ABSTRACT
(1) Background: Functional magnetic resonance imaging (fMRI) utilizing multi-echo gradient echo-planar imaging (ME-GE-EPI) has demonstrated higher sensitivity and stability compared to utilizing single-echo gradient echo-planar imaging (SE-GE-EPI). The direct derivation of T2* maps from fitting multi-echo data enables accurate recording of dynamic functional changes in the brain, exhibiting higher sensitivity than echo combination maps. However, the widely employed voxel-wise log-linear fitting is susceptible to inevitable noise accumulation during image acquisition. (2) Methods: This work introduced a synthetic data-driven deep learning (SD-DL) method to obtain T2* maps for multi-echo (ME) fMRI analysis. (3) Results: The experimental results showed the efficient enhancement of the temporal signal-to-noise ratio (tSNR), improved task-based blood oxygen level-dependent (BOLD) percentage signal change, and enhanced performance in multi-echo independent component analysis (MEICA) using the proposed method. (4) Conclusion: T2* maps derived from ME-fMRI data using the proposed SD-DL method exhibit enhanced BOLD sensitivity in comparison to T2* maps derived from the LLF method.
ABSTRACT
Laplace NMR is a powerful tool for studying molecular dynamics and spin interactions, providing diffusion and relaxation information that complements Fourier NMR used for composition determination and structure elucidation. However, Laplace NMR demands sophisticated signal processing algorithms such as inverse Laplace transform (ILT). Due to the inherently ill-posed nature of ILT problems, it is generally challenging to perform satisfactory Laplace NMR processing and reconstruction, particularly for two-dimensional Laplace NMR. Herein, we propose a proof-of-concept approach that blends a physics-informed strategy with data-driven deep learning for two-dimensional Laplace NMR reconstruction. This approach integrates prior knowledge of mathematical and physical laws governing multidimensional decay signals by constructing a forward process model to simulate relationships among different decay factors. Benefiting from a noniterative neural network algorithm that automatically acquires prior information from synthetic data during training, this approach avoids tedious parameter tuning and enhances user friendliness. Experimental results demonstrate the practical effectiveness of this approach. As an advanced and impactful technique, this approach brings a fresh perspective to multidimensional Laplace NMR inversion.
ABSTRACT
Autism spectrum disorder (ASD) is a common neurodevelopmental disorder. Functional magnetic resonance imaging (fMRI) can be used to measure the temporal correlation of blood-oxygen-level-dependent (BOLD) signals in the brain to assess the brain's intrinsic connectivity and capture dynamic changes in the brain. In this study, the hidden Markov model (HMM) and dynamic graph (DG) theory are used to study the spatial-temporal characteristics and dynamics of brain networks based on dynamic functional connectivity (DFC). By using HMM, we identified three typical brain states for ASD and healthy control (HC). Furthermore, we explored the correlation between HMM time-varying properties and clinical autism scale scores. Differences in brain topological characteristics and dynamics between ASD and HC were compared by DG analysis. The experimental results indicate that ASD is more inclined to enter a strongly connected HMM brain state, leading to the isolation of brain networks and alterations in the topological characteristics of brain networks, such as default mode network (DMN), ventral attention network (VAN), and visual network (VN). This work suggests that using different data-driven methods based on DFC to study brain network dynamics would have better information complementarity, which can provide a new direction for the extraction of neuro-biomarkers in the early diagnosis of ASD.
ABSTRACT
Objective. Most deep neural network-based diffusion tensor imaging methods require the diffusion gradients' number and directions in the data to be reconstructed to match those in the training data. This work aims to develop and evaluate a novel dynamic-convolution-based method called FlexDTI for highly efficient diffusion tensor reconstruction with flexible diffusion encoding gradient scheme.Approach. FlexDTI was developed to achieve high-quality DTI parametric mapping with flexible number and directions of diffusion encoding gradients. The method used dynamic convolution kernels to embed diffusion gradient direction information into feature maps of the corresponding diffusion signal. Furthermore, it realized the generalization of a flexible number of diffusion gradient directions by setting the maximum number of input channels of the network. The network was trained and tested using datasets from the Human Connectome Project and local hospitals. Results from FlexDTI and other advanced tensor parameter estimation methods were compared.Main results. Compared to other methods, FlexDTI successfully achieves high-quality diffusion tensor-derived parameters even if the number and directions of diffusion encoding gradients change. It reduces normalized root mean squared error by about 50% on fractional anisotropy and 15% on mean diffusivity, compared with the state-of-the-art deep learning method with flexible diffusion encoding gradient scheme.Significance. FlexDTI can well learn diffusion gradient direction information to achieve generalized DTI reconstruction with flexible diffusion gradient scheme. Both flexibility and reconstruction quality can be taken into account in this network.
