Machine Learning for Rapid Magnetic Resonance Fingerprinting Tissue Property Quantification.
Ontology highlight
ABSTRACT:
SUBMITTER: Hamilton JI
PROVIDER: S-EPMC7595247 | biostudies-literature | 2020 Jan
REPOSITORIES: biostudies-literature
Publications
Machine Learning for Rapid Magnetic Resonance Fingerprinting Tissue Property Quantification.
Hamilton Jesse I JI Seiberlich Nicole N
Proceedings of the IEEE. Institute of Electrical and Electronics Engineers 20190911 1
Magnetic Resonance Fingerprinting (MRF) is an MRI-based method that can provide quantitative maps of multiple tissue properties simultaneously from a single rapid acquisition. Tissue property maps are generated by matching the complex signal evolutions collected at the scanner to a dictionary of signals derived using Bloch equation simulations. However, in some circumstances, the process of dictionary generation and signal matching can be time-consuming, reducing the utility of this technique. R ...[more]
Similar Datasets
Project description:Magnetic resonance fingerprinting (MRF) is a quantitative imaging technique that can simultaneously measure multiple important tissue properties of human body. Although MRF has demonstrated improved scan efficiency as compared to conventional techniques, further acceleration is still desired for translation into routine clinical practice. The purpose of this paper is to accelerate MRF acquisition by developing a new tissue quantification method for MRF that allows accurate quantification with fewer sampling data. Most of the existing approaches use the MRF signal evolution at each individual pixel to estimate tissue properties, without considering the spatial association among neighboring pixels. In this paper, we propose a spatially constrained quantification method that uses the signals at multiple neighboring pixels to better estimate tissue properties at the central pixel. Specifically, we design a unique two-step deep learning model that learns the mapping from the observed signals to the desired properties for tissue quantification, i.e.: 1) with a feature extraction module for reducing the dimension of signals by extracting a low-dimensional feature vector from the high-dimensional signal evolution and 2) a spatially constrained quantification module for exploiting the spatial information from the extracted feature maps to generate the final tissue property map. A corresponding two-step training strategy is developed for network training. The proposed method is tested on highly undersampled MRF data acquired from human brains. Experimental results demonstrate that our method can achieve accurate quantification for T1 and T2 relaxation times by using only 1/4 time points of the original sequence (i.e., four times of acceleration for MRF acquisition).
| S-EPMC6692257 | biostudies-literature
Project description:The purpose of this work was to develop a 31 P spectroscopic magnetic resonance fingerprinting (MRF) method for fast quantification of the chemical exchange rate between phosphocreatine (PCr) and adenosine triphosphate (ATP) via creatine kinase (CK). A 31 P MRF sequence (CK-MRF) was developed to quantify the forward rate constant of ATP synthesis via CK ( kfCK), the T1 relaxation time of PCr ( T1PCr), and the PCr-to-ATP concentration ratio ( MRPCr). The CK-MRF sequence used a balanced steady-state free precession (bSSFP)-type excitation with ramped flip angles and a unique saturation scheme sensitive to the exchange between PCr and γATP. Parameter estimation was accomplished by matching the acquired signals to a dictionary generated using the Bloch-McConnell equation. Simulation studies were performed to examine the susceptibility of the CK-MRF method to several potential error sources. The accuracy of nonlocalized CK-MRF measurements before and after an ischemia-reperfusion (IR) protocol was compared with the magnetization transfer (MT-MRS) method in rat hindlimb at 9.4 T (n = 14). The reproducibility of CK-MRF was also assessed by comparing CK-MRF measurements with both MT-MRS (n = 17) and four angle saturation transfer (FAST) (n = 7). Simulation results showed that CK-MRF quantification of kfCK was robust, with less than 5% error in the presence of model inaccuracies including dictionary resolution, metabolite T2 values, inorganic phosphate metabolism, and B1 miscalibration. Estimation of kfCK by CK-MRF (0.38 ± 0.02 s-1 at baseline and 0.42 ± 0.03 s-1 post-IR) showed strong agreement with MT-MRS (0.39 ± 0.03 s-1 at baseline and 0.44 ± 0.04 s-1 post-IR). kfCK estimation was also similar between CK-MRF and FAST (0.38 ± 0.02 s-1 for CK-MRF and 0.38 ± 0.11 s-1 for FAST). The coefficient of variation from 20 s CK-MRF quantification of kfCK was 42% of that by 150 s MT-MRS acquisition and was 12% of that by 20 s FAST acquisition. This study demonstrates the potential of a 31 P spectroscopic MRF framework for rapid, accurate and reproducible quantification of chemical exchange rate of CK in vivo.
