VPatho: a deep learning-based two-stage approach for accurate prediction of gain-of-function and loss-of-function variants.

Determining the pathogenicity and functional impact (i.e. gain-of-function; GOF or loss-of-function; LOF) of a variant is vital for unraveling the genetic level mechanisms of human diseases. To provide a 'one-stop' framework for the accurate identification of pathogenicity and functional impact of variants, we developed a two-stage deep-learning-based computational solution, termed VPatho, which was trained using a total of 9619 pathogenic GOF/LOF and 138 026 neutral variants curated from various databases. A total number of 138 variant-level, 262 protein-level and 103 genome-level features were extracted for constructing the models of VPatho. The development of VPatho consists of two stages: (i) a random under-sampling multi-scale residual neural network (ResNet) with a newly defined weighted-loss function (RUS-Wg-MSResNet) was proposed to predict variants' pathogenicity on the gnomAD_NV + GOF/LOF dataset; and (ii) an XGBOD model was constructed to predict the functional impact of the given variants. Benchmarking experiments demonstrated that RUS-Wg-MSResNet achieved the highest prediction performance with the weights calculated based on the ratios of neutral versus pathogenic variants. Independent tests showed that both RUS-Wg-MSResNet and XGBOD achieved outstanding performance. Moreover, assessed using variants from the CAGI6 competition, RUS-Wg-MSResNet achieved superior performance compared to state-of-the-art predictors. The fine-trained XGBOD models were further used to blind test the whole LOF data downloaded from gnomAD and accordingly, we identified 31 nonLOF variants that were previously labeled as LOF/uncertain variants. As an implementation of the developed approach, a webserver of VPatho is made publicly available at http://csbio.njust.edu.cn/bioinf/vpatho/ to facilitate community-wide efforts for profiling and prioritizing the query variants with respect to their pathogenicity and functional impact.

Feasibility of undersampled spiral trajectories in MREPT for fast conductivity imaging.

PURPOSE: To investigate spiral-based imaging including trajectories with undersampling as a fast and robust alternative for phase-based magnetic resonance electrical properties tomography (MREPT) techniques. METHODS: Spiral trajectories with various undersampling ratios were prescribed to acquire images from an experimental phantom and a healthy volunteer at 3T. The non-Cartesian acquisitions were reconstructed using SPIRiT, and conductivity maps were derived using phase-based cr-MREPT. The resulting maps were compared between different sampling trajectories. Additionally, a conductivity map was obtained using a Cartesian balanced SSFP acquisition from the volunteer to comparatively demonstrate the robustness of the proposed method. RESULTS: The phantom and volunteer results illustrate the benefits of the spiral acquisitions. Specifically, undersampled spiral acquisitions display improved robustness against field inhomogeneity artifacts and lowered SD values with shortened readout times. Furthermore, average of conductivity values measured for the cerebrospinal fluid with the spiral acquisitions were 1.703 S/m, indicating a close agreement with the theoretical values of 1.794 S/m. CONCLUSION: A spiral-based acquisition framework for conductivity imaging with and without undersampling is presented. Overall, spiral-based acquisitions improved robustness against field inhomogeneity artifacts, while achieving whole head coverage with multiple averages in less than a minute.

Efficient pulse sequence design framework for high-dimensional MR fingerprinting scans using systematic error index.

PURPOSE: For effective optimization of MR fingerprinting (MRF) pulse sequences, estimating and minimizing errors from actual scan conditions are crucial. Although virtual-scan simulations offer an approximation to these errors, their computational demands become expensive for high-dimensional MRF frameworks, where interactions between more than two tissue properties are considered. This complexity makes sequence optimization impractical. We introduce a new mathematical model, the systematic error index (SEI), to address the scalability challenges for high-dimensional MRF sequence design. METHODS: By eliminating the need to perform dictionary matching, the SEI model approximates quantification errors with low computational costs. The SEI model was validated in comparison with virtual-scan simulations. The SEI model was further applied to optimize three high-dimensional MRF sequences that quantify two to four tissue properties. The optimized scans were examined in simulations and healthy subjects. RESULTS: The proposed SEI model closely approximated the virtual-scan simulation outcomes while achieving hundred- to thousand-times acceleration in the computational speed. In both simulation and in vivo experiments, the optimized MRF sequences yield higher measurement accuracy with fewer undersampling artifacts at shorter scan times than the heuristically designed sequences. CONCLUSION: We developed an efficient method for estimating real-world errors in MRF scans with high computational efficiency. Our results illustrate that the SEI model could approximate errors both qualitatively and quantitatively. We also proved the practicality of the SEI model of optimizing sequences for high-dimensional MRF frameworks with manageable computational power. The optimized high-dimensional MRF scans exhibited enhanced robustness against undersampling and system imperfections with faster scan times.

