Deep J-Sense: Accelerated MRI Reconstruction via Unrolled Alternating Optimization.
Ontology highlight
ABSTRACT:
SUBMITTER: Arvinte M
PROVIDER: S-EPMC8767765 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PROPELLER technique is widely used in MRI examinations for being motion insensitive, but it prolongs scan time and is restricted mainly to T2 contrast. Parallel imaging can accelerate PROPELLER and enable more flexible contrasts. Here, we propose a multi-step joint-blade (MJB) SENSE reconstruction to reduce the noise amplification in parallel imaging accelerated PROPELLER. MJB SENSE utilizes the fact that PROPELLER blades contain sharable information and blade-combined images can serve as regularization references. It consists of three steps. First, conventional blade-combined images are obtained using the conventional simple single-blade (SSB) SENSE, which reconstructs each blade separately. Second, the blade-combined images are employed as regularization for blade-wise noise reduction. Last, with virtual high-frequency data resampled from the previous step, all blades are jointly reconstructed to form the final images. Simulations were performed to evaluate the proposed MJB SENSE for noise reduction and motion correction. MJB SENSE was also applied to both T2-weighted and T1-weighted in vivo brain data. Compared to SSB SENSE, MJB SENSE greatly reduced the noise amplification at various acceleration factors, leading to increased image SNR in all simulation and in vivo experiments, including T1-weighted imaging with short echo trains. Furthermore, it preserved motion correction capability and was computationally efficient.
| S-EPMC5311996 | biostudies-literature
Project description:PurposeTo accelerate and improve multishot diffusion-weighted MRI reconstruction using deep learning.MethodsAn unrolled pipeline containing recurrences of model-based gradient updates and neural networks was introduced for accelerating multishot DWI reconstruction with shot-to-shot phase correction. The network was trained to predict results of jointly reconstructed multidirection data using single-direction data as input. In vivo brain and breast experiments were performed for evaluation.ResultsThe proposed method achieves a reconstruction time of 0.1 second per image, over 100-fold faster than a shot locally low-rank reconstruction. The resultant image quality is comparable to the target from the joint reconstruction with a peak signal-to-noise ratio of 35.3 dB, a normalized root-mean-square error of 0.0177, and a structural similarity index of 0.944. The proposed method also improves upon the locally low-rank reconstruction (2.9 dB higher peak signal-to-noise ratio, 29% lower normalized root-mean-square error, and 0.037 higher structural similarity index). With training data from the brain, this method also generalizes well to breast diffusion-weighted imaging, and fine-tuning further reduces aliasing artifacts.ConclusionA proposed data-driven approach enables almost real-time reconstruction with improved image quality, which improves the feasibility of multishot DWI in a wide range of clinical and neuroscientific studies.
| S-EPMC8095163 | biostudies-literature
Project description:Accurate navigation and targeting are critical for neurological interventions including biopsy and deep brain stimulation. Real-time image guidance further improves surgical planning and MRI is ideally suited for both pre- and intra-operative imaging. However, balancing spatial and temporal resolution is a major challenge for real-time interventional MRI (i-MRI). Here, we proposed a deep unrolled neural network, dubbed as LSFP-Net, for real-time i-MRI reconstruction. By integrating LSFP-Net and a custom-designed, MR-compatible interventional device into a 3 T MRI scanner, a real-time MRI-guided brain intervention system is proposed. The performance of the system was evaluated using phantom and cadaver studies. 2D/3D real-time i-MRI was achieved with temporal resolutions of 80/732.8 ms, latencies of 0.4/3.66 s including data communication, processing and reconstruction time, and in-plane spatial resolution of 1 × 1 mm2. The results demonstrated that the proposed method enables real-time monitoring of the remote-controlled brain intervention, and showed the potential to be readily integrated into diagnostic scanners for image-guided neurosurgery.
| S-EPMC10716161 | biostudies-literature
Project description:Undersampling is an effective method for reducing scan acquisition time for MRI. Strategies for accelerated MRI such as parallel MRI and Compressed Sensing MRI present challenging image reconstruction problems with non-differentiable cost functions and computationally demanding operations. Variable splitting (VS) can simplify implementation of difficult image reconstruction problems, such as the combination of parallel MRI and Compressed Sensing, CS-SENSE-MRI. Combined with augmented Lagrangian (AL) and alternating minimization strategies, variable splitting can yield iterative minimization algorithms with simpler auxiliary variable updates. However, arbitrary variable splitting schemes are not guaranteed to converge. Many variable splitting strategies are combined with periodic boundary conditions. The resultant circulant Hessians enable 𝒪(n log n) computation but may compromise image accuracy at the spatial boundaries. We propose two methods for CS-SENSE-MRI that use regularization with non-periodic boundary conditions to prevent wrap-around artifacts. Each algorithm computes one of the resulting variable updates efficiently in 𝒪(n) time using a parallelizable tridiagonal solver. AL-tridiag is a VS method designed to enable efficient computation for non-periodic boundary conditions. Another proposed algorithm, ADMM-tridiag, uses a similar VS scheme but also ensures convergence to a minimizer of the proposed cost function using the Alternating Direction Method of Multipliers (ADMM). AL-tridiag and ADMM-tridiag show speeds competitive with previous VS CS-SENSE-MRI reconstruction algorithm AL-P2. We also apply the tridiagonal VS approach to a simple image inpainting problem.