| S-EPMC5690599 | biostudies-literature
Project description:Magnetic resonance is an exceptionally powerful and versatile measurement technique. The basic structure of a magnetic resonance experiment has remained largely unchanged for almost 50?years, being mainly restricted to the qualitative probing of only a limited set of the properties that can in principle be accessed by this technique. Here we introduce an approach to data acquisition, post-processing and visualization--which we term 'magnetic resonance fingerprinting' (MRF)--that permits the simultaneous non-invasive quantification of multiple important properties of a material or tissue. MRF thus provides an alternative way to quantitatively detect and analyse complex changes that can represent physical alterations of a substance or early indicators of disease. MRF can also be used to identify the presence of a specific target material or tissue, which will increase the sensitivity, specificity and speed of a magnetic resonance study, and potentially lead to new diagnostic testing methodologies. When paired with an appropriate pattern-recognition algorithm, MRF inherently suppresses measurement errors and can thus improve measurement accuracy.
| S-EPMC3602925 | biostudies-literature
Project description:PurposeTo develop a rapid 2D MR fingerprinting technique with a submillimeter in-plane resolution using a deep learning-based tissue quantification approach.MethodsA rapid and high-resolution MR fingerprinting technique was developed for brain T1 and T2 quantification. The 2D acquisition was performed using a FISP-based MR fingerprinting sequence and a spiral trajectory with 0.8-mm in-plane resolution. A deep learning-based method was used to replace the standard template matching method for improved tissue characterization. A novel network architecture (i.e., residual channel attention U-Net) was proposed to improve high-resolution details in the estimated tissue maps. Quantitative brain imaging was performed with 5 adults and 2 pediatric subjects, and the performance of the proposed approach was compared with several existing methods in the literature.ResultsIn vivo measurements with both adult and pediatric subjects show that high-quality T1 and T2 mapping with 0.8-mm in-plane resolution can be achieved in 7.5 seconds per slice. The proposed deep learning method outperformed existing algorithms in tissue quantification with improved accuracy. Compared with the standard U-Net, high-resolution details in brain tissues were better preserved by the proposed residual channel attention U-Net. Experiments on pediatric subjects further demonstrated the potential of the proposed technique for fast pediatric neuroimaging. Alongside reduced data acquisition time, a 5-fold acceleration in tissue property mapping was also achieved with the proposed method.ConclusionA rapid and high-resolution MR fingerprinting technique was developed, which enables high-quality T1 and T2 quantification with 0.8-mm in-plane resolution in 7.5 seconds per slice.
| S-EPMC8210473 | biostudies-literature
Project description:PURPOSE:To minimize the known biases introduced by fat in rapid T1 and T2 quantification in muscle using a single-run magnetic resonance fingerprinting (MRF) water-fat separation sequence. METHODS:The single-run MRF acquisition uses an alternating in-phase/out-of-phase TE pattern to achieve water-fat separation based on a 2-point DIXON method. Conjugate phase reconstruction and fat deblurring were applied to correct for B0 inhomogeneities and chemical shift blurring. Water and fat signals were matched to the on-resonance MRF dictionary. The method was first tested in a multicompartment phantom. To test whether the approach is capable of measuring small in vivo dynamic changes in relaxation times, experiments were run in 9 healthy volunteers; parameter values were compared with and without water-fat separation during muscle recovery after plantar flexion exercise. RESULTS:Phantom results show the robustness of the water-fat resolving MRF approach to undersampling. Parameter maps in volunteers show a significant (P < .01) increase in T1 (105 ± 94 ms) and decrease in T2 (14 ± 6 ms) when using water-fat-separated MRF, suggesting improved parameter quantification by reducing the well-known biases introduced by fat. Exercise results showed smooth T1 and T2 recovery curves. CONCLUSION:Water-fat separation using conjugate phase reconstruction is possible within a single-run MRF scan. This technique can be used to rapidly map relaxation times in studies requiring dynamic scanning, in which the presence of fat is problematic.