Fast 3D fMRI acquisition with high spatial resolutions over a reduced FOV.

PURPOSE: To develop and demonstrate a fast 3D fMRI acquisition technique with high spatial resolution over a reduced FOV, named k-t 3D reduced FOV imaging (3D-rFOVI). METHODS: Based on 3D gradient-echo EPI, k-t 3D-rFOVI used a 2D RF pulse to reduce the FOV in the in-plane phase-encoding direction, boosting spatial resolution without increasing echo train length. For image acceleration, full sampling was applied in the central k-space region along the through-slab direction (kz) for all time frames, while randomized undersampling was used in outer kz regions at different time frames. Images were acquired at 3T and reconstructed using a method based on partial separability. fMRI detection sensitivity of k-t 3D-rFOVI was quantitively analyzed with simulation data. Human visual fMRI experiments were performed to evaluate k-t 3D-rFOVI and compare it with a commercial multiband EPI sequence. RESULTS: The simulation data showed that k-t 3D-rFOVI can detect 100% of fMRI activations with an acceleration factor (R) of 2 and ˜80% with R = 6. In the human fMRI data acquired with 1.5-mm spatial resolution and 800-ms volume TR (TRvol), k-t 3D-rFOVI with R = 4 detected 46% more activated voxels in the visual cortex than the multiband EPI. Additional fMRI experiments showed that k-t 3D-rFOVI can achieve TRvol of 480 ms with R = 6, while reliably detecting visual activation. CONCLUSIONS: k-t 3D-rFOVI can simultaneously achieve a high spatial resolution (1.5-mm isotropically) and short TRvol (480-ms) at 3T. It offers a robust acquisition technique for fast fMRI studies over a focused brain volume.

Accelerated model-based T1, T2* and proton density mapping using a Bayesian approach with automatic hyperparameter estimation.

PURPOSE: To achieve automatic hyperparameter estimation for the model-based recovery of quantitative MR maps from undersampled data, we propose a Bayesian formulation that incorporates the signal model and sparse priors among multiple image contrasts. THEORY: We introduce a novel approximate message passing framework "AMP-PE" that enables the automatic and simultaneous recovery of hyperparameters and quantitative maps. METHODS: We employed the variable-flip-angle method to acquire multi-echo measurements using gradient echo sequence. We explored undersampling schemes to incorporate complementary sampling patterns across different flip angles and echo times. We further compared AMP-PE with conventional compressed sensing approaches such as the l 1 $$ {l}_1 $$ -norm minimization, PICS and other model-based approaches such as GraSP, MOBA. RESULTS: Compared to conventional compressed sensing approaches such as the l 1 $$ {l}_1 $$ -norm minimization and PICS, AMP-PE achieved superior reconstruction performance with lower errors in T 2 ∗ $$ {\mathrm{T}}_2^{\ast } $$ mapping and comparable performance in T 1 $$ {\mathrm{T}}_1 $$ and proton density mappings. When compared to other model-based approaches including GraSP and MOBA, AMP-PE exhibited greater robustness and outperformed GraSP in reconstruction error. AMP-PE offers faster speed than MOBA. AMP-PE performed better than MOBA at higher sampling rates and worse than MOBA at a lower sampling rate. Notably, AMP-PE eliminates the need for hyperparameter tuning, which is a requisite for all the other approaches. CONCLUSION: AMP-PE offers the benefits of model-based recovery with the additional key advantage of automatic hyperparameter estimation. It works adeptly in situations where ground-truth is difficult to obtain and in clinical environments where it is desirable to automatically adapt hyperparameters to individual protocol, scanner and patient.

A novel fusion technology utilizing complex network and sequence information for FAD-binding site identification.