Subject(s)
Deep Learning , Diffusion Tensor Imaging , Image Processing, Computer-Assisted , Diffusion Tensor Imaging/methods , Humans , Image Processing, Computer-Assisted/methodsABSTRACT
BACKGROUND: Non-small cell lung cancer (NSCLC) is a highly prevalent and fatal form of lung cancer. In China, Aconiti Lateralis Radix Praeparata (Fuzi in Chinese), derived from the lateral root of Aconitum carmichaeli Debx. (Ranunculaceae, Aconitum), is extensively prescribed to treat cancer in traditional medicine and clinical practice. However, the precise mechanism by which Fuzi treats NSCLC remains unknown. PURPOSE: This article aims to assess the efficacy of Fuzi against NSCLC and elucidate its underlying mechanism. METHODS: Marker ingredients of Fuzi decoction were quantified using UPLC-TSQ-MS. The effectiveness of Fuzi on NSCLC was evaluated using a xenograft mouse model. Subsequently, a comprehensive approach involving network pharmacology, serum metabolomics, and 16S rDNA sequencing was employed to investigate the anti-NSCLC mechanism of Fuzi. RESULTS: Pharmacological evaluation revealed significant tumour growth inhibition by Fuzi, accompanied by minimal toxicity. Network pharmacology identified 29 active Fuzi compounds influencing HIF-1, PI3K/Akt signalling, and central carbon metabolism in NSCLC. Integrating untargeted serum metabolomics highlighted 30 differential metabolites enriched in aminoacyl-tRNA biosynthesis, alanine, aspartate, and glutamate metabolism, and the tricarboxylic acid (TCA) cycle. Targeted serum metabolomics confirmed elevated glucose content and reduced levels of pyruvate, lactate, citrate, α-ketoglutarate, succinate, fumarate, and malate following Fuzi administration. Furthermore, 16S rDNA sequencing assay showed that Fuzi ameliorated the dysbiosis after tumorigenesis, decreased the abundance of Proteobacteria, and increased that of Firmicutes and Bacteriodetes. PICRUSt analysis revealed that Fuzi modulated the pentose phosphate pathway of the gut microbiota. Spearman correlation showed that Proteobacteria and Escherichia_Shigella accelerated the TCA cycle, whereas Bacteroidota, Bacteroides, and Lachnospiraceae_NK4A136_group suppressed the TCA cycle. CONCLUSIONS: This study firstly introduces a novel NSCLC mechanism involving Fuzi, encompassing energy metabolism and intestinal flora. It clarifies the pivotal role of the gut microbiota in treating NSCLC and modulating the TCA cycle. Moreover, these findings offer valuable insights for clinical practices and future research of Fuzi against NSCLC.
Subject(s)
Aconitum , Carcinoma, Non-Small-Cell Lung , Drugs, Chinese Herbal , Lung Neoplasms , Humans , Mice , Animals , Plant Extracts/pharmacology , Carcinoma, Non-Small-Cell Lung/drug therapy , Dysbiosis/drug therapy , Phosphatidylinositol 3-Kinases , Lung Neoplasms/drug therapy , Drugs, Chinese Herbal/pharmacology , DNA, RibosomalABSTRACT
Objective. Diffusion tensor imaging (DTI) is excellent for non-invasively quantifying tissue microstructure. Theoretically DTI can be achieved with six different diffusion weighted images and one reference image, but the tensor estimation accuracy is poor in this case. Increasing the number of diffusion directions has benefits for the tensor estimation accuracy, which results in long scan time and makes DTI sensitive to motion. It would be beneficial to decrease the scan time of DTI by using fewer diffusion-weighted images without compromising reconstruction quality.Approach. A novel DTI scan scheme was proposed to achieve fast DTI, where only three diffusion directions per slice was required under a specific direction switching manner, and a deep-learning based reconstruction method was utilized using multi-slice information sharing and correspondingT1-weighted image for high-quality DTI reconstruction. A network with two encoders developed from U-Net was implemented for better utilizing the diffusion data redundancy between neighboring slices. The method performed direct nonlinear mapping from diffusion-weighted images to diffusion tensor.Main results. The performance of the proposed method was verified on the Human Connectome Project public data and clinical patient data. High-quality mean diffusivity, fractional anisotropy, and directionally encoded colormap can be achieved with only three diffusion directions per slice.Significance. High-quality DTI-derived maps can be achieved in less than one minute of scan time. The great reduction of scan time will help push the wider application of DTI in clinical practice.
