.

Preprocessing Data

Some T1 image may need to be normalized to 1x1x1 mm voxels as a preprocessing step for proper results. This normalization can be created by using FreeSurfer's command:

                        mri_convert original_T1.nii  new_T1.nii.gz  -c

Also conform, a python version of mri_convert, can be used for the T1 image normalization such that:

                         python conform.py  -i <input> -o <output>

After selecting the T1 weighted image for 3D segmentation, Brainchop applies different preprocessing steps underneath such as:

• Converting data to JavaScript readable format.
• Converting input data to tensors in order to deploy tfjs framework for the 3D inference.
• Convert tensors to batches for Grey Matter/White Matter inference.
• Image normalization to enhance model accuracy.