Multi-pathway multi-echo acquisition and neural contrast translation to generate a variety of quantitative and qualitative image contrasts

Time-Saving 3D MR Imaging Protocols with Millimeter and Submillimeter Isotropic Spatial Resolution for Face and Neck Imaging as Implemented at a Single-Site Major Referral Center

MR imaging has become the routine technique for staging nasopharyngeal carcinoma, evaluating perineural tumor spread, and detecting cartilage invasion in laryngeal carcinoma. However, these protocols traditionally require in the range of 25 to 35 minutes of acquisition time. 3D sequences offer the potential advantage of time savings through the acquisition of 1-mm or submillimeter resolution isotropic data followed by multiplanar reformats that require no further imaging time. We have iteratively optimized vendor product 3D T1-weighted MR imaging sequences for morphologic face and neck imaging, reducing the average acquisition time of our 3T protocols by 9 minutes 57 seconds (40.9%) and of our 1.5T protocols by 9 minutes 5 seconds (37.0%), while simultaneously maintaining or improving spatial resolution. This clinical report describes our experience optimizing and implementing commercially available 3D T1-weighted MR imaging pulse sequence protocols for clinical face and neck MR imaging examinations using illustrative cases. We provide protocol details to allow others to replicate our implementations, and we report challenges we faced along with our solutions.

A Non-Contrast Multi-Parametric MRI Biomarker for Assessment of MR-Guided Focused Ultrasound Thermal Therapies

OBJECTIVE

We present the development of a non-contrast multi-parametric magnetic resonance (MPMR) imaging biomarker to assess treatment outcomes for magnetic resonance-guided focused ultrasound (MRgFUS) ablations of localized tumors. Images obtained immediately following MRgFUS ablation were inputs for voxel-wise supervised learning classifiers, trained using registered histology as a label for thermal necrosis.

METHODS

VX2 tumors in New Zealand white rabbits quadriceps were thermally ablated using an MRgFUS system under 3 T MRI guidance. Animals were re-imaged three days post-ablation and euthanized. Histological necrosis labels were created by 3D registration between MR images and digitized H&E segmentations of thermal necrosis to enable voxel-wise classification of necrosis. Supervised MPMR classifier inputs included maximum temperature rise, cumulative thermal dose (CTD), post-FUS differences in T2-weighted images, and apparent diffusion coefficient, or ADC, maps. A logistic regression, support vector machine, and random forest classifier were trained in red a leave-one-out strategy in test data from four subjects.

RESULTS

In the validation dataset, the MPMR classifiers achieved higher recall and Dice than a clinically adopted 240 cumulative equivalent minutes at 43 °C (CEM 43) threshold (0.43) in all subjects. The average Dice scores of overlap with the registered histological label for the logistic regression (0.63) and support vector machine (0.63) MPMR classifiers were within 6% of the acute contrast-enhanced non-perfused volume (0.67).

CONCLUSIONS

Voxel-wise registration of MPMR data to histological outcomes facilitated supervised learning of an accurate non-contrast MR biomarker for MRgFUS ablations in a rabbit VX2 tumor model.

Direct synthesis of multi-contrast brain MR images from MR multitasking spatial factors using deep learning

PURPOSE

To develop a deep learning method to synthesize conventional contrast-weighted images in the brain from MR multitasking spatial factors.

METHODS

Eighteen subjects were imaged using a whole-brain quantitative T1 -T2 -T1ρ MR multitasking sequence. Conventional contrast-weighted images consisting of T1 MPRAGE, T1 gradient echo, and T2 fluid-attenuated inversion recovery were acquired as target images. A 2D U-Net-based neural network was trained to synthesize conventional weighted images from MR multitasking spatial factors. Quantitative assessment and image quality rating by two radiologists were performed to evaluate the quality of deep-learning-based synthesis, in comparison with Bloch-equation-based synthesis from MR multitasking quantitative maps.

RESULTS

The deep-learning synthetic images showed comparable contrasts of brain tissues with the reference images from true acquisitions and were substantially better than the Bloch-equation-based synthesis results. Averaging on the three contrasts, the deep learning synthesis achieved normalized root mean square error = 0.184 ± 0.075, peak SNR = 28.14 ± 2.51, and structural-similarity index = 0.918 ± 0.034, which were significantly better than Bloch-equation-based synthesis (p < 0.05). Radiologists' rating results show that compared with true acquisitions, deep learning synthesis had no notable quality degradation and was better than Bloch-equation-based synthesis.