Subject(s)
Deep Learning , Diffusion Tensor Imaging , Humans , Diffusion Tensor Imaging/methods , Algorithms , Diffusion Magnetic Resonance Imaging , AnisotropyABSTRACT
RATIONALE AND OBJECTIVES: This project aims to investigate the diagnostic performance of multiple overlapping-echo detachment imaging (MOLED) technique-derived transverse relaxation time (T2) maps in predicting progesterone receptor (PR) and S100 expression in meningiomas. MATERIALS AND METHODS: 63 meningioma patients were enrolled from October 2021 to August 2022, who underwent a complete routine magnetic resonance imaging and T2 MOLED, which can characterize the whole brain transverse relaxation time within 32 seconds in a single scan. After the surgical resection of meningiomas, the expression levels of PR and S100 were determined by an experienced pathologist using immunohistochemistry techniques. Histogram analysis was performed in tumor parenchyma based on the parametric maps. Independent t test and Mann-Whitney U test were applied for the comparison of histogram parameters between different groups, with a significance level of P < .05. Logistic regression and receiver operating characteristic (ROC) analysis with 95% confidence interval were conducted for the diagnostic efficiency evaluation. RESULTS: PR-positive group had significantly elevated T2 histogram parameters (P = .001-.049) compared to the PR-negative group. The multivariate logistic regression model with T2 showed the highest area under the ROC curve (AUC) for predicting PR expression (AUC=0.818). Additionally, the multivariate model also had the best diagnostic performance for predicting meningioma S100 expression (AUC=0.768). CONCLUSION: The MOLED technique-derived T2 maps can distinguish PR and S100 status in meningiomas preoperatively.
Subject(s)
Meningeal Neoplasms , Meningioma , Humans , Meningioma/diagnostic imaging , Meningioma/surgery , Meningioma/pathology , Diffusion Magnetic Resonance Imaging/methods , Prospective Studies , Receptors, Progesterone , Magnetic Resonance Imaging/methods , Meningeal Neoplasms/diagnostic imaging , Meningeal Neoplasms/surgery , Meningeal Neoplasms/pathology , Retrospective StudiesABSTRACT
RATIONALE AND OBJECTIVES: Stroke patients commonly face challenges during magnetic resonance imaging (MRI) examinations due to involuntary movements. This study aims to overcome these challenges by utilizing multiple overlapping-echo detachment (MOLED) quantitative technology. Through this technology, we also seek to detect microstructural changes of the normal-appearing corticospinal tract (NA-CST) in subacute-chronic stroke patients. MATERIALS AND METHODS: 79 patients underwent 3.0 T MRI scans, including routine scans and MOLED technique. A deep learning network was utilized for image reconstruction, and the accuracy, reliability, and resistance to motion of the MOLED technique were validated on phantoms and volunteers. Subsequently, we assessed motor dysfunction severity, ischemic lesion volume, T2 values of the bilateral NA-CST, and the T2 ratio (rT2) between the ipsilesional and contralesional NA-CST in patients. RESULTS: The MOLED technique showed high accuracy (P < 0.001) and excellent repeatability, with a mean coefficient of variation (CoV) of 1.11%. It provided reliable quantitative results even under head movement, with a mean difference (Meandiff)= 0.28% and a standard deviation difference (SDdiff)= 1.34%. Additionally, the T2 value of the ipsilesional NA-CST was significantly higher than contralesional side (P < 0.001), and a positive correlation was observed between rT2 and the severity of motor dysfunction (rs =0.575, P < 0.001). Furthermore, rT2 successfully predicted post-stroke motor impairment, with an area under the curve (AUC) was 0.883. CONCLUSION: The MOLED technique offers significant advantages for quantitatively imaging stroke patients with involuntary movements. Additionally, T2 mapping from MOLED can detect microstructural changes in the NA-CST, potentially aiding in monitoring stroke-induced motor impairment.
