Automated generation of cerebral blood flow and arterial transit time maps from multiple delay arterial spin-labeled MRI

Effects of the Training Data Condition on Arterial Spin Labeling Parameter Estimation Using a Simulation-Based Supervised Deep Neural Network

OBJECTIVE

A simulation-based supervised deep neural network (DNN) can accurately estimate cerebral blood flow (CBF) and arterial transit time (ATT) from multidelay arterial spin labeling signals. However, the performance of deep learning depends on the characteristics of the training data set. We aimed to investigate the effects of the ground truth (GT) ranges of CBF and ATT on the performance of the DNN when training data were prepared using arterial spin labeling signal simulation.

METHODS

Deep neural networks were individually trained using 36 patterns of the training data sets. Simulation test data (1,000,000 points), 17 healthy volunteers, and 1 patient with moyamoya disease were included. The simulation test data were used to evaluate accuracy, precision, and noise immunity of the DNN. The best-performing DNN was determined by the normalized mean absolute error (NMAE), normalized root mean squared error (NRMSE), and normalized coefficient of variation over repeated training (CV Net ). Cerebral blood flow and ATT values and their histograms were compared between the GT and predicted values. For the in vivo data, the dependency of the predicted values on the GT ranges was visually evaluated by comparing CBF and ATT maps between the best-performing DNN and the other DNNs. Moreover, using the synthesized noisy images, noise immunity was compared between the best-performing DNN based on the simulation study and a conventional method.

RESULTS

The simulation study showed that a network trained by the GT of CBF and ATT in the ranges of 0 to 120 mL/100 g/min and 0 to 4500 milliseconds, respectively, had the highest performance (NMAE CBF , 0.150; NRMSE CBF , 0.231; CV NET CBF , 0.028; NMAE ATT , 0.158; NRMSE ATT , 0.257; and CV NET ATT , 0.028). Although the predicted CBF and ATT varied with the GT range of the training data sets, the appropriate settings preserved the accuracy, precision, and noise immunity of the DNN. In addition, the same results were observed in in vivo studies.

CONCLUSIONS

The GT ranges to prepare the training data affected the performance of the simulation-based supervised DNNs. The predicted CBF and ATT values depended on the GT range; inappropriate settings degraded the accuracy, whereas appropriate settings of the GT range provided accurate and precise estimates.

A model-based MR parameter mapping network robust to substantial variations in acquisition settings

Deep learning methods show great potential for the efficient and precise estimation of quantitative parameter maps from multiple magnetic resonance (MR) images. Current deep learning-based MR parameter mapping (MPM) methods are mostly trained and tested using data with specific acquisition settings. However, scan protocols usually vary with centers, scanners, and studies in practice. Thus, deep learning methods applicable to MPM with varying acquisition settings are highly required but still rarely investigated. In this work, we develop a model-based deep network termed MMPM-Net for robust MPM with varying acquisition settings. A deep learning-based denoiser is introduced to construct the regularization term in the nonlinear inversion problem of MPM. The alternating direction method of multipliers is used to solve the optimization problem and then unrolled to construct MMPM-Net. The variation in acquisition parameters can be addressed by the data fidelity component in MMPM-Net. Extensive experiments are performed on R2 mapping and R1 mapping datasets with substantial variations in acquisition settings, and the results demonstrate that the proposed MMPM-Net method outperforms other state-of-the-art MR parameter mapping methods both qualitatively and quantitatively.

Transformer-based deep learning denoising of single and multi-delay 3D arterial spin labeling

PURPOSE

To present a Swin Transformer-based deep learning (DL) model (SwinIR) for denoising single-delay and multi-delay 3D arterial spin labeling (ASL) and compare its performance with convolutional neural network (CNN) and other Transformer-based methods.

METHODS

SwinIR and CNN-based spatial denoising models were developed for single-delay ASL. The models were trained on 66 subjects (119 scans) and tested on 39 subjects (44 scans) from three different vendors. Spatiotemporal denoising models were developed using another dataset (6 subjects, 10 scans) of multi-delay ASL. A range of input conditions was tested for denoising single and multi-delay ASL, respectively. The performance was evaluated using similarity metrics, spatial SNR and quantification accuracy of cerebral blood flow (CBF), and arterial transit time (ATT).

RESULTS

SwinIR outperformed CNN and other Transformer-based networks, whereas pseudo-3D models performed better than 2D models for denoising single-delay ASL. The similarity metrics and image quality (SNR) improved with more slices in pseudo-3D models and further improved when using M0 as input, but introduced greater biases for CBF quantification. Pseudo-3D models with three slices achieved optimal balance between SNR and accuracy, which can be generalized to different vendors. For multi-delay ASL, spatiotemporal denoising models had better performance than spatial-only models with reduced biases in fitted CBF and ATT maps.