CONCLUSION

A deep learning technique was developed to synthesize conventional weighted images from MR multitasking spatial factors in the brain, enabling the simultaneous acquisition of multiparametric quantitative maps and clinical contrast-weighted images in a single scan.

Tailored magnetic resonance fingerprinting

Neuroimaging of certain pathologies requires both multi-parametric qualitative and quantitative imaging. The role of the quantitative MRI (qMRI) is well accepted but suffers from long acquisition times leading to patient discomfort, especially in geriatric and pediatric patients. Previous studies show that synthetic MRI can be used in order to reduce the scan time and provide qMRI as well as multi-contrast data. However, this approach suffers from artifacts such as partial volume and flow. In order to increase the scan efficiency (the number of contrasts and quantitative maps acquired per unit time), we designed, simulated, and demonstrated rapid, simultaneous, multi-contrast qualitative (T₁ weighted, T₁ fluid attenuated inversion recovery (FLAIR), T₂ weighted, water, and fat), and quantitative imaging (T₁ and T₂ maps) through the approach of tailored MR fingerprinting (TMRF) to cover whole-brain in approximately four minutes. We performed TMRF on in vivo four healthy human brains and in vitro ISMRM/NIST phantom and compared with vendor supplied gold standard (GS) and MRF sequences. All scans were performed on a 3 T GE Premier system and images were reconstructed offline using MATLAB. The reconstructed qualitative images were then subjected to custom DL denoising and gradient anisotropic diffusion denoising. The quantitative tissue parametric maps were reconstructed using a dense neural network to gain computational speed compared to dictionary matching. The grey matter and white matter tissues in qualitative and quantitative data for the in vivo datasets were segmented semi-automatically. The SNR and mean contrasts were plotted and compared across all three methods. The GS images show better SNR in all four subjects compared to MRF and TMRF (GS > TMRF>MRF). The T₁ and T₂ values of MRF are relatively overestimated as compared to GS and TMRF. The scan efficiency for TMRF is 1.72 min^-1 which is higher compared to GS (0.32 min^-1) and MRF (0.90 min^-1).

Deep-Learning-Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint

BACKGROUND

Magnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast-weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could significantly decrease the imaging time.

PURPOSE

To improve clinical utility of MRF by synthesizing contrast-weighted MR images from the quantitative data provided by MRF, using U-nets that were trained for the synthesis task utilizing L1- and perceptual loss functions, and their combinations.

STUDY TYPE

Retrospective.

POPULATION

Knee joint MRI data from 184 subjects from Northern Finland 1986 Birth Cohort (ages 33-35, gender distribution not available).

FIELD STRENGTH AND SEQUENCE

A 3 T, multislice-MRF, proton density (PD)-weighted 3D-SPACE (sampling perfection with application optimized contrasts using different flip angle evolution), fat-saturated T2-weighted 3D-space, water-excited double echo steady state (DESS).

ASSESSMENT

Data were divided into training, validation, test, and radiologist's assessment sets in the following way: 136 subjects to training, 3 for validation, 3 for testing, and 42 for radiologist's assessment. The synthetic and target images were evaluated using 5-point Likert scale by two musculoskeletal radiologists blinded and with quantitative error metrics.

STATISTICAL TESTS

Friedman's test accompanied with post hoc Wilcoxon signed-rank test and intraclass correlation coefficient. The statistical cutoff P <0.05 adjusted by Bonferroni correction as necessary was utilized.

RESULTS

The networks trained in the study could synthesize conventional images with high image quality (Likert scores 3-4 on a 5-point scale). Qualitatively, the best synthetic images were produced with combination of L1- and perceptual loss functions and perceptual loss alone, while L1-loss alone led to significantly poorer image quality (Likert scores below 3). The interreader and intrareader agreement were high (0.80 and 0.92, respectively) and significant. However, quantitative image quality metrics indicated best performance for the pure L1-loss.