Flavin adenine dinucleotide (FAD) binding sites play an increasingly important role as useful targets for inhibiting bacterial infections. To reveal protein topological structural information as a reasonable complement for the identification FAD-binding sites, we designed a novel fusion technology according to sequence and complex network. The specially designed feature vectors were combined and fed into CatBoost for model construction. Moreover, due to the minority class (positive samples) is more significant for biological researches, a random under-sampling technique was applied to solve the imbalance. Compared with the previous methods, our methods achieved the best results for two independent test datasets. Especially, the MCC obtained by FADsite and FADsite_seq were 14.37 %-53.37 % and 21.81 %-60.81 % higher than the results of existing methods on Test6; and they showed improvements ranging from 6.03 % to 21.96 % and 19.77 %-35.70 % on Test4. Meanwhile, statistical tests show that our methods significantly differ from the state-of-the-art methods and the cross-entropy loss shows that our methods have high certainty. The excellent results demonstrated the effectiveness of using sequence and complex network information in identifying FAD-binding sites. It may be complementary to other biological studies. The data and resource codes are available at https://github.com/Kangxiaoneuq/FADsite.

Understanding random resampling techniques for class imbalance correction and their consequences on calibration and discrimination of clinical risk prediction models.

OBJECTIVE: Class imbalance is sometimes considered a problem when developing clinical prediction models and assessing their performance. To address it, correction strategies involving manipulations of the training dataset, such as random undersampling or oversampling, are frequently used. The aim of this article is to illustrate the consequences of these class imbalance correction strategies on clinical prediction models' internal validity in terms of calibration and discrimination performances. METHODS: We used both heuristic intuition and formal mathematical reasoning to characterize the relations between conditional probabilities of interest and probabilities targeted when using random undersampling or oversampling. We propose a plug-in estimator that represents a natural correction for predictions obtained from models that have been trained on artificially balanced datasets ("naïve" models). We conducted a Monte Carlo simulation with two different data generation processes and present a real-world example using data from the International Stroke Trial database to empirically demonstrate the consequences of applying random resampling techniques for class imbalance correction on calibration and discrimination (in terms of Area Under the ROC, AUC) for logistic regression and tree-based prediction models. RESULTS: Across our simulations and in the real-world example, calibration of the naïve models was very poor. The models using the plug-in estimator generally outperformed the models relying on class imbalance correction in terms of calibration while achieving the same discrimination performance. CONCLUSION: Random resampling techniques for class imbalance correction do not generally improve discrimination performance (i.e., AUC), and their use is hard to justify when aiming at providing calibrated predictions. Improper use of such class imbalance correction techniques can lead to suboptimal data usage and less valid risk prediction models.

Prediction of hypertension risk based on multiple feature fusion.

OBJECTIVE: In the application of machine learning to the prediction of hypertension, many factors have seriously affected the classification accuracy and generalization performance. We propose a pulse wave classification model based on multi-feature fusion for accuracy prediction of hypertension. METHODS AND MATERIALS: We propose an ensemble under-sampling model with dynamic weights to decrease the influence of class imbalance on classification, further to automatically classify of hypertension on inquiry diagnosis. We also build a deep learning model based on hybrid attention mechanism, which transforms pulse waves to feature maps for extraction of in-depth features, so as to automatically classify hypertension on pulse diagnosis. We build the multi-feature fusion model based on dynamic Dempster/Shafer (DS) theory combining inquiry diagnosis and pulse diagnosis to enhance fault tolerance of prediction for multiple classifiers. In addition, this study calculates feature importance ranking of scale features on inquiry diagnosis and temporal and frequency-domain features on pulse diagnosis. RESULTS: The accuracy, sensitivity, specificity, F1-score and G-mean after 5-fold cross-validation were 94.08%, 93.43%, 96.86%, 93.45% and 95.12%, respectively, based on the hypertensive samples of 409 cases from Longhua Hospital affiliated to Shanghai University of Traditional Chinese Medicine and Hospital of Integrated Traditional Chinese and Western Medicine. We find the key factors influencing hypertensive classification accuracy, so as to assist in the prevention and clinical diagnosis of hypertension. CONCLUSION: Compared with the state-of-the-art models, the multi-feature fusion model effectively utilizes the patients' correlated multimodal features, and has higher classification accuracy and generalization performance.

usDSM: a novel method for deleterious synonymous mutation prediction using undersampling scheme.

