MRI-to-CT synthesis using drifting models

1. 1Investigate drifting models for MRI-to-CT synthesis
2. 2Compare performance with existing models like UNet, VAE, WGAN-GP, and PPFM
3. 3Evaluate the accuracy of bone details in synthesized CT images
4. 4Refine the models for improved performance and clinical applicability

Radiologists and medical imaging researchers can benefit from this technology to reduce ionizing radiation exposure, while software engineers and AI researchers can develop and refine the models

💡 Drifting models can accurately synthesize pelvis CT images from MRI, enabling MR-only workflows

📸 MRI-to-CT synthesis using drifting models reduces radiation exposure #AIinRadiology