DATA CONCLUSION

Synthesizing high-quality contrast-weighted images from MRF data using deep learning is feasible. However, more studies are needed to validate the diagnostic accuracy of these synthetic images.

EVIDENCE LEVEL

4.

TECHNICAL EFFICACY

Stage 1.

Structural and functional imaging of brains

Analyzing the complex structures and functions of brain is the key issue to understanding the physiological and pathological processes. Although neuronal morphology and local distribution of neurons/blood vessels in the brain have been known, the subcellular structures of cells remain challenging, especially in the live brain. In addition, the complicated brain functions involve numerous functional molecules, but the concentrations, distributions and interactions of these molecules in the brain are still poorly understood. In this review, frontier techniques available for multiscale structure imaging from organelles to the whole brain are first overviewed, including magnetic resonance imaging (MRI), computed tomography (CT), positron emission tomography (PET), serial-section electron microscopy (ssEM), light microscopy (LM) and synchrotron-based X-ray microscopy (XRM). Specially, XRM for three-dimensional (3D) imaging of large-scale brain tissue with high resolution and fast imaging speed is highlighted. Additionally, the development of elegant methods for acquisition of brain functions from electrical/chemical signals in the brain is outlined. In particular, the new electrophysiology technologies for neural recordings at the single-neuron level and in the brain are also summarized. We also focus on the construction of electrochemical probes based on dual-recognition strategy and surface/interface chemistry for determination of chemical species in the brain with high selectivity and long-term stability, as well as electrochemophysiological microarray for simultaneously recording of electrochemical and electrophysiological signals in the brain. Moreover, the recent development of brain MRI probes with high contrast-to-noise ratio (CNR) and sensitivity based on hyperpolarized techniques and multi-nuclear chemistry is introduced. Furthermore, multiple optical probes and instruments, especially the optophysiological Raman probes and fiber Raman photometry, for imaging and biosensing in live brain are emphasized. Finally, a brief perspective on existing challenges and further research development is provided.

Multiparametric mapping in the brain from conventional contrast-weighted images using deep learning

PURPOSE

To develop a deep-learning-based method to quantify multiple parameters in the brain from conventional contrast-weighted images.

METHODS

Eighteen subjects were imaged using an MR Multitasking sequence to generate reference T₁ and T₂ maps in the brain. Conventional contrast-weighted images consisting of T₁ MPRAGE, T₁ GRE, and T₂ FLAIR were acquired as input images. A U-Net-based neural network was trained to estimate T₁ and T₂ maps simultaneously from the contrast-weighted images. Six-fold cross-validation was performed to compare the network outputs with the MR Multitasking references.

RESULTS

The deep-learning T₁ /T₂ maps were comparable with the references, and brain tissue structures and image contrasts were well preserved. A peak signal-to-noise ratio >32 dB and a structural similarity index >0.97 were achieved for both parameter maps. Calculated on brain parenchyma (excluding CSF), the mean absolute errors (and mean percentage errors) for T₁ and T₂ maps were 52.7 ms (5.1%) and 5.4 ms (7.1%), respectively. ROI measurements on four tissue compartments (cortical gray matter, white matter, putamen, and thalamus) showed that T₁ and T₂ values provided by the network outputs were in agreement with the MR Multitasking reference maps. The mean differences were smaller than ± 1%, and limits of agreement were within ± 5% for T₁ and within ± 10% for T₂ after taking the mean differences into account.

CONCLUSION

A deep-learning-based technique was developed to estimate T₁ and T₂ maps from conventional contrast-weighted images in the brain, enabling simultaneous qualitative and quantitative MRI without modifying clinical protocols.

Simultaneous T1 -weighted and T2 -weighted 3D MRI using RF phase-modulated gradient echo imaging

PURPOSE

T₁ -weighted and T₂ -weighted (T1w and T2w) imaging are essential sequences in routine clinical practice to detect and characterize a wide variety of pathologies. Many approaches have been proposed to obtain T1w and T2w contrast, although many challenges still remain, including long acquisition time and limitations that favor 2D imaging. In this study, we propose a novel method for simultaneous T1w and T2w imaging using RF phase-modulated 3D gradient-echo imaging.

