No abstract

Purpose: In diffusion-weighted magnetic resonance imaging (DW-MRI), the fiber orientation distribution function (fODF) is of great importance for solving complex fiber configurations to achieve reliable tractography throughout the brain, which ultimately facilitates the understanding of brain connectivity and exploration of neurological dysfunction. Recently, multi-shell multi-tissue constrained spherical deconvolution (MSMT-CSD) method has been explored for reconstructing full fODFs. To achieve a reliable fitting, similar to other model-based approaches, a large number of diffusion measurements is typically required for MSMT-CSD method. The prolonged acquisition is, however, not feasible in practical clinical routine and is prone to motion artifacts. To accelerate the acquisition, we proposed a method to reconstruct the fODF from downsampled diffusion-weighted images (DWIs) by leveraging the strong inference ability of the deep convolutional neural network (CNN). Methods: The method treats spherical harmonics (SH)-represented DWI signals and fODF coefficients as inputs and outputs, respectively. To compensate for the reduced gradient directions with reduced number of DWIs in acquisition in each voxel, its surrounding voxels are incorporated by the network for exploiting their spatial continuity. The resulting fODF coefficients are fitted with applying the CNN in a multi-target regression model. The network is composed of two convolutional layers and three fully connected layers. To obtain an initial evaluation of the method, we quantitatively measured its performance on a simulated dataset. Then, for in vivo tests, we employed data from 24 subjects from the Human Connectome Project (HCP) as training set and six subjects as test set. The performance of the proposed method was primarily compared to the super-resolved MSMT-CSD with the decreasing number of DWIs. The fODFs reconstructed by MSMT-CSD from all available 288 DWIs were used as training labels and the reference standard. The performance was quantitatively measured by the angular correlation coefficient (ACC) and the mean angular error (MAE). Results: For the simulated dataset, the proposed method exhibited the potential advantage over the model reconstruction. For the in vivo dataset, it achieved superior results over the MSMT-CSD in all the investigated cases, with its advantage more obvious when a limited number of DWIs were used. As the number of DWIs was reduced from 95 to 25, the median ACC ranged from 0.96 to 0.91 for the CNN, but 0.93 to 0.77 for the MSMT-CSD (with perfect score of 1). The angular error in the typical regions of interest (ROIs) was also much lower, especially in multi-fiber regions. The average MAE for the CNN method in regions containing one, two, three fibers was, respectively, 1.09°, 2.75°, and 8.35°smaller than the MSMT-CSD method. The visual inception of the fODF further 3101 confirmed this superiority. Moreover, the tractography results validated the effectiveness of the learned fODF, in preserving known major branching fiber...

Purpose: To improve image quality and accelerate the acquisition of 3D MR fingerprinting (MRF). Methods: Building on the multi-axis spiral-projection MRF technique, a subspace reconstruction with locally low-rank constraint and a modified spiral-projection spatiotemporal encoding scheme called tiny golden-angle shuffling were implemented for rapid whole-brain high-resolution quantitative mapping. Reconstruction parameters such as the locally low-rank regularization parameter and the subspace rank were tuned using retrospective in vivo data and simulated examinations. B 0 inhomogeneity correction using multifrequency interpolation was incorporated into the subspace reconstruction to further improve the image quality by mitigating blurring caused by off-resonance effect. Results: The proposed MRF acquisition and reconstruction framework yields high-quality 1-mm isotropic whole-brain quantitative maps in 2 min at better quality compared with 6-min acquisitions of prior approaches. The proposed method was validated to not induce bias in T 1 and T 2 mapping. High-quality whole-brain MRF data were also obtained at 0.66-mm isotropic resolution in 4 min using the proposed technique, where the increased resolution was shown to improve visualization of subtle brain structures. Conclusions: The proposed tiny golden-angle shuffling, MRF with optimized spiral-projection trajectory and subspace reconstruction enables high-resolution quantitative mapping in ultrafast acquisition time.