Subject(s)
Magnetic Resonance Imaging , Pyramidal Tracts , Stroke , Humans , Male , Female , Middle Aged , Pyramidal Tracts/diagnostic imaging , Stroke/diagnostic imaging , Stroke/complications , Magnetic Resonance Imaging/methods , Aged , Reproducibility of Results , Chronic Disease , Adult , Motion , Phantoms, Imaging , Deep LearningABSTRACT
BACKGROUND: Meningioma subtype is crucial in treatment planning and prognosis delineation, for grade 1 meningiomas. T2 relaxometry could provide detailed microscopic information but is often limited by long scanning times. PURPOSE: To investigate the potential of T2 maps derived from multiple overlapping-echo detachment imaging (MOLED) for predicting meningioma subtypes and Ki-67 index, and to compare the diagnostic efficiency of two different region-of-interest (ROI) placements (whole-tumor and contrast-enhanced, respectively). STUDY TYPE: Prospective. PHANTOM/SUBJECTS: A phantom containing 11 tubes of MnCl2 at different concentrations, eight healthy volunteers, and 75 patients with grade 1 meningioma. FIELD STRENGTH/SEQUENCE: 3 T scanner. MOLED, T2-weighted spin-echo sequence, T2-dark-fluid sequence, and postcontrast T1-weighted gradient echo sequence. ASSESSMENT: Two ROIs were delineated: the whole-tumor area (ROI1) and contrast-enhanced area (ROI2). Histogram parameters were extracted from T2 maps. Meningioma subtypes and Ki-67 index were reviewed by a neuropathologist according to the 2021 classification criteria. STATISTICAL TESTS: Linear regression, Bland-Altman analysis, Pearson's correlation analysis, independent t test, Mann-Whitney U test, Kruskal-Wallis test with Bonferroni correction, and multivariate logistic regression analysis with the P-value significance level of 0.05. RESULTS: The MOLED T2 sequence demonstrated excellent accuracy for phantoms and volunteers (Meandiff = -1.29%, SDdiff = 1.25% and Meandiff = 0.36%, SDdiff = 2.70%, respectively), and good repeatability for volunteers (average coefficient of variance = 1.13%; intraclass correlation coefficient = 0.877). For both ROI1 and ROI2, T2 variance had the highest area under the curves (area under the ROC curve = 0.768 and 0.761, respectively) for meningioma subtyping. There was no significant difference between the two ROIs (P = 0.875). Significant correlations were observed between T2 parameters and Ki-67 index (r = 0.237-0.374). DATA CONCLUSION: MOLED T2 maps can effectively differentiate between meningothelial, fibrous, and transitional meningiomas. Moreover, T2 histogram parameters were significantly correlated with the Ki-67 index. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY: Stage 2.
Subject(s)
Magnetic Resonance Imaging , Meningeal Neoplasms , Meningioma , Phantoms, Imaging , Humans , Meningioma/diagnostic imaging , Female , Male , Meningeal Neoplasms/diagnostic imaging , Meningeal Neoplasms/pathology , Middle Aged , Magnetic Resonance Imaging/methods , Adult , Prospective Studies , Aged , Ki-67 Antigen/metabolism , Contrast Media , ROC Curve , Neoplasm GradingABSTRACT
Objective. Most quantitative magnetic resonance imaging (qMRI) methods are time-consuming. Multiple overlapping-echo detachment (MOLED) imaging can achieve quantitative parametric mapping of a single slice within around one hundred milliseconds. Nevertheless, imaging the whole brain, which involves multiple slices, still takes a few seconds. To further accelerate qMRI, we introduce multiband SENSE (MB-SENSE) technology to MOLED to realize simultaneous multi-slice T2mapping.Approach.The multiband MOLED (MB-MOLED) pulse sequence was carried out to acquire raw overlapping-echo signals, and deep learning was utilized to reconstruct T2maps. To address the issue of image quality degradation due to a high multiband factor MB, a plug-and-play (PnP) algorithm with prior denoisers (DRUNet) was applied. U-Net was used for T2map reconstruction. Numerical simulations, water phantom experiments and human brain experiments were conducted to validate our proposed approach.Main results.Numerical simulations show that PnP algorithm effectively improved the quality of reconstructed T2maps at low signal-to-noise ratios. Water phantom experiments indicate that MB-MOLED inherited the advantages of MOLED and its results were in good agreement with the results of reference method.In vivoexperiments for MB = 1, 2, 4 without the PnP algorithm, and 4 with PnP algorithm indicate that the use of PnP algorithm improved the quality of reconstructed T2maps at a high MB. For the first time, with MB = 4, T2mapping of the whole brain was achieved within 600 ms.Significance.MOLED and MB-SENSE can be combined effectively. This method enables sub-second T2mapping of the whole brain. The PnP algorithm can improve the quality of reconstructed T2maps. The novel approach shows significant promise in applications necessitating high temporal resolution, such as functional and dynamic qMRI.