THEORY

Configuration theory is used to derive closed-form equations for the steady state of RF phase-modulated gradient-echo signal. These equations suggest the use of small RF phase increments to provide orthogonal signal contrast with T2w and T1w in the real and imaginary components, respectively. Background phase can be removed using a two-pass acquisition with opposite RF phase increments.

METHODS

Simulation and phantom experiments were performed to validate our proposed method. Volunteer images of the brain and knee were acquired to demonstrate the clinical feasibility. The proposed method was compared with T1w and T2w fast spin-echo imaging.

RESULTS

The relative signal intensity of images acquired using the proposed method agreed closely with simulations and fast spin-echo imaging in phantoms. Images from volunteer imaging showed very similar contrast compared to conventional fast spin-echo imaging.

CONCLUSION

Radiofrequency phase-modulated gradient-echo with small RF phase increments is an alternative method that provides simultaneous T1w and T2w contrast in short scan times with 3D volumetric coverage.

A deep learning approach for synthetic MRI based on two routine sequences and training with synthetic data

BACKGROUND AND OBJECTIVE

Synthetic magnetic resonance imaging (MRI) is a low cost procedure that serves as a bridge between qualitative and quantitative MRI. However, the proposed methods require very specific sequences or private protocols which have scarcely found integration in clinical scanners. We propose a learning-based approach to compute T1, T2, and PD parametric maps from only a pair of T1- and T2-weighted images customarily acquired in the clinical routine.

METHODS

Our approach is based on a convolutional neural network (CNN) trained with synthetic data; specifically, a synthetic dataset with 120 volumes was constructed from the anatomical brain model of the BrainWeb tool and served as the training set. The CNN learns an end-to-end mapping function to transform the input T1- and T2-weighted images to their underlying T1, T2, and PD parametric maps. Then, conventional weighted images unseen by the network are analytically synthesized from the parametric maps. The network can be fine tuned with a small database of actual weighted images and maps for better performance.

RESULTS

This approach is able to accurately compute parametric maps from synthetic brain data achieving normalized squared error values predominantly below 1%. It also yields realistic parametric maps from actual MR brain acquisitions with T1, T2, and PD values in the range of the literature and with correlation values above 0.95 compared to the T1 and T2 maps obtained from relaxometry sequences. Further, the synthesized weighted images are visually realistic; the mean square error values are always below 9% and the structural similarity index is usually above 0.90. Network fine tuning with actual maps improves performance, while training exclusively with a small database of actual maps shows a performance degradation.

CONCLUSIONS

These results show that our approach is able to provide realistic parametric maps and weighted images out of a CNN that (a) is trained with a synthetic dataset and (b) needs only two inputs, which are in turn obtained from a common full-brain acquisition that takes less than 8 min of scan time. Although a fine tuning with actual maps improves performance, synthetic data is crucial to reach acceptable performance levels. Hence, we show the utility of our approach for both quantitative MRI in clinical viable times and for the synthesis of additional weighted images to those actually acquired.

Multiple-echo steady-state (MESS): Extending DESS for joint T2 mapping and chemical-shift corrected water-fat separation

Purpose

To extend the double echo steady‐state (DESS) sequence to enable chemical‐shift corrected water‐fat separation.

Methods

This study proposes multiple‐echo steady‐state (MESS), a sequence that modifies the readouts of the DESS sequence to acquire two echoes each with bipolar readout gradients with higher readout bandwidth. This enables water‐fat separation and eliminates the need for water‐selective excitation that is often used in combination with DESS, without increasing scan time. An iterative fitting approach was used to perform joint chemical‐shift corrected water‐fat separation and T₂ estimation on all four MESS echoes simultaneously. MESS and water‐selective DESS images were acquired for five volunteers, and were compared qualitatively as well as quantitatively on cartilage T₂ and thickness measurements. Signal‐to‐noise ratio (SNR) and T₂ quantification were evaluated numerically using pseudo‐replications of the acquisition.

Results

The water‐fat separation provided by MESS was robust and with quality comparable to water‐selective DESS. MESS T₂ estimation was similar to DESS, albeit with slightly higher variability. Noise analysis showed that SNR in MESS was comparable to DESS on average, but did exhibit local variations caused by uncertainty in the water‐fat separation.