| S-EPMC7217066 | biostudies-literature
Project description:BACKGROUND:Phase contrast (PC) cardiovascular magnetic resonance (CMR) is widely employed for flow quantification, but analysis typically requires time consuming manual segmentation which can require human correction. Advances in machine learning have markedly improved automated processing, but have yet to be applied to PC-CMR. This study tested a novel machine learning model for fully automated analysis of PC-CMR aortic flow. METHODS:A machine learning model was designed to track aortic valve borders based on neural network approaches. The model was trained in a derivation cohort encompassing 150 patients who underwent clinical PC-CMR then compared to manual and commercially-available automated segmentation in a prospective validation cohort. Further validation testing was performed in an external cohort acquired from a different site/CMR vendor. RESULTS:Among 190 coronary artery disease patients prospectively undergoing CMR on commercial scanners (84% 1.5T, 16% 3T), machine learning segmentation was uniformly successful, requiring no human intervention: Segmentation time was <?0.01?min/case (1.2?min for entire dataset); manual segmentation required 3.96?±?0.36?min/case (12.5?h for entire dataset). Correlations between machine learning and manual segmentation-derived flow approached unity (r?=?0.99, p?<?0.001). Machine learning yielded smaller absolute differences with manual segmentation than did commercial automation (1.85?±?1.80 vs. 3.33?±?3.18?mL, p?<?0.01): Nearly all (98%) of cases differed by ?5?mL between machine learning and manual methods. Among patients without advanced mitral regurgitation, machine learning correlated well (r?=?0.63, p?<?0.001) and yielded small differences with cine-CMR stroke volume (? 1.3?±?17.7?mL, p?=?0.36). Among advanced mitral regurgitation patients, machine learning yielded lower stroke volume than did volumetric cine-CMR (? 12.6?±?20.9?mL, p?=?0.005), further supporting validity of this method. Among the external validation cohort (n?=?80) acquired using a different CMR vendor, the algorithm yielded equivalently small differences (? 1.39?±?1.77?mL, p?=?0.4) and high correlations (r?=?0.99, p?<?0.001) with manual segmentation, including similar results in 20 patients with bicuspid or stenotic aortic valve pathology (? 1.71?±?2.25?mL, p?=?0.25). CONCLUSION:Fully automated machine learning PC-CMR segmentation performs robustly for aortic flow quantification - yielding rapid segmentation, small differences with manual segmentation, and identification of differential forward/left ventricular volumetric stroke volume in context of concomitant mitral regurgitation. Findings support use of machine learning for analysis of large scale CMR datasets.
| S-EPMC6322266 | biostudies-literature
Project description:PurposeTo study the effects of magnetization transfer (MT, in which a semi-solid spin pool interacts with the free pool), in the context of magnetic resonance fingerprinting (MRF).MethodsSimulations and phantom experiments were performed to study the impact of MT on the MRF signal and its potential influence on T1 and T2 estimation. Subsequently, an MRF sequence implementing off-resonance MT pulses and a dictionary with an MT dimension, generated by incorporating a two-pool model, were used to estimate the fractional pool size in addition to the B1+ , T1 , and T2 values. The proposed method was evaluated in the human brain.ResultsSimulations and phantom experiments showed that an MRF signal obtained from a cross-linked bovine serum sample is influenced by MT. Using a dictionary based on an MT model, a better match between simulations and acquired MR signals can be obtained (NRMSE 1.3% vs. 4.7%). Adding off-resonance MT pulses can improve the differentiation of MT from T1 and T2 . In vivo results showed that MT affects the MRF signals from white matter (fractional pool-size ~16%) and gray matter (fractional pool-size ~10%). Furthermore, longer T1 (~1060 ms vs. ~860 ms) and T2 values (~47 ms vs. ~35 ms) can be observed in white matter if MT is accounted for.ConclusionOur experiments demonstrated a potential influence of MT on the quantification of T1 and T2 with MRF. A model that encompasses MT effects can improve the accuracy of estimated relaxation parameters and allows quantification of the fractional pool size.