ABSTRACT
Objective. The acquisition of diffusion-weighted images for intravoxel incoherent motion (IVIM) imaging is time consuming. This work aims to accelerate the scan through a highly under-sampling diffusion-weighted turbo spin echo PROPELLER (DW-TSE-PROPELLER) scheme and to develop a reconstruction method for accurate IVIM parameter mapping from the under-sampled data.Approach.The proposed under-sampling DW-TSE-PROPELLER scheme for IVIM imaging is that a few blades perb-value are acquired and rotated along theb-value dimension to cover high-frequency information. A physics-informed residual feedback unrolled network (PIRFU-Net) is proposed to directly estimate distortion-free and artifact-free IVIM parametric maps (i.e., the perfusion-free diffusion coefficientDand the perfusion fractionf) from highly under-sampled DW-TSE-PROPELLER data. PIRFU-Net used an unrolled convolution network to explore data redundancy in the k-q space to remove under-sampling artifacts. An empirical IVIM physical constraint was incorporated into the network to ensure that the signal evolution curves along theb-value follow a bi-exponential decay. The residual between the realistic and estimated measurements was fed into the network to refine the parametric maps. Meanwhile, the use of synthetic training data eliminated the need for genuine DW-TSE-PROPELLER data.Main results.The experimental results show that the DW-TSE-PROPELLER acquisition was six times faster than full k-space coverage PROPELLER acquisition and within a clinically acceptable time. Compared with the state-of-the-art methods, the distortion-freeDandfmaps estimated by PIRFU-Net were more accurate and had better-preserved tissue boundaries on a simulated human brain and realistic phantom/rat brain/human brain data.Significance.Our proposed method greatly accelerates IVIM imaging. It is capable of directly and simultaneously reconstructing distortion-free, artifact-free, and accurateDandfmaps from six-fold under-sampled DW-TSE-PROPELLER data.
Subject(s)
Diffusion Magnetic Resonance Imaging , Magnetic Resonance Imaging , Humans , Diffusion Magnetic Resonance Imaging/methods , Feedback , Motion , HeadABSTRACT
PURPOSE: To develop a deep learning-based method, dubbed Denoising CEST Network (DECENT), to fully exploit the spatiotemporal correlation prior to CEST image denoising. METHODS: DECENT is composed of two parallel pathways with different convolution kernel sizes aiming to extract the global and spectral features embedded in CEST images. Each pathway consists of a modified U-Net with residual Encoder-Decoder network and 3D convolution. Fusion pathway with 1 × 1 × 1 convolution kernel is utilized to concatenate two parallel pathways, and the output of DECENT is noise-reduced CEST images. The performance of DECENT was validated in numerical simulations, egg white phantom experiments, and ischemic mouse brain and human skeletal muscle experiments in comparison with existing state-of-the-art denoising methods. RESULTS: Rician noise was added to CEST images to mimic a low SNR situation for numerical simulation, egg white phantom experiment, and mouse brain experiments, while human skeletal muscle experiments were of inherently low SNR. From the denoising results evaluated by peak SNR (PSNR) and structural similarity index (SSIM), the proposed deep learning-based denoising method (DECENT) can achieve better performance compared to existing CEST denoising methods such as NLmCED, MLSVD, and BM4D, avoiding complicated parameter tuning or time-consuming iterative processes. CONCLUSIONS: DECENT can well exploit the prior spatiotemporal correlation knowledge of CEST images and restore the noise-free images from their noisy observations, outperforming state-of-the-art denoising methods.
