Perfusion Maps Acquired From Dynamic Angiography MRI Using Deep Learning Approaches.

Area of Science:

• Medical Imaging
• Artificial Intelligence in Medicine
• Neurology

Background:

• Standard stroke MRI protocols often require two contrast agent doses for both perfusion-weighted imaging (PWI) and MR angiography (MRA).
• This dual-dose approach increases patient burden and imaging time.
• A single-dose method could significantly improve efficiency in stroke diagnostics.

Purpose of the Study:

• To develop and validate a deep learning method for simultaneous PWI and MRA acquisition from a single contrast injection.
• To assess the feasibility of generating comprehensive stroke imaging data in one session.

Main Methods:

• Retrospective analysis of 60 patients with ischemic symptoms undergoing 3T MRI.
• Utilized U-Net architectures with varying encoder/decoder sizes and adversarial networks.
• Trained networks using dynamic susceptibility contrast MRI (DSC-MRI) derived perfusion maps (rCBV, rCBF, MTT, Tmax) as ground truth.

Main Results:

• Deep learning models successfully extracted four perfusion maps.
• A U-Net architecture with multiple decoders and enhanced encoders demonstrated superior performance (e.g., pSNR 24.7 ± 3.2, SSIM 0.89 ± 0.08 for rCBV).
• High agreement (DICE score up to 0.95 ± 0.04) was observed between generated and ground truth perfusion maps in hypoperfused areas.

Conclusions:

• The proposed deep learning approach enables simultaneous acquisition of vessel architecture and perfusion parameters from a single contrast-enhanced MRA scan.
• This method holds potential to streamline stroke imaging protocols.
• Future applications may include more efficient and comprehensive stroke assessment.