Cross-modality image synthesis from TOF-MRA to CTA using diffusion-based models
This work addresses a domain-specific problem for medical imaging researchers and clinicians by enabling cross-modality synthesis to overcome data limitations in cerebrovascular disease diagnosis and treatment.
This study tackled the problem of generating synthetic Computed Tomography Angiography (CTA) images from Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) using diffusion-based models to address the scarcity of open-source CTA data for AI research in cerebrovascular disease, and found that diffusion models outperform a traditional U-Net-based approach.
Cerebrovascular disease often requires multiple imaging modalities for accurate diagnosis, treatment, and monitoring. Computed Tomography Angiography (CTA) and Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) are two common non-invasive angiography techniques, each with distinct strengths in accessibility, safety, and diagnostic accuracy. While CTA is more widely used in acute stroke due to its faster acquisition times and higher diagnostic accuracy, TOF-MRA is preferred for its safety, as it avoids radiation exposure and contrast agent-related health risks. Despite the predominant role of CTA in clinical workflows, there is a scarcity of open-source CTA data, limiting the research and development of AI models for tasks such as large vessel occlusion detection and aneurysm segmentation. This study explores diffusion-based image-to-image translation models to generate synthetic CTA images from TOF-MRA input. We demonstrate the modality conversion from TOF-MRA to CTA and show that diffusion models outperform a traditional U-Net-based approach. Our work compares different state-of-the-art diffusion architectures and samplers, offering recommendations for optimal model performance in this cross-modality translation task.