Contrast Anatomy Learning and Analysis for MR Intensity Translation and Integration (CALAMITI)
Contrast Anatomy Learning and Analysis for MR Intensity Translation and Integration (CALAMITI) is our current MR harmonization method. It was designed to achieve unsupervised multi-site MR harmonization. The associated publications are:
- L. Zuo, B.E. Dewey, A. Carass, Y. Liu, Y. He, P.A. Calabresi, and J.L. Prince, "Information-based Disentangled Representation Learning for Unsupervised MR Harmonization", 27th Conference on Information Processing in Medical Imaging (IPMI 2021), Virtually in Bornholm, Denmark, June 28 - July 2, 2021.
- L. Zuo, B. E. Dewey, Y. Liu, Y. He, S. D. Newsome, E. M. Mowry, S. M. Resnick, J. L. Prince, and A. Carass, "Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory", NeuroImage, 118569, 2021. (doi)
|330Mb (including sample data)|
CALAMITI requires the following preprocessing steps:
- N4 inhomogeneity correction.
- Registration to MNI space (0.8mm isotropic resolution is ideal. Image dimension after MNI registration is 241*288*241).
- White matter peak normalization (see https://github.com/jcreinhold/intensity-normalization).
CALAMITI requires paired multi-contrast MR images (e.g., T1-w and T2-w) during training. The ideal structure of the data directory and naming convention are as follows:
├──absolute_path_to_data ├──SiteA | ├──train | | ├──SiteA_T1w_SUB*_ORIENTATION_SLICE*.nii.gz ("ORIENTATION" should be "AXIAL", "CORONAL", or "SAGITTAL") | | └──SiteA_T2w_SUB*_ORIENTATION_SLICE*.nii.gz | └──valid | ├──SiteA_T1w_SUB*_ORIENTATION_SLICE*.nii.gz | └──SiteA_T2w_SUB*_ORIENTATION_SLICE*.nii.gz └──SiteB ├──train | ├──SiteB_T1w_SUB*_ORIENTATION_SLICE*.nii.gz | └──SiteB_T2w_SUB*_ORIENTATION_SLICE*.nii.gz └──valid ├──SiteB_T1w_SUB*_ORIENTATION_SLICE*.nii.gz └──SiteB_T2w_SUB*_ORIENTATION_SLICE*.nii.gz
Sample command and dependencies
- After downloading the code, sample command for CALAMITI training can be found in
"script"folder. Testing (encoding and decoding) code can be found in
- Conda environment can be downloaded .
If you have other questions regarding the method or software, please email Lianrui Zuo at