Related Experiment Video
Updated: Sep 7, 2025
Author Spotlight: Noninvasive Cerebral Blood Flow Determination in Human Functional Brain Region for Diagnosis of Neurological Disorders
Published on: May 31, 2024
Perfusion Maps Acquired From Dynamic Angiography MRI Using Deep Learning Approaches
Muhammad Asaduddin1, Hong Gee Roh2, Hyun Jeong Kim3
1Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea.
Background:
A typical stroke MRI protocol includes perfusion-weighted imaging (PWI) and MR angiography (MRA), requiring a second dose of contrast agent. A deep learning method to acquire both PWI and MRA with single dose can resolve this issue.
Purpose:
To acquire both PWI and MRA simultaneously using deep learning approaches.
Study Type:
Retrospective.
Subjects:
A total of 60 patients (30-73 years old, 31 females) with ischemic symptoms due to occlusion or ≥50% stenosis (measured relative to proximal artery diameter) of the internal carotid artery, middle cerebral artery, or anterior cerebral artery. The 51/1/8 patient data were used as training/validation/test.
Field Strength/Sequence:
A 3 T, time-resolved angiography with stochastic trajectory (contrast-enhanced MRA) and echo planar imaging (dynamic susceptibility contrast MRI, DSC-MRI).
Assessment:
We investigated eight different U-Net architectures with different encoder/decoder sizes and with/without an adversarial network to generate perfusion maps from contrast-enhanced MRA. Relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF), mean transit time (MTT), and time-to-max (Tmax ) were mapped from DSC-MRI and used as ground truth to train the networks and to generate the perfusion maps from the contrast-enhanced MRA input.
Statistical Tests:
Normalized root mean square error, structural similarity (SSIM), peak signal-to-noise ratio (pSNR), DICE, and FID scores were calculated between the perfusion maps from DSC-MRI and contrast-enhanced MRA. One-tailed t-test was performed to check the significance of the improvements between networks. P values < 0.05 were considered significant.
Results:
The four perfusion maps were successfully extracted using the deep learning networks. U-net with multiple decoders and enhanced encoders showed the best performance (pSNR 24.7 ± 3.2 and SSIM 0.89 ± 0.08 for rCBV). DICE score in hypo-perfused area showed strong agreement between the generated perfusion maps and the ground truth (highest DICE: 0.95 ± 0.04).
Data Conclusion:
With the proposed approach, dynamic angiography MRI may provide vessel architecture and perfusion-relevant parameters simultaneously from a single scan.
Evidence Level:
3 TECHNICAL EFFICACY: Stage 5.
Insights
Deep learning enables simultaneous acquisition of perfusion-weighted imaging (PWI) and MR angiography (MRA) using a single contrast dose. This novel approach enhances stroke imaging efficiency and accuracy.
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.