Although synonymous mutations do not alter the encoded amino acids, they may impact protein function by interfering with the regulation of RNA splicing or altering transcript splicing. New progress on next-generation sequencing technologies has put the exploration of synonymous mutations at the forefront of precision medicine. Several approaches have been proposed for predicting the deleterious synonymous mutations specifically, but their performance is limited by imbalance of the positive and negative samples. In this study, we firstly expanded the number of samples greatly from various data sources and compared six undersampling strategies to solve the problem of the imbalanced datasets. The results suggested that cluster centroid is the most effective scheme. Secondly, we presented a computational model, undersampling scheme based method for deleterious synonymous mutation (usDSM) prediction, using 14-dimensional biology features and random forest classifier to detect the deleterious synonymous mutation. The results on the test datasets indicated that the proposed usDSM model can attain superior performance in comparison with other state-of-the-art machine learning methods. Lastly, we found that the deep learning model did not play a substantial role in deleterious synonymous mutation prediction through a lot of experiments, although it achieves superior results in other fields. In conclusion, we hope our work will contribute to the future development of computational methods for a more accurate prediction of the deleterious effect of human synonymous mutation. The web server of usDSM is freely accessible at http://usdsm.xialab.info/.

Model-constrained reconstruction accelerated with Fourier-based undersampling for hyperpolarized [1-13 C] pyruvate imaging.

PURPOSE: Model-constrained reconstruction with Fourier-based undersampling (MoReFUn) is introduced to accelerate the acquisition of dynamic MRI using hyperpolarized [1-13 C]-pyruvate. METHODS: The MoReFUn method resolves spatial aliasing using constraints introduced by a pharmacokinetic model that describes the signal evolution of both pyruvate and lactate. Acceleration was evaluated on three single-channel data sets: a numerical digital phantom that is used to validate the accuracy of reconstruction and model parameter restoration under various SNR and undersampling ratios, prospectively and retrospectively sampled data of an in vitro dynamic multispectral phantom, and retrospectively undersampled imaging data from a prostate cancer patient to test the fidelity of reconstructed metabolite time series. RESULTS: All three data sets showed successful reconstruction using MoReFUn. In simulation and retrospective phantom data, the restored time series of pyruvate and lactate maintained the image details, and the mean square residual error of the accelerated reconstruction increased only slightly (< 10%) at a reduction factor up to 8. In prostate data, the quantitative estimation of the conversion-rate constant of pyruvate to lactate was achieved with high accuracy of less than 10% error at a reduction factor of 2 compared with the conversion rate derived from unaccelerated data. CONCLUSION: The MoReFUn technique can be used as an effective and reliable imaging acceleration method for metabolic imaging using hyperpolarized [1-13 C]-pyruvate.

Mitigating undersampling errors in MR fingerprinting by sequence optimization.

PURPOSE: To develop a method for MR Fingerprinting (MRF) sequence optimization that takes both the applied undersampling pattern and a realistic reference map into account. METHODS: A predictive model for the undersampling error leveraging on perturbation theory was exploited to optimize the MRF flip angle sequence for improved robustness against undersampling artifacts. In this framework parameter maps from a previously acquired MRF scan were used as reference. Sequences were optimized for different sequence lengths, smoothness constraints and undersampling factors. Numerical simulations and in vivo measurements in eight healthy subjects were performed to assess the effect of the performed optimization. The optimized MRF sequences were compared to a conventionally shaped flip angle pattern and an optimized pattern based on the Cramér-Rao lower bound (CRB). RESULTS: Numerical simulations and in vivo results demonstrate that the undersampling errors can be suppressed by flip angle optimization. Analysis of the in vivo results show that a sequence optimized for improved robustness against undersampling with a flip angle train of length 400 yielded significantly lower median absolute errors in T 1 : 5 . 6 % ± 2 . 9 % and T 2 : 7 . 9 % ± 2 . 3 % compared to the conventional ( T 1 : 8 . 0 % ± 1 . 9 % , T 2 : 14 . 5 % ± 2 . 6 % ) and CRB-based ( T 1 : 21 . 6 % ± 4 . 1 % , T 2 : 31 . 4 % ± 4 . 4 % ) sequences. CONCLUSION: The proposed method is able to optimize the MRF flip angle pattern such that significant mitigation of the artifacts from strong k-space undersampling in MRF is achieved.

SuperMAP: Deep ultrafast MR relaxometry with joint spatiotemporal undersampling.

