Cross-modality image synthesis from TOF-MRA to CTA using diffusion-based models

TL;DR

This paper presents a diffusion-based approach for converting TOF-MRA images into synthetic CTA images, improving over traditional methods and aiding in cerebrovascular disease diagnosis.

Contribution

The study introduces a diffusion model framework for cross-modality image synthesis from TOF-MRA to CTA, outperforming U-Net-based approaches.

Findings

Diffusion models outperform U-Net in CTA synthesis from TOF-MRA.

Different diffusion architectures and samplers are evaluated for optimal performance.

Synthetic CTA images can potentially enhance AI research with limited real CTA data.

Abstract

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.