| S-EPMC5424476 | biostudies-literature
Project description:Hand gesture recognition (HGR) are the most significant tasks for communicating with the real-world environment. Recently, gesture recognition has been extensively utilized in diverse domains, including but not limited to virtual reality, augmented reality, health diagnosis, and robot interaction. On the other hand, accurate techniques typically utilize various modalities generated from RGB input sequences, such as optical flow which acquires the motion data in the images and videos. However, this approach impacts real-time performance due to its demand of substantial computational resources. This study aims to introduce a robust and effective approach to hand gesture recognition. We utilize two publicly available benchmark datasets. Initially, we performed preprocessing steps, including denoising, foreground extraction, and hand detection via associated component techniques. Next, hand segmentation is done to detect landmarks. Further, we utilized three multi-fused features, including geometric features, 3D point modeling and reconstruction, and angular point features. Finally, grey wolf optimization served useful features of artificial neural networks for hand gesture recognition. The experimental results have shown that the proposed HGR achieved significant recognition of 89.92% and 89.76% over IPN hand and Jester datasets, respectively.
| S-EPMC10703008 | biostudies-literature
Project description:PURPOSE:Golden-angle radial sparse parallel (GRASP) MRI reconstruction requires gridding and regridding to transform data between radial and Cartesian k-space. These operations are repeatedly performed in each iteration, which makes the reconstruction computationally demanding. This work aimed to accelerate GRASP reconstruction using self-calibrating GRAPPA operator gridding (GROG) and to validate its performance in clinical imaging. METHODS:GROG is an alternative gridding approach based on parallel imaging, in which k-space data acquired on a non-Cartesian grid are shifted onto a Cartesian k-space grid using information from multicoil arrays. For iterative non-Cartesian image reconstruction, GROG is performed only once as a preprocessing step. Therefore, the subsequent iterative reconstruction can be performed directly in Cartesian space, which significantly reduces computational burden. Here, a framework combining GROG with GRASP (GROG-GRASP) is first optimized and then compared with standard GRASP reconstruction in 22 prostate patients. RESULTS:GROG-GRASP achieved approximately 4.2-fold reduction in reconstruction time compared with GRASP (?333?min versus ?78?min) while maintaining image quality (structural similarity index ? 0.97 and root mean square error ? 0.007). Visual image quality assessment by two experienced radiologists did not show significant differences between the two reconstruction schemes. With a graphics processing unit implementation, image reconstruction time can be further reduced to approximately 14?min. CONCLUSION:The GRASP reconstruction can be substantially accelerated using GROG. This framework is promising toward broader clinical application of GRASP and other iterative non-Cartesian reconstruction methods. Magn Reson Med 80:286-293, 2018. © 2017 International Society for Magnetic Resonance in Medicine.
| S-EPMC5876102 | biostudies-literature
Project description:PurposeTo enable parameter-free, accelerated cardiovascular magnetic resonance (CMR).MethodsRegularized reconstruction methods, such as compressed sensing (CS), can significantly accelerate MRI data acquisition but require tuning of regularization weights. In this work, a technique, called Sparsity adaptive Composite Recovery (SCoRe) that exploits sparsity in multiple, disparate sparsifying transforms is presented. A data-driven adjustment of the relative contributions of different transforms yields a parameter-free CS recovery process. SCoRe is validated in a dynamic digital phantom as well as in retrospectively and prospectively undersampled cine CMR data.ResultsThe results from simulation and 6 retrospectively undersampled datasets indicate that SCoRe with auto-tuned regularization weights yields lower root-mean-square error (RMSE) and higher structural similarity index (SSIM) compared to state-of-the-art CS methods. In 45 prospectively undersampled datasets acquired from 15 volunteers, the image quality was scored by 2 expert reviewers, with SCoRe receiving a higher average score (p < 0.01) compared to other CS methods.ConclusionsSCoRe enables accelerated cine CMR from highly undersampled data. In contrast to other acceleration techniques, SCoRe adapts regularization weights based on noise power and level of sparsity in each transform, yielding superior performance without admitting any free parameters.