PURPOSE: To develop an ultrafast and robust MR parameter mapping network using deep learning. THEORY AND METHODS: We design a deep learning framework called SuperMAP that directly converts a series of undersampled (both in k-space and parameter-space) parameter-weighted images into several quantitative maps, bypassing the conventional exponential fitting procedure. We also present a novel technique to simultaneously reconstruct T1rho and T2 relaxation maps within a single scan. Full data were acquired and retrospectively undersampled for training and testing using traditional and state-of-the-art techniques for comparison. Prospective data were also collected to evaluate the trained network. The performance of all methods is evaluated using the parameter qualification errors and other metrics in the segmented regions of interest. RESULTS: SuperMAP achieved accurate T1rho and T2 mapping with high acceleration factors (R = 24 and R = 32). It exploited both spatial and temporal information and yielded low error (normalized mean square error of 2.7% at R = 24 and 2.8% at R = 32) and high resemblance (structural similarity of 97% at R = 24 and 96% at R = 32) to the gold standard. The network trained with retrospectively undersampled data also works well for the prospective data (with a slightly lower acceleration factor). SuperMAP is also superior to conventional methods. CONCLUSION: Our results demonstrate the feasibility of generating superfast MR parameter maps through very few undersampled parameter-weighted images. SuperMAP can simultaneously generate T1rho and T2 relaxation maps in a short scan time.

Global attention-enabled texture enhancement network for MR image reconstruction.

PURPOSE: Although recent convolutional neural network (CNN) methodologies have shown promising results in fast MR imaging, there is still a desire to explore how they can be used to learn the frequency characteristics of multicontrast images and reconstruct texture details. METHODS: A global attention-enabled texture enhancement network (GATE-Net) with a frequency-dependent feature extraction module (FDFEM) and convolution-based global attention module (GAM) is proposed to address the highly under-sampling MR image reconstruction problem. First, FDFEM enables GATE-Net to effectively extract high-frequency features from shareable information of multicontrast images to improve the texture details of reconstructed images. Second, GAM with less computation complexity has the receptive field of the entire image, which can fully explore useful shareable information of multi-contrast images and suppress less beneficial shareable information. RESULTS: The ablation studies are conducted to evaluate the effectiveness of the proposed FDFEM and GAM. Experimental results under various acceleration rates and datasets consistently demonstrate the superiority of GATE-Net, in terms of peak signal-to-noise ratio, structural similarity and normalized mean square error. CONCLUSION: A global attention-enabled texture enhancement network is proposed. it can be applied to multicontrast MR image reconstruction tasks with different acceleration rates and datasets and achieves superior performance in comparison with state-of-the-art methods.

Mitigating Under-Sampling Artifacts in 3D Photoacoustic Imaging Using Res-UNet Based on Digital Breast Phantom.

In recent years, photoacoustic (PA) imaging has rapidly grown as a non-invasive screening technique for breast cancer detection using three-dimensional (3D) hemispherical arrays due to their large field of view. However, the development of breast imaging systems is hindered by a lack of patients and ground truth samples, as well as under-sampling problems caused by high costs. Most research related to solving these problems in the PA field were based on 2D transducer arrays or simple regular shape phantoms for 3D transducer arrays or images from other modalities. Therefore, we demonstrate an effective method for removing under-sampling artifacts based on deep neural network (DNN) to reconstruct high-quality PA images using numerical digital breast simulations. We constructed 3D digital breast phantoms based on human anatomical structures and physical properties, which were then subjected to 3D Monte-Carlo and K-wave acoustic simulations to mimic acoustic propagation for hemispherical transducer arrays. Finally, we applied a 3D delay-and-sum reconstruction algorithm and a Res-UNet network to achieve higher resolution on sparsely-sampled data. Our results indicate that when using a 757 nm laser with uniform intensity distribution illuminated on a numerical digital breast, the imaging depth can reach 3 cm with 0.25 mm spatial resolution. In addition, the proposed DNN can significantly enhance image quality by up to 78.4%, as measured by MS-SSIM, and reduce background artifacts by up to 19.0%, as measured by PSNR, even at an under-sampling ratio of 10%. The post-processing time for these improvements is only 0.6 s. This paper suggests a new 3D real time DNN method addressing the sparse sampling problem based on numerical digital breast simulations, this approach can also be applied to clinical data and accelerate the development of 3D photoacoustic hemispherical transducer arrays for early breast cancer diagnosis.

An Efficient CRT Based Algorithm for Frequency Determination from Undersampled Real Waveform.