| S-EPMC7083689 | biostudies-literature
Project description:PurposeDevelop a method for rigid body motion-corrected magnetic resonance fingerprinting (MRF).MethodsMRF has shown some robustness to abrupt motion toward the end of the acquisition. Here, we study the effects of different types of rigid body motion during the acquisition on MRF and propose a novel approach to correct for this motion. The proposed method (MC-MRF) follows 4 steps: (1) sliding window reconstruction is performed to produce high-quality auxiliary dynamic images; (2) rotation and translation motion is estimated from the dynamic images by image registration; (3) estimated motion is used to correct acquired k-space data with corresponding rotations and phase shifts; and (4) motion-corrected data are reconstructed with low-rank inversion. MC-MRF was validated in a standard T1 /T2 phantom and 2D in vivo brain acquisitions in 7 healthy subjects. Additionally, the effect of through-plane motion in 2D MC-MRF was investigated.ResultsSimulation results show that motion in MRF can introduce artifacts in T1 and T2 maps, depending when it occurs. MC-MRF improved parametric map quality in all phantom and in vivo experiments with in-plane motion, comparable to the no-motion ground truth. Reduced parametric map quality, even after motion correction, was observed for acquisitions with through-plane motion, particularly for smaller structures in T2 maps.ConclusionHere, a novel method for motion correction in MRF (MC-MRF) is proposed, which improves parametric map quality and accuracy in comparison to no-motion correction approaches. Future work will include validation of 3D MC-MRF to enable also through-plane motion correction.
| S-EPMC6519164 | biostudies-literature
Project description:PURPOSE:To develop a fast magnetic resonance fingerprinting (MRF) method for quantitative chemical exchange saturation transfer (CEST) imaging. METHODS:We implemented a CEST-MRF method to quantify the chemical exchange rate and volume fraction of the N? -amine protons of L-arginine (L-Arg) phantoms and the amide and semi-solid exchangeable protons of in vivo rat brain tissue. L-Arg phantoms were made with different concentrations (25-100?mM) and pH (pH?4-6). The MRF acquisition schedule varied the saturation power randomly for 30 iterations (phantom: 0-6??T; in vivo: 0-4??T) with a total acquisition time of ?2?min. The signal trajectories were pattern-matched to a large dictionary of signal trajectories simulated using the Bloch-McConnell equations for different combinations of exchange rate, exchangeable proton volume fraction, and water T1 and T2 relaxation times. RESULTS:The chemical exchange rates of the N? -amine protons of L-Arg were significantly (P?<?0.0001) correlated with the rates measured with the quantitation of exchange using saturation power method. Similarly, the L-Arg concentrations determined using MRF were significantly (P?<?0.0001) correlated with the known concentrations. The pH dependence of the exchange rate was well fit (R2 ?=?0.9186) by a base catalyzed exchange model. The amide proton exchange rate measured in rat brain cortex (34.8?±?11.7?Hz) was in good agreement with that measured previously with the water exchange spectroscopy method (28.6?±?7.4?Hz). The semi-solid proton volume fraction was elevated in white (12.2?±?1.7%) compared to gray (8.1?± 1.1%) matter brain regions in agreement with previous magnetization transfer studies. CONCLUSION:CEST-MRF provides a method for fast, quantitative CEST imaging.
| S-EPMC6234098 | biostudies-literature
Project description:Quantitative assessment of brain myelination has gained attention for both research and diagnosis of neurological diseases. However, conventional pulse sequences cannot directly acquire the myelin-proton signals due to its extremely short T2 and T2* values. To obtain the myelin-proton signals, dedicated short T2 acquisition techniques, such as ultrashort echo time (UTE) imaging, have been introduced. However, it remains challenging to isolate the myelin-proton signals from tissues with longer T2. In this article, we extended our previous two-dimensional ultrashort echo time magnetic resonance fingerprinting (UTE-MRF) with dual-echo acquisition to three dimensional (3D). Given a relatively low proton density (PD) of myelin-proton, we utilized Cramér-Rao Lower Bound to encode myelin-proton with the maximal SNR efficiency for optimizing the MR fingerprinting design, in order to improve the sensitivity of the sequence to myelin-proton. In addition, with a second echo of approximately 3 ms, myelin-water component can be also captured. A myelin-tissue (myelin-proton and myelin-water) fraction mapping can be thus calculated. The optimized 3D UTE-MRF with dual-echo acquisition is tested in simulations, physical phantom and in vivo studies of both healthy subjects and multiple sclerosis patients. The results suggest that the rapidly decayed myelin-proton and myelin-water signal can be depicted with UTE signals of our method at clinically relevant resolution (1.8 mm isotropic) in 15 min. With its good sensitivity to myelin loss in multiple sclerosis patients demonstrated, our method for the whole brain myelin-tissue fraction mapping in clinical friendly scan time has the potential for routine clinical imaging.
| S-EPMC10028641 | biostudies-literature