| S-EPMC6435424 | biostudies-literature
Project description:Multi-task learning (MTL) learns multiple related tasks simultaneously to improve generalization performance. Alternating structure optimization (ASO) is a popular MTL method that learns a shared low-dimensional predictive structure on hypothesis spaces from multiple related tasks. It has been applied successfully in many real world applications. As an alternative MTL approach, clustered multi-task learning (CMTL) assumes that multiple tasks follow a clustered structure, i.e., tasks are partitioned into a set of groups where tasks in the same group are similar to each other, and that such a clustered structure is unknown a priori. The objectives in ASO and CMTL differ in how multiple tasks are related. Interestingly, we show in this paper the equivalence relationship between ASO and CMTL, providing significant new insights into ASO and CMTL as well as their inherent relationship. The CMTL formulation is non-convex, and we adopt a convex relaxation to the CMTL formulation. We further establish the equivalence relationship between the proposed convex relaxation of CMTL and an existing convex relaxation of ASO, and show that the proposed convex CMTL formulation is significantly more efficient especially for high-dimensional data. In addition, we present three algorithms for solving the convex CMTL formulation. We report experimental results on benchmark datasets to demonstrate the efficiency of the proposed algorithms.
| S-EPMC4200604 | biostudies-literature
Project description:PurposeTo rapidly reconstruct undersampled 3D non-Cartesian image-based navigators (iNAVs) using an unrolled deep learning (DL) model, enabling nonrigid motion correction in coronary magnetic resonance angiography (CMRA).MethodsAn end-to-end unrolled network is trained to reconstruct beat-to-beat 3D iNAVs acquired during a CMRA sequence. The unrolled model incorporates a nonuniform FFT operator in TensorFlow to perform the data-consistency operation, and the regularization term is learned by a convolutional neural network (CNN) based on the proximal gradient descent algorithm. The training set includes 6,000 3D iNAVs acquired from 7 different subjects and 11 scans using a variable-density (VD) cones trajectory. For testing, 3D iNAVs from 4 additional subjects are reconstructed using the unrolled model. To validate reconstruction accuracy, global and localized motion estimates from DL model-based 3D iNAVs are compared with those extracted from 3D iNAVs reconstructed with l1 -ESPIRiT. Then, the high-resolution coronary MRA images motion corrected with autofocusing using the l1 -ESPIRiT and DL model-based 3D iNAVs are assessed for differences.Results3D iNAVs reconstructed using the DL model-based approach and conventional l1 -ESPIRiT generate similar global and localized motion estimates and provide equivalent coronary image quality. Reconstruction with the unrolled network completes in a fraction of the time compared to CPU and GPU implementations of l1 -ESPIRiT (20× and 3× speed increases, respectively).ConclusionsWe have developed a deep neural network architecture to reconstruct undersampled 3D non-Cartesian VD cones iNAVs. Our approach decreases reconstruction time for 3D iNAVs, while preserving the accuracy of nonrigid motion information offered by them for correction.
| S-EPMC8331070 | biostudies-literature
Project description:PurposeTo develop and evaluate a real-time phase contrast (PC) MRI protocol via complex-difference deep learning (DL) framework.MethodsDL used two 3D U-nets to separately filter aliasing artifact from radial real-time velocity-compensated and complex-difference images. U-nets were trained with synthetic real-time PC generated from electrocardiograph (ECG) -gated, breath-hold, segmented PC (ECG-gated segmented PC) acquired at the ascending aorta of 510 patients. In 21 patients, free-breathing, ungated real-time (acceleration rate = 28.8) and ECG-gated segmented (acceleration rate = 2) PC were prospectively acquired at the ascending aorta. Hemodynamic parameters (cardiac output [CO], stroke volume [SV], and mean velocity at peak systole [peak mean velocity]) were measured for ECG-gated segmented and DL-filtered synthetic real-time PC and compared using Bland-Altman and linear regression analyses. Additionally, hemodynamic parameters were quantified from DL-filtered, compressed-sensing (CS) -reconstructed, and gridding reconstructed prospective real-time PC and compared to ECG-gated segmented PC.ResultsSynthetic real-time PC with DL showed strong correlation (R > 0.98) and good agreement with ECG-gated segmented PC for quantified hemodynamic parameters (mean-difference: CO = -0.3 L/min, SV = -4.3 mL, peak mean velocity = -2.3 cm/s). On average, DL required 0.39 s/frame to filter prospective real-time PC, which was 4.6-fold faster than CS. Compared to CS, DL showed superior correlation, tighter limits of agreement (LOAs), better bias for peak mean velocity, and worse bias for CO and SV. Compared to gridding, DL showed similar correlation, tighter LOAs for CO and SV, similar bias for CO, and worse bias for SV and peak mean velocity.ConclusionThe complex-difference DL framework accelerated real-time PC-MRI by nearly 28-fold, enabling rapid free-running real-time assessment of flow hemodynamics.
| S-EPMC8145775 | biostudies-literature