Conclusion

In the same acquisition time as DESS, MESS provides water‐fat separation with comparable SNR in the reconstructed water and fat images. By providing additional image contrasts in addition to the water‐selective DESS images, MESS provides a promising alternative to DESS.

Alternating unbalanced SSFP for 3D R 2 ' mapping of the human brain

PURPOSE

Measuring the transverse-relaxation rate R 2 ' provides valuable information in quantitative evaluation of tissue microstructure, for example, in terms of oxygenation levels. Here, we propose an alternating unbalanced SSFP pulse sequence for rapid whole-brain 3D R 2 ' mapping.

METHODS

Unlike currently practiced, spin echo-based R 2 ' measurement techniques, the proposed method alternates between SSFP-FID and SSFP-ECHO modes for rapid 3D encoding of transverse relaxation rates expressed as R₂ + R 2 ' and R₂ - R 2 ' . Z-shimming gradients embedded into multi-echo trains of each SSFP module are designed to achieve relative immunity to large-scale magnetic-field variations (ΔB₀ ). Appropriate models for the temporal evolution of the two groups of SSFP signals were constructed with ΔB₀ -induced modulations accounted for, leading to ΔB₀ -corrected estimation of R₂ , R 2 ' , and R 2 ∗ (= R₂ + R 2 ' ). Additionally, relative magnetic susceptibility (Δχ) maps were obtained by quantitative susceptibility mapping of the phase data. Numerical simulations were performed to optimize scan parameters, followed by in vivo studies at 3 T in 7 healthy subjects. Measured parameters were evaluated in six brain regions, and subjected to interparameter correlation analysis.

RESULTS

The resultant maps of R 2 ' and additionally derived R₂ , R 2 ∗ , and Δχ all demonstrated the expected contrast across brain territories (eg, deep brain structures versus cortex), with the measured values in good agreement with previous reports. Furthermore, regression analyses yielded strong linear relationships for the transverse relaxation parameters ( R 2 ' , R₂ , and R 2 ∗ ) against Δχ.

CONCLUSION

Results suggest feasibility of the proposed method as a practical and reliable means for measuring R 2 ' , R₂ , R 2 ∗ , and Δχ across the entire brain.

Synthetic MRI: Technologies and Applications in Neuroradiology

Synthetic MRI is a technique that synthesizes contrast-weighted images from multicontrast MRI data. There have been advances in synthetic MRI since the technique was introduced. Although a number of synthetic MRI methods have been developed for quantifying one or more relaxometric parameters and for generating multiple contrast-weighted images, this review focuses on several methods that quantify all three relaxometric parameters (T₁ , T₂ , and proton density) and produce multiple contrast-weighted images. Acquisition, quantification, and image synthesis techniques are discussed for each method. We discuss the image quality and diagnostic accuracy of synthetic MRI methods and their clinical applications in neuroradiology. Based on this analysis, we highlight areas that need to be addressed for synthetic MRI to be widely implemented in the clinic. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 1.

Deriving new soft tissue contrasts from conventional MR images using deep learning

Versatile soft tissue contrast in magnetic resonance imaging is a unique advantage of the imaging modality. However, the versatility is not fully exploited. In this study, we propose a deep learning-based strategy to derive more soft tissue contrasts from conventional MR images obtained in standard clinical MRI. Two types of experiments are performed. First, MR images corresponding to different pulse sequences are predicted from one or more images already acquired. As an example, we predict T_1ρ weighted knee image from T₂ weighted image and/or T₁ weighted image. Furthermore, we estimate images corresponding to alternative imaging parameter values. In a representative case, variable flip angle images are predicted from a single T₁ weighted image, whose accuracy is further validated in quantitative T₁ map subsequently derived. To accomplish these tasks, images are retrospectively collected from 56 subjects, and self-attention convolutional neural network models are trained using 1104 knee images from 46 subjects and tested using 240 images from 10 other subjects. High accuracy has been achieved in resultant qualitative images as well as quantitative T₁ maps. The proposed deep learning method can be broadly applied to obtain more versatile soft tissue contrasts without additional scans or used to normalize MR data that were inconsistently acquired for quantitative analysis.