CONCLUSIONS

SwinIR provided better performance than CNN and other Transformer-based methods for denoising both single and multi-delay 3D ASL data. The proposed model offers flexibility to improve image quality and/or reduce scan time for 3D ASL to facilitate its clinical use.

Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images

Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden's index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications.

Deeply Accelerated Arterial Spin Labeling Perfusion MRI for Measuring Cerebral Blood Flow and Arterial Transit Time

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.

Hyperperfusion of bilateral amygdala in patients with chronic migraine: an arterial spin-labeled magnetic resonance imaging study

BACKGROUND

Amygdala, an essential element of the limbic system, has served as an important structure in pain modulation. There is still a lack of clarity about altered cerebral perfusion of amygdala in migraine. This study aimed to investigate the perfusion variances of bilateral amygdala in episodic migraine (EM) and chronic migraine (CM) using multi-delay pseudo-continuous arterial spin-labeled magnetic resonance imaging (pCASL-MRI).

METHODS

Twenty-six patients with EM, 55 patients with CM (33 CM with medication overuse headache (MOH)), and 26 age- and sex-matched healthy controls (HCs) were included. All participants underwent 3D multi-delay pCASL MR imaging to obtain cerebral perfusion data, including arrival-time-corrected cerebral blood flow (CBF) and arterial cerebral blood volume (aCBV). The CBF and aCBV values in the bilateral amygdala were compared among the three groups. Correlation analyses between cerebral perfusion parameters and clinical variables were performed.

RESULTS

Compared with HC participants, patients with CM were found to have increased CBF and aCBV values in the left amygdala, as well as increased CBF values in the right amygdala (all P < 0.05). There were no significant differences of CBF and aCBV values in the bilateral amygdala between the HC and EM groups, the EM and CM groups, as well as the CM without and with MOH groups (all P > 0.05). In patients with CM, the increased perfusion parameters of bilateral amygdala were positively correlated with MIDAS score after adjustments for age, sex, and body mass index (BMI).

CONCLUSION

Hyperperfusion of bilateral amygdala might provide potential hemodynamics evidence in the neurolimbic pain network of CM.

Parametric cerebral blood flow and arterial transit time mapping using a 3D convolutional neural network

PURPOSE

To reduce the total scan time of multiple postlabeling delay (multi-PLD) pseudo-continuous arterial spin labeling (pCASL) by developing a hierarchically structured 3D convolutional neural network (H-CNN) that estimates the arterial transit time (ATT) and cerebral blow flow (CBF) maps from the reduced number of PLDs as well as averages.

METHODS

A total of 48 subjects (38 females and 10 males), aged 56-80 years, compromising a training group (n = 45) and a validation group (n = 3) underwent MRI including multi-PLD pCASL. We proposed an H-CNN to estimate the ATT and CBF maps using a reduced number of PLDs and a separately reduced number of averages. The proposed method was compared with a conventional nonlinear model fitting method using the mean absolute error (MAE).

RESULTS

The H-CNN provided the MAEs of 32.69 ms for ATT and 3.32 mL/100 g/min for CBF estimations using a full data set that contains six PLDs and six averages in the 3 test subjects. The H-CNN also showed that the smaller number of PLDs can be used to estimate both ATT and CBF without significant discrepancy from the reference (MAEs of 231.45 ms for ATT and 9.80 mL/100 g/min for CBF using three of six PLDs).

CONCLUSION

The proposed machine learning-based ATT and CBF mapping offers substantially reduced scan time of multi-PLD pCASL.

Transformer based deep learning denoising of single and multi-delay 3D Arterial Spin Labeling

Purpose

To present a Swin Transformer-based deep learning (DL) model for denoising of single-delay and multi-delay 3D arterial spin labeling (ASL) and compare its performance with convolutional neural network (CNN) methods.

Methods

Swin Transformer and CNN-based spatial denoising models were developed for single-delay ASL. The models were trained on 59 subjects (104 scans) and tested on 44 subjects (57 scans) from 3 different vendors. Spatiotemporal denoising models were developed using another dataset (6 subjects, 10 scans) of multi-delay ASL. A range of input conditions was tested for denoising single and multi-delay ASL respectively. The performance was evaluated using similarity metrics, spatial signal-to-noise ratio (SNR) and quantification accuracy of cerebral blood flow (CBF) and arterial transit time (ATT).

Results

Swin Transformer outperformed CNN-based networks, whereas pseudo-3D models showed better performance than 2D models for denoising single-delay ASL. The similarity metrics and image quality (SNR) improved with more slices in pseudo-3D models, and further improved when using M0 as input but introduced greater biases for CBF quantification. Pseudo-3D models with 3 slices as input achieved optimal balance between SNR and accuracy, which can be generalized to different vendors. For multi-delay, spatiotemporal denoising models had better performance than spatial-only models with reduced biases in fitted CBF and ATT maps.

