In specific cardiovascular diseases that affect right ventricular (RV) morphology, standard axial (AX) orientation is preferred by some investigators but due to the rare occurrence of these diseases, data in this domain is scarce. The model uses Unsupervised Domain Adaptation (UDA) of 3D cardiac magnetic resonance (CMR) images to transform from axial to short-axis orientation and performs a segmentation task via a pre-trained fixed network. At the end of the learning process, the model is able to transform the data set such that it corresponds to a short-axis view, which can be segmented more reliably by the pre-trained short-axis segmentation module.
Input variables : AX cardiac magnetic resonance (CMR)
Output Variables : Segmented CMR
Visit Model : github.com
Additional links : arxiv.org
| Model Category | : | Public |
| Date Published | : | January, 2021 |
| Healthcare Domain | : | Medical Technology |
| Code | : | github.com |
| Medical Imaging |
| Image Segmentation |