With the success of deep learning in a wide variety of areas, many deep multi-task learning (MTL) models have been proposed claiming improvements in performance obtained by sharing the learned structure across several related tasks. However, the dynamics of multi-task learning in deep neural networks is still not well understood at either the theoretical or experimental level. In particular, the usefulness of different task pairs is not known a priori. Practically, this means that properly combining the losses of different tasks becomes a critical issue in multi-task learning, as different methods may yield different results. In this paper, we benchmarked different multi-task learning approaches using shared trunk with task specific branches architecture across three different MTL datasets. For the first dataset, i.e. Multi-MNIST (Modified National Institute of Standards and Technology database), we thoroughly tested several weighting strategies, including simply adding task-specific cost functions together, dynamic weight average (DWA) and uncertainty weighting methods each with various amounts of training data per-task. We find that multitask learning typically does not improve performance for a user-defined combination of tasks. Further experiments evaluated on diverse tasks and network architectures on various datasets suggested that multitask learning requires careful selection of both task pairs and weighting strategies to equal or exceed the performance of single task learning.INDEX TERMS Dynamic weighting average, multi-MNIST, multi-objective optimization, multi-task learning, uncertainty weighting.

Diffusion kurtosis imaging (DKI) is an advanced diffusion imaging method that captures complex brain microstructural properties; however, it often has a lengthy acquisition time compared to conventional diffusion tensor imaging (DTI). Recently, a deep learning-based method has shown the potential for reducing the number of diffusion-weighted images (DWIs) required to compute the rotationally invariant scalar measures to twelve. In this study, we propose a three-dimensional (3D) convolutional neural network (CNN) to estimate the scalar measures. This network further improves the performance of the deep learning-based method with a largely reduced number of required DWIs. In our approach, all the DTI and DKI measures were estimated using a single network, and a hierarchical structure was introduced to customize the outputs based on their computational complexities and to learn the commonalities of the measures. Moreover, 3 × 3 × 3 convolution kernels were introduced to extract features from the 3D input patches and utilize the spatial context from adjacent neighborhoods, which also strengthened the network's robustness against noise. The proposed method was evaluated with two datasets. The results showed that, compared with the previous method that used an artificial neural network, our proposed hierarchical CNN provided enhanced efficiency for estimating all eight diffusion measures. It also improved the robustness against noise and retained the fine structures with only a few DWIs (as few as eight). This result suggests that it is possible to achieve kurtosis mapping in most clinical scanners within one minute, which could significantly extend the clinical utility of the DKI.

Multicenter diffusion magnetic resonance imaging (MRI) has drawn great attention recently due to the expanding need for large-scale brain imaging studies, whereas the variability in MRI scanners and data acquisition tends to confound reliable individual-based analysis of diffusion measures. In addition, a growing number of multi-shell diffusion models have been shown with the potential to generate various estimates of physio-pathological information, yet their reliability and reproducibility in multicenter studies remain to be assessed. In this article, we describe a multi-shell diffusion dataset collected from three traveling subjects with identical acquisition settings in ten imaging centers. Both the scanner type and imaging protocol for anatomical and diffusion imaging were well controlled. This dataset is expected to replenish individual reproducible studies via multicenter collaboration by providing an open resource for advanced and novel microstructural and tractography modelling and quantification.

No abstract

Multicenter magnetic resonance imaging is gaining more popularity in large-sample projects. Since both varying hardware and software across different centers cause unavoidable data heterogeneity across centers, its impact on reliability in study outcomes has also drawn much attention recently.One fundamental issue arises in how to derive model parameters reliably from image data of varying quality. This issue is even more challenging for advanced diffusion methods such as diffusion kurtosis imaging (DKI). Recently, deep learning-based methods have been demonstrated with their potential for robust and efficient computation of diffusion-derived measures. Inspired by these approaches, the current study specifically designed a framework based on a three-dimensional hierarchical convolutional neural network, to jointly reconstruct and harmonize DKI measures from multicenter acquisition to reformulate these to a state-of-the-art hardware using data from traveling subjects. The results from the harmonized data acquired with different protocols show that: 1) the inter-scanner variation of DKI measures within white matter was reduced by 51.5% in mean kurtosis, 65.9% in axial kurtosis, 53.7% in radial kurtosis, and 61.5% in kurtosis fractional anisotropy, respectively; 2) data reliability of each single scanner was enhanced and brought to the level of the reference scanner; and 3) the harmonization network was able to reconstruct reliable DKI values from high data variability. Overall the results demonstrate the feasibility of the proposed deep learning-based method for DKI harmonization and help to simplify the protocol setup procedure for multicenter scanners with different hardware and software configurations.