Related Experiment Video
Updated: Jul 14, 2025
Author Spotlight: Noninvasive Cerebral Blood Flow Determination in Human Functional Brain Region for Diagnosis of Neurological Disorders
Published on: May 31, 2024
Deeply Accelerated Arterial Spin Labeling Perfusion MRI for Measuring Cerebral Blood Flow and Arterial Transit Time
Abstract:
Cerebral blood flow (CBF) indicates both vascular integrity and brain function. Regional CBF can be non-invasively measured with arterial spin labeling (ASL) perfusion MRI. By repeating the same ASL MRI sequence several times, each with a different post-labeling delay (PLD), another important neurovascular index, the arterial transit time (ATT) can be estimated by fitting the acquired ASL signal to a kinetic model. This process however faces two challenges: one is the multiplicatively prolonged scan time, making it impractically for clinical use due to the escalated risk of motions; the other is the reduced signal-to-noise-ratio (SNR) in the long PLD scans due to the T1 decay of the labeled spins. Increasing SNR needs more repetitions which will further increase the total scan time. Currently, there lacks a way to accurately estimate ATT from a parsimonious number of PLDs. In this paper, we proposed a deep learning-based algorithm to reduce the number of PLDs and to accurately estimate ATT and CBF. Two separate deep networks were trained: one is designed to estimate CBF and ATT from ASL data with a single PLD; the other is to estimate CBF and ATT from ASL data with two PLDs. The models were trained and tested using the large Human Connectome Project multiple-PLD ASL MRI. Performance of the DL-based approach was compared to the traditional full dataset-based data fitting approach. Our results showed that ATT and CBF can be reliably estimated using deep networks even with one PLD.
Insights
Deep learning accurately estimates arterial transit time (ATT) and cerebral blood flow (CBF) using fewer arterial spin labeling MRI scans. This novel approach overcomes clinical limitations of prolonged scan times and reduced signal-to-noise ratio.
Area of Science:
- Neuroimaging
- Medical Physics
- Artificial Intelligence
Background:
- Cerebral blood flow (CBF) and arterial transit time (ATT) are crucial neurovascular indices.
- Arterial spin labeling (ASL) MRI enables non-invasive measurement of regional CBF.
- Estimating ATT requires multiple post-labeling delays (PLDs), leading to prolonged scan times and reduced signal-to-noise ratio (SNR).
Purpose of the Study:
- To develop a deep learning (DL) algorithm for accurate ATT and CBF estimation from a reduced number of ASL MRI PLDs.
- To address the clinical impractibility of current multi-PLD ASL methods due to scan time and SNR limitations.
Main Methods:
- Two deep neural networks were trained to estimate CBF and ATT from ASL data with either one or two PLDs.
- Models were trained and validated using the Human Connectome Project multi-PLD ASL MRI dataset.
- Performance was compared against traditional kinetic model fitting using the full dataset.
Main Results:
- Deep learning models reliably estimated ATT and CBF with significantly fewer PLDs.
- The DL-based approach demonstrated comparable accuracy to traditional methods despite reduced data acquisition.
- Accurate estimations were achieved even with a single PLD, drastically reducing scan time.
Conclusions:
- Deep learning offers a viable solution for accurate and efficient estimation of ATT and CBF from ASL MRI.
- This approach can overcome the limitations of prolonged scanning and SNR reduction in multi-PLD ASL.
- The proposed DL algorithm holds promise for improving the clinical utility of ASL MRI for neurovascular assessment.