Subject(s)
Algorithms , Neural Networks, Computer , Mice , Animals , Humans , Signal-To-Noise Ratio , Computer Simulation , Phantoms, Imaging , Image Processing, Computer-Assisted/methodsABSTRACT
Objective. Bloch simulation constitutes an essential part of magnetic resonance imaging (MRI) development. However, even with the graphics processing unit (GPU) acceleration, the heavy computational load remains a major challenge, especially in large-scale, high-accuracy simulation scenarios. This work aims to develop a deep learning-based simulator to accelerate Bloch simulation.Approach. The simulator model, called Simu-Net, is based on an end-to-end convolutional neural network and is trained with synthetic data generated by traditional Bloch simulation. It uses dynamic convolution to fuse spatial and physical information with different dimensions and introduces position encoding templates to achieve position-specific labeling and overcome the receptive field limitation of the convolutional network.Main results. Compared with mainstream GPU-based MRI simulation software, Simu-Net successfully accelerates simulations by hundreds of times in both traditional and advanced MRI pulse sequences. The accuracy and robustness of the proposed framework were verified qualitatively and quantitatively. Besides, the trained Simu-Net was applied to generate sufficient customized training samples for deep learning-basedT2mapping and comparable results to conventional methods were obtained in the human brain.Significance. As a proof-of-concept work, Simu-Net shows the potential to apply deep learning for rapidly approximating the forward physical process of MRI and may increase the efficiency of Bloch simulation for optimization of MRI pulse sequences and deep learning-based methods.
Subject(s)
Deep Learning , Humans , Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , Computer Simulation , Neural Networks, ComputerABSTRACT
PURPOSE: To develop and evaluate a single-shot quantitative MRI technique called GRE-MOLED (gradient-echo multiple overlapping-echo detachment) for rapid T 2 * $$ {T}_2^{\ast } $$ mapping. METHODS: In GRE-MOLED, multiple echoes with different TEs are generated and captured in a single shot of the k-space through MOLED encoding and EPI readout. A deep neural network, trained by synthetic data, was employed for end-to-end parametric mapping from overlapping-echo signals. GRE-MOLED uses pure GRE acquisition with a single echo train to deliver T 2 * $$ {T}_2^{\ast } $$ maps less than 90 ms per slice. The self-registered B0 information modulated in image phase was utilized for distortion-corrected parametric mapping. The proposed method was evaluated in phantoms, healthy volunteers, and task-based FMRI experiments. RESULTS: The quantitative results of GRE-MOLED T 2 * $$ {T}_2^{\ast } $$ mapping demonstrated good agreement with those obtained from the multi-echo GRE method (Pearson's correlation coefficient = 0.991 and 0.973 for phantom and in vivo brains, respectively). High intrasubject repeatability (coefficient of variation <1.0%) were also achieved in scan-rescan test. Enabled by deep learning reconstruction, GRE-MOLED showed excellent robustness to geometric distortion, noise, and random subject motion. Compared to the conventional FMRI approach, GRE-MOLED also achieved a higher temporal SNR and BOLD sensitivity in task-based FMRI. CONCLUSION: GRE-MOLED is a new real-time technique for T 2 * $$ {T}_2^{\ast } $$ quantification with high efficiency and quality, and it has the potential to be a better quantitative BOLD detection method.
Subject(s)
Deep Learning , Humans , Magnetic Resonance Imaging/methods , Brain/diagnostic imaging , Neural Networks, Computer , Phantoms, Imaging , Echo-Planar Imaging/methodsABSTRACT
OBJECTIVES: To develop a real-time abdominal T2 mapping method without requiring breath-holding or respiratory-gating. METHODS: The single-shot multiple overlapping-echo detachment (MOLED) pulse sequence was employed to achieve free-breathing T2 mapping of the abdomen. Deep learning was used to untangle the non-linear relationship between the MOLED signal and T2 mapping. A synthetic data generation flow based on Bloch simulation, modality synthesis, and randomization was proposed to overcome the inadequacy of real-world training set. RESULTS: The results from simulation and in vivo experiments demonstrated that our method could deliver high-quality T2 mapping. The average NMSE and R2 values of linear regression in the digital phantom experiments were 0.0178 and 0.9751. Pearson's correlation coefficient between our predicted T2 and reference T2 in the phantom experiments was 0.9996. In the measurements for the patients, real-time capture of the T2 value changes of various abdominal organs before and after contrast agent injection was realized. A total of 33 focal liver lesions were detected in the group, and the mean and standard deviation of T2 values were 141.1 ± 50.0 ms for benign and 63.3 ± 16.0 ms for malignant lesions. The coefficients of variance in a test-retest experiment were 2.9%, 1.2%, 0.9%, 3.1%, and 1.8% for the liver, kidney, gallbladder, spleen, and skeletal muscle, respectively. CONCLUSIONS: Free-breathing abdominal T2 mapping is achieved in about 100 ms on a clinical MRI scanner. The work paved the way for the development of real-time dynamic T2 mapping in the abdomen. KEY POINTS: ⢠MOLED achieves free-breathing abdominal T2 mapping in about 100 ms, enabling real-time capture of T2 value changes due to CA injection in abdominal organs. ⢠Synthetic data generation flow mitigates the issue of lack of sizable abdominal training datasets.