The Chinese Remainder Theorem (CRT) based frequency estimation has been widely studied during the past two decades. It enables one to estimate frequencies by sub-Nyquist sampling rates, which reduces the cost of hardware in a sensor network. Several studies have been done on the complex waveform; however, few works studied its applications in the real waveform case. Different from the complex waveform, existing CRT methods cannot be straightforwardly applied to handle a real waveform's spectrum due to the spurious peaks. To tackle the ambiguity problem, in this paper, we propose the first polynomial-time closed-form Robust CRT (RCRT) for the single-tone real waveform, which can be considered as a special case of RCRT for arbitrary two numbers. The time complexity of the proposed algorithm is O(L), where L is the number of samplers. Furthermore, our algorithm also matches the optimal error-tolerance bound.

Gradient-echo-train-based sub-millisecond periodic event encoded dynamic imaging with random (k, t)-space undersampling: k-t get-SPEEDI.

PURPOSE: The gradient-echo-train-based Sub-millisecond Periodic Event Encoded Dynamic Imaging (get-SPEEDI) technique provides ultrahigh temporal resolutions (∼0.6 ms) for detecting rapid physiological activities, but its practical adoption can be hampered by long scan times. This study aimed at developing a more efficient variant of get-SPEEDI for reducing the scan time without degrading temporal resolution or image quality. METHODS: The proposed pulse sequence, named k-t get-SPEEDI, accelerated get-SPEEDI acquisition by undersampling the k-space phase-encoding lines semi-randomly. At each time frame, k-space was fully sampled in the central region whereas randomly undersampled in the outer regions. A time-series of images was reconstructed using an algorithm based on the joint partial separability and sparsity constraints. To demonstrate the performance of k-t get-SPEEDI, images of human aortic valve opening and closing were acquired with 0.6-ms temporal resolution and compared with those from conventional get-SPEEDI. RESULTS: k-t get-SPEEDI achieved a 2-fold scan time reduction over the conventional get-SPEEDI (from ∼6 to ∼3 min), while achieving comparable SNRs and contrast-to-noise ratio (CNRs) for visualizing the dynamic process of aortic valve: SNR/CNR ≈$$ \approx $$ 70/38 vs. 73/39 in the k-t and conventional get-SPEEDI scans, respectively. The time courses of aortic valve area also matched well between these two sequences with a correlation coefficient of 0.86. CONCLUSIONS: The k-t get-SPEEDI pulse sequence was able to half the scan time without compromising the image quality and ultrahigh temporal resolution. Additional scan time reduction may also be possible, facilitating in vivo adoptions of SPEEDI techniques.

A data-driven semantic segmentation model for direct cardiac functional analysis based on undersampled radial MR cine series.

PURPOSE: Image acquisition and subsequent manual analysis of cardiac cine MRI is time-consuming. The purpose of this study was to train and evaluate a 3D artificial neural network for semantic segmentation of radially undersampled cardiac MRI to accelerate both scan time and postprocessing. METHODS: A database of Cartesian short-axis MR images of the heart (148,500 images, 484 examinations) was assembled from an openly accessible database and radial undersampling was simulated. A 3D U-Net architecture was pretrained for segmentation of undersampled spatiotemporal cine MRI. Transfer learning was then performed using samples from a second database, comprising 108 non-Cartesian radial cine series of the midventricular myocardium to optimize the performance for authentic data. The performance was evaluated for different levels of undersampling by the Dice similarity coefficient (DSC) with respect to reference labels, as well as by deriving ventricular volumes and myocardial masses. RESULTS: Without transfer learning, the pretrained model performed moderately on true radial data [maximum number of projections tested, P = 196; DSC = 0.87 (left ventricle), DSC = 0.76 (myocardium), and DSC =0.64 (right ventricle)]. After transfer learning with authentic data, the predictions achieved human level even for high undersampling rates (P = 33, DSC = 0.95, 0.87, and 0.93) without significant difference compared with segmentations derived from fully sampled data. CONCLUSION: A 3D U-Net architecture can be used for semantic segmentation of radially undersampled cine acquisitions, achieving a performance comparable with human experts in fully sampled data. This approach can jointly accelerate time-consuming cine image acquisition and cumbersome manual image analysis.

Optimization of undersampling parameters for 3D intracranial compressed sensing MR angiography at 7 T.

