mahmoud-ekhani / ct_2_mri

ct_aortic_anatomy_to_pc_mri_flow_conversion

ct_2_mri

ct_aortic_anatomy_to_pc_mri_flow_conversion

We present the implementation of a conditional generative adversarial network (cGAN) for converting aortic anatomy obtained from CT scans into aortic flow dynamics derived from phase-contrast 4D flow MRI. This implementation differs from a standard pix-2-pix cGAN in that all 2D kernels have been converted to 3D, allowing for more accurate and realistic results in the conversion process. This 3D cGAN has the potential to revolutionize the way we understand and analyze aortic flow dynamics, providing a more comprehensive and detailed understanding of this critical aspect of cardiovascular health. By converting CT scan data into flow dynamics, we can gain a deeper insight into the functioning of the aorta and identify potential areas of concern or dysfunction. This innovative approach has the potential to greatly improve the diagnosis and treatment of aortic conditions, ultimately leading to better patient outcomes.