Subject(s)
Deep Learning , Humans , Abdomen/diagnostic imaging , Respiration , Liver/pathology , Magnetic Resonance Imaging/methods , Phantoms, ImagingABSTRACT
BACKGROUND: Echo planar imaging (EPI) suffers from Nyquist ghost caused by eddy currents and other non-ideal factors. Deep learning has received interest for EPI ghost correction. However, large datasets with qualified labels are usually unavailable, especially for the under-sampled EPI data due to the imperfection of traditional ghost correction algorithms. PURPOSE: To develop a multi-coil synthetic-data-based deep learning method for the Nyquist ghost correction and reconstruction of under-sampled EPI. METHODS: Our network is trained purely with synthetic data. The labels of the training samples are generated by combining a public magnetic resonance imaging dataset and a few pre-collected coil sensitivity maps. The input is synthesized by under-sampling (for the accelerated case) and adding phase errors between the even and odd echoes of the label. To bridge the gap between synthetic data and data from real acquisition, linear and non-linear 2D phase errors are considered during the training data generation. RESULTS: The proposed method outperformed the existing mainstream approaches in several experiments. The average ghost-to-signal ratios of our/3-line navigator-based methods were 0.51%/5.36% and 0.42%/8.64% in fully-sampled and under-sampled in vivo experiments, respectively. In the sagittal experiments, our method successfully corrected higher-order and 2D phase errors. Our method also outperformed other reference-based methods on motion-corrupted data. In the simulation experiments, the peak signal-to-noise ratios were 37.6/38.3 dB for 2D linear/non-linear simulated phase errors, indicating that our method was consistently reliable for different kinds of phase errors. CONCLUSION: Our method achieves superb ghost correction and parallel imaging reconstruction without any calibration information, and can be readily adapted to other EPI-based applications.
Subject(s)
Echo-Planar Imaging , Image Processing, Computer-Assisted , Echo-Planar Imaging/methods , Image Processing, Computer-Assisted/methods , Brain , Artifacts , Phantoms, Imaging , AlgorithmsABSTRACT
PURPOSE: This work introduces and validates a deep-learning-based fitting method, which can rapidly provide accurate and robust estimation of cytological features of brain tumor based on the IMPULSED (imaging microstructural parameters using limited spectrally edited diffusion) model fitting with diffusion-weighted MRI data. METHODS: The U-Net was applied to rapidly quantify extracellular diffusion coefficient (Dex ), cell size (d), and intracellular volume fraction (vin ) of brain tumor. At the training stage, the image-based training data, synthesized by randomizing quantifiable microstructural parameters within specific ranges, was used to train U-Net. At the test stage, the pre-trained U-Net was applied to estimate the microstructural parameters from simulated data and the in vivo data acquired on patients at 3T. The U-Net was compared with conventional non-linear least-squares (NLLS) fitting in simulations in terms of estimation accuracy and precision. RESULTS: Our results confirm that the proposed method yields better fidelity in simulations and is more robust to noise than the NLLS fitting. For in vivo data, the U-Net yields obvious quality improvement in parameter maps, and the estimations of all parameters are in good agreement with the NLLS fitting. Moreover, our method is several orders of magnitude faster than the NLLS fitting (from about 5 min to <1 s). CONCLUSION: The image-based training scheme proposed herein helps to improve the quality of the estimated parameters. Our deep-learning-based fitting method can estimate the cell microstructural parameters fast and accurately.