PURPOSE: 3D time-of-flight MRA can accurately visualize the intracranial vasculature but is limited by long acquisition times. Compressed sensing reconstruction can be used to substantially accelerate acquisitions. The quality of those reconstructions depends on the undersampling patterns used. In this work, we optimize sets of undersampling parameters for various acceleration factors of Cartesian 3D time-of-flight MRA. METHODS: Fully sampled datasets, acquired at 7 Tesla, were retrospectively undersampled using variable-density Poisson disk sampling with various autocalibration region sizes, polynomial orders, and acceleration factors. The accuracy of reconstructions from the different undersampled datasets was assessed using the vessel-masked structural similarity index. Identified optimal undersampling parameters were then evaluated in additional prospectively undersampled datasets. Compressed sensing reconstruction parameters were chosen based on a preliminary reconstruction parameter optimization. RESULTS: For all acceleration factors, using a fully sampled calibration area of 12 × 12 k-space lines and a polynomial order of 2 resulted in the highest image quality. The importance of parameter optimization of the sampling was found to increase for higher acceleration factors. The results were consistent across resolutions and regions of interest with vessels of varying sizes and tortuosity. The number of visible small vessels increased by 7.0% and 14.2% when compared to standard parameters for acceleration factors of 7.2 and 15, respectively. CONCLUSION: The image quality of compressed sensing time-of-flight MRA can be improved by appropriate choice of undersampling parameters. The optimized sets of parameters are independent of the acceleration factor and enable a larger number of vessels to be visualized.

A probabilistic Bayesian approach to recover R2*$$ {R}_{2\ast } $$ map and phase images for quantitative susceptibility mapping.

PURPOSE: Undersampling is used to reduce the scan time for high-resolution three-dimensional magnetic resonance imaging. In order to achieve better image quality and avoid manual parameter tuning, we propose a probabilistic Bayesian approach to recover R2∗$$ {R}_2^{\ast } $$ map and phase images for quantitative susceptibility mapping (QSM), while allowing automatic parameter estimation from undersampled data. THEORY: Sparse prior on the wavelet coefficients of images is interpreted from a Bayesian perspective as sparsity-promoting distribution. A novel nonlinear approximate message passing (AMP) framework that incorporates a mono-exponential decay model is proposed. The parameters are treated as unknown variables and jointly estimated with image wavelet coefficients. METHODS: Undersampling takes place in the y-z plane of k-space according to the Poisson-disk pattern. Retrospective undersampling is performed to evaluate the performances of different reconstruction approaches, prospective undersampling is performed to demonstrate the feasibility of undersampling in practice. RESULTS: The proposed AMP with parameter estimation (AMP-PE) approach successfully recovers R2∗$$ {R}_2^{\ast } $$ maps and phase images for QSM across various undersampling rates. It is more computationally efficient, and performs better than the state-of-the-art l1$$ {l}_1 $$ -norm regularization (L1) approach in general, except a few cases where the L1 approach performs as well as AMP-PE. CONCLUSION: AMP-PE achieves better performance by drawing information from both the sparse prior and the mono-exponential decay model. It does not require parameter tuning, and works with a clinical, prospective undersampling scheme where parameter tuning is often impossible or difficult due to the lack of ground-truth image.

Calibrationless multi-slice Cartesian MRI via orthogonally alternating phase encoding direction and joint low-rank tensor completion.

We propose a multi-slice acquisition with orthogonally alternating phase encoding (PE) direction and subsequent joint calibrationless reconstruction for accelerated multiple individual 2D slices or multi-slice 2D Cartesian MRI. Specifically, multi-slice multi-channel data are first acquired with random or uniform PE undersampling while orthogonally alternating PE direction between adjacent slices. They are then jointly reconstructed through a recently developed low-rank multi-slice Hankel tensor completion (MS-HTC) approach. The proposed acquisition and reconstruction strategy was evaluated with human brain MR data. It effectively suppressed aliasing artifacts even at high acceleration factor, outperforming the existing MS-HTC approach, where PE direction is the same between adjacent slices. More importantly, the new strategy worked robustly with uniform undersampling or random undersampling without any consecutive central k-space lines. In summary, our proposed multi-slice MRI strategy exploits both coil sensitivity and image content similarities across adjacent slices. Orthogonally alternating PE direction among slices substantially facilitates the low-rank completion process and improves image reconstruction quality. This new strategy is applicable to uniform and random PE undersampling. It can be easily implemented in practice for Cartesian parallel imaging of multiple individual 2D slices without any coil sensitivity calibration.