Conclusions

Swin Transformer DL models provided better performance than CNN methods for denoising both single and multi-delay 3D ASL data. The proposed model offers flexibility to improve image quality and/or reduce scan time for 3D ASL to facilitate its clinical use.

Cerebral perfusion variance in new daily persistent headache and chronic migraine: an arterial spin-labeled MR imaging study

BACKGROUND AND PURPOSE

New daily persistent headache (NDPH) and chronic migraine (CM) are two different types of headaches that might involve vascular dysregulation. There is still a lack of clarity about altered brain perfusion in NDPH and CM. This study aimed to investigate the cerebral perfusion variances of NDPH and CM using multi-delay pseudo-continuous arterial spin-labeled magnetic resonance imaging (pCASL-MRI).

METHODS

Fifteen patients with NDPH, 18 patients with CM, and 15 age- and sex-matched healthy controls (HCs) were included. All participants underwent 3D multi-delay pCASL-MRI to obtain cerebral perfusion data, including arrival-time-corrected cerebral blood flow (CBF) and arterial cerebral blood volume (aCBV). The automated anatomical labeling atlas 3 (AAL3) was used to parcellate 170 brain regions. The CBF and aCBV values in each brain region were compared among the three groups. Correlation analyses between cerebral perfusion parameters and clinical variables were performed.

RESULTS

Compared with HC participants, patients with NDPH were found to have decreased CBF and aCBV values in multiple regions in the right hemisphere, including the right posterior orbital gyrus (OFCpost.R), right middle occipital gyrus (MOG.R), and ventral anterior nucleus of right thalamus (tVA.R), while patients with CM showed increased CBF and aCBV values presenting in the ventral lateral nucleus of left thalamus (tVL.L) and right thalamus (tVL.R) compared with HCs (all p < 0.05). In patients with NDPH, after age and sex adjustment, the increased aCBV values of IFGorb. R were positively correlated with GAD-7 scores; and the increased CBF and aCBV values of tVA.R were positively correlated with disease duration.

CONCLUSION

The multi-delay pCASL technique can detect cerebral perfusion variation in patients with NDPH and CM. The cerebral perfusion changes may suggest different variations between NDPH and CM, which might provide hemodynamic evidence of these two types of primary headaches.

Estimation of Cerebral Blood Flow and Arterial Transit Time From Multi-Delay Arterial Spin Labeling MRI Using a Simulation-Based Supervised Deep Neural Network

BACKGROUND

An inherently poor signal-to-noise ratio (SNR) causes inaccuracy and less precision in cerebral blood flow (CBF) and arterial transit time (ATT) when using arterial spin labeling (ASL). Deep neural network (DNN)-based parameter estimation can solve these problems.

PURPOSE

To reduce the effects of Rician noise on ASL parameter estimation and compute unbiased CBF and ATT using simulation-based supervised DNNs.

STUDY TYPE

Retrospective.

POPULATION

One million simulation test data points, 17 healthy volunteers (five women and 12 men, 33.2 ± 14.6 years of age), and one patient with moyamoya disease.

FIELD STRENGTH/SEQUENCE

3.0 T/Hadamard-encoded pseudo-continuous ASL with a three-dimensional fast spin-echo stack of spirals.

ASSESSMENT

Performances of DNN and conventional methods were compared. For test data, the normalized mean absolute error (NMAE) and normalized root mean squared error (NRMSE) between the ground truth and predicted values were evaluated. For in vivo data, baseline CBF and ATT and their relative changes with respect to SNR using artificial noise-added images were assessed.

STATISTICAL TESTS

One-way analysis of variance with post-hoc Tukey's multiple comparison test, paired t-test, and the Bland-Altman graphical analysis. Statistical significance was defined as P < 0.05.

RESULTS

For both CBF and ATT, NMAE and NRMSE were lower with DNN than with the conventional method. The baseline values were significantly smaller with DNN than with the conventional method (CBF in gray matter, 66 ± 10 vs. 71 ± 12 mL/100 g/min; white matter, 45 ± 6 vs. 46 ± 7 mL/100 g/min; ATT in gray matter, 1424 ± 201 vs. 1471 ± 154 msec). CBF and ATT increased with decreasing SNR; however, their change rates were smaller with DNN than were those with the conventional method. Higher CBF in the prolonged ATT region and clearer contrast in ATT were identified by DNN in a clinical case.

DATA CONCLUSION

DNN outperformed the conventional method in terms of accuracy, precision, and noise immunity.

EVIDENCE LEVEL

3 Technical Efficacy: Stage 1.