Subject(s)
Brain Neoplasms , Diffusion Magnetic Resonance Imaging , Humans , Diffusion Magnetic Resonance Imaging/methods , Least-Squares Analysis , Brain Neoplasms/diagnostic imaging , Image Processing, Computer-AssistedABSTRACT
Diffusion-ordered nuclear magnetic resonance spectroscopy (DOSY) plays a vital role in mixture studies. However, its applications to complex mixture samples are generally limited by spectral congestion along the chemical shift domain caused by extensive J coupling networks and abundant compounds. Herein, we develop the in-phase multidimensional DOSY strategy for complex mixture analyses by simultaneously revealing molecular self-diffusion behaviors and multiplet structures with optimal spectral resolution. As a proof of concept, two pure shift-based three-dimensional (3D) DOSY protocols are proposed to record high-resolution 3D spectroscopic view with separated mixture components and their resolved multiplet coupling structures, thus suitable for analyzing complex mixtures that contain abundant compounds and complicated molecular structures, even under adverse magnetic field conditions. Therefore, this study shows a promising tool for component analyses and multiplet structure studies on practical mixture samples.
Subject(s)
Complex Mixtures , Magnetic Resonance Imaging , Magnetic Resonance Spectroscopy/methods , Diffusion , Molecular StructureABSTRACT
BACKGROUND AND OBJECTIVE: Compressed sensing (CS) has gained increased attention in magnetic resonance imaging (MRI), leveraging its efficacy to accelerate image acquisition. Incoherence measurement and non-linear reconstruction are the most crucial guarantees of accurate restoration. However, the loose link between measurement and reconstruction hinders the further improvement of reconstruction quality, i.e., the default sampling pattern is not adaptively tailored to the downstream reconstruction method. When single-contrast reconstruction (SCR) has been upgraded to its multi-contrast reconstruction (MCR) variant, the identical morphologic information as a priori source could be integrated into the reconstruction procedure. How to measure less and reconstruct effectively by using the shareable morphologic information of various contrast images is an attractive topic. METHODS: An adaptive sampling (AS) based end-to-end framework (ASSCR or ASMCR) is proposed to address this issue, which simultaneously optimizes sampling patterns and reconstruction from under-sampled data in SCR or MCR scenarios. Several deep probabilistic subsampling (DPS) modules are used in AS network to construct a sampling pattern generator. In SCR and MCR, a convolution block and a data consistency layer are iteratively applied in the reconstruction network. Specifically, the learned optimal sampling pattern output from the trained AS sub-net is used for under-sampling. Incoherence measurement for single-contrast images and the combination of sampling patterns for multi-contrast data are guided by the SCR/MCR sub-net. RESULTS: Experiments were conducted on two single-contrast and one multi-contrast public MRI datasets. Compared with several state-of-the-art reconstruction methods, SCR results show that a learned sampling pattern brings the quality of the reconstructed image closer to the fully-sampled reference. With the addition of different contrast images, under-sampled images with higher acceleration factors could be well recovered. CONCLUSION: The proposed method could improve the reconstruction quality of under-sampled images by using adaptive sampling patterns and learning-based reconstruction.
Subject(s)
Image Processing, Computer-Assisted , Magnetic Resonance Imaging , Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , AlgorithmsABSTRACT
Multi-parametric quantitative magnetic resonance imaging (mqMRI) allows the characterization of multiple tissue properties non-invasively and has shown great potential to enhance the sensitivity of MRI measurements. However, real-time mqMRI during dynamic physiological processes or general motions remains challenging. To overcome this bottleneck, we propose a novel mqMRI technique based on multiple overlapping-echo detachment (MOLED) imaging, termed MQMOLED, to enable mqMRI in a single shot. In the data acquisition of MQMOLED, multiple MR echo signals with different multi-parametric weightings and phase modulations are generated and acquired in the same k-space. The k-space data is Fourier transformed and fed into a well-trained neural network for the reconstruction of multi-parametric maps. We demonstrated the accuracy and repeatability of MQMOLED in simultaneous mapping apparent proton density (APD) and any two parameters among T2, T2*, and apparent diffusion coefficient (ADC) in 130-170 ms. The abundant information delivered by the multiple overlapping-echo signals in MQMOLED makes the technique potentially robust to system imperfections, such as inhomogeneity of static magnetic field or radiofrequency field. Benefitting from the single-shot feature, MQMOLED exhibits a strong motion tolerance to the continuous movements of subjects. For the first time, it captured the synchronous changes of ADC, T2, and T1-weighted APD in contrast-enhanced perfusion imaging on patients with brain tumors, providing additional information about vascular density to the hemodynamic parametric maps. We expect that MQMOLED would promote the development of mqMRI technology and greatly benefit the applications of mqMRI, including therapeutics and analysis of metabolic/functional processes.