Synthesizing high-resolution brain MR T1-MPRage-like Images from low-dose CT

Motivation: Using deep learning to improve the soft tissue contrast in low-dose brain CT similar to MRI. Goal(s): Converting low-dose brain CT to high-resolution T1-MPRAGE-like Images. Approach: A ResUNet-based deep learning approach is developed to learn the complex transformation from low-dose brain CT to its corresponding T1-MPRAGE. Results: With the proposed approach, we obtained high-resolution MR T1-MPRAGE-like images with superior soft-tissue contrasts from noisy low-dose brain CT images. Impact: By transferring brain CT to T1-MPRAGE-like images, our approach provides superior soft tissue contrast from low-dose brain CT images. Our method would allow tissue-specific analysis using noisy non-contrast CT.