# Diagnostically competitive performance of a physiology-informed generative multi-task network for contrast-free CT perfusion

## TL;DR

A new AI framework called MAGIC generates contrast-free CT perfusion maps using non-contrast CT scans, offering a cost-effective and safer alternative to traditional CTP for stroke assessment.

## Contribution

The novel use of a physiology-informed generative multi-task network to produce contrast-free CTP maps with diagnostic accuracy comparable to traditional methods.

## Key findings

- MAGIC produces high-quality perfusion maps comparable to contrast-based CTP in a double-blinded study with experts.
- The framework is robust to abnormalities in brain perfusion and does not require contrast agents.
- MAGIC offers a cost-effective and rapid alternative for perfusion imaging in stroke care.

## Abstract

Perfusion imaging is extensively utilized to assess hemodynamic status and tissue perfusion in various organs. Computed tomography perfusion (CTP) imaging plays a key role in the early assessment and planning of stroke treatment. While CTP provides essential perfusion parameters to identify abnormal blood flow in the brain. However, CTP can be expensive with limited accessibility, and the use of contrast agents in CTP can lead to allergic reactions and adverse side effects. To address these challenges, we propose a novel deep learning framework called Multitask Automated Generation of Intermodal CT perfusion maps (MAGIC). This framework combines generative artificial intelligence and physiological information to map non-contrast computed tomography (CT) imaging to multiple contrast-free CTP imaging maps. We demonstrate enhanced image fidelity by incorporating physiological characteristics into the loss terms. Our network was trained and validated using CT image data from patients referred for stroke at UF Health and demonstrated robustness to abnormalities in brain perfusion activity. A double-blinded study was conducted involving seven experienced neuroradiologists and vascular neurologists. This study validated MAGIC's visual quality and diagnostic accuracy showing favorable performance compared to clinical perfusion imaging with intravenous contrast injection. Overall, MAGIC holds great promise in revolutionizing healthcare by offering contrast-free, cost-effective, and rapid perfusion imaging.