Multi-Device Parallel MRI Reconstruction: Efficient Partitioning for Undersampled 5D Cardiac CINE.

Cardiac CINE, a form of dynamic cardiac MRI, is indispensable in the diagnosis and treatment of heart conditions, offering detailed visualization essential for the early detection of cardiac diseases. As the demand for higher-resolution images increases, so does the volume of data requiring processing, presenting significant computational challenges that can impede the efficiency of diagnostic imaging. Our research presents an approach that takes advantage of the computational power of multiple Graphics Processing Units (GPUs) to address these challenges. GPUs are devices capable of performing large volumes of computations in a short period, and have significantly improved the cardiac MRI reconstruction process, allowing images to be produced faster. The innovation of our work resides in utilizing a multi-device system capable of processing the substantial data volumes demanded by high-resolution, five-dimensional cardiac MRI. This system surpasses the memory capacity limitations of single GPUs by partitioning large datasets into smaller, manageable segments for parallel processing, thereby preserving image integrity and accelerating reconstruction times. Utilizing OpenCL technology, our system offers adaptability and cross-platform functionality, ensuring wider applicability. The proposed multi-device approach offers an advancement in medical imaging, accelerating the reconstruction process and facilitating faster and more effective cardiac health assessment.

Elastic AlignedSENSE for Dynamic MR Reconstruction: A Proof of Concept in Cardiac Cine.

Numerous methods in the extensive literature on magnetic resonance imaging (MRI) reconstruction exploit temporal redundancy to accelerate cardiac cine. Some of them include motion compensation, which involves high computational costs and long runtimes. In this work, we proposed a method-elastic alignedSENSE (EAS)-for the direct reconstruction of a motion-free image plus a set of nonrigid deformations to reconstruct a 2D cardiac sequence. The feasibility of the proposed approach was tested in 2D Cartesian and golden radial multi-coil breath-hold cardiac cine acquisitions. The proposed approach was compared against parallel imaging compressed sense (sPICS) and group-wise motion corrected compressed sense (GWCS) reconstructions. EAS provides better results on objective measures with considerable less runtime when an acceleration factor is higher than 10×. Subjective assessment of an expert, however, invited proposing the combination of EAS and GWCS as a preferable alternative to GWCS or EAS in isolation.

Fast 4D elastic group-wise image registration. Convolutional interpolation revisited.

BACKGROUND AND OBJECTIVE: This paper proposes a new and highly efficient implementation of 3D+t groupwise registration based on the free-form deformation paradigm. METHODS: Deformation is posed as a cascade of 1D convolutions, achieving great reduction in execution time for evaluation of transformations and gradients. RESULTS: The proposed method has been applied to 4D cardiac MRI and 4D thoracic CT monomodal datasets. Results show an average runtime reduction above 90%, both in CPU and GPU executions, compared with the classical tensor product formulation. CONCLUSIONS: Our implementation, although fully developed for the metric sum of squared differences, can be extended to other metrics and its adaptation to multiresolution strategies is straightforward. Therefore, it can be extremely useful to speed up image registration procedures in different applications where high dimensional data are involved.

A clinically viable vendor-independent and device-agnostic solution for accelerated cardiac MRI reconstruction.

BACKGROUND AND OBJECTIVE: Recent research has reported methods that reconstruct cardiac MR images acquired with acceleration factors as high as 15 in Cartesian coordinates. However, the computational cost of these techniques is quite high, taking about 40 min of CPU time in a typical current machine. This delay between acquisition and final result can completely rule out the use of MRI in clinical environments in favor of other techniques, such as CT. In spite of this, reconstruction methods reported elsewhere can be parallelized to a high degree, a fact that makes them suitable for GPU-type computing devices. This paper contributes a vendor-independent, device-agnostic implementation of such a method to reconstruct 2D motion-compensated, compressed-sensing MRI sequences in clinically viable times. METHODS: By leveraging our OpenCLIPER framework, the proposed system works in any computing device (CPU, GPU, DSP, FPGA, etc.), as long as an OpenCL implementation is available, and development is significantly simplified versus a pure OpenCL implementation. In OpenCLIPER, the problem is partitioned in independent black boxes which may be connected as needed, while device initialization and maintenance is handled automatically. Parallel implementations of both a groupwise FFD-based registration method, as well as a multicoil extension of the NESTA algorithm have been carried out as processes of OpenCLIPER. Our platform also includes significant development and debugging aids. HIP code and precompiled libraries can be integrated seamlessly as well since OpenCLIPER makes data objects shareable between OpenCL and HIP. This also opens an opportunity to include CUDA source code (via HIP) in prospective developments. RESULTS: The proposed solution can reconstruct a whole 12-14 slice CINE volume acquired in 19-32 coils and 20 phases, with an acceleration factor of ranging 4-8, in a few seconds, with results comparable to another popular platform (BART). If motion compensation is included, reconstruction time is in the order of one minute. CONCLUSIONS: We have obtained clinically-viable times in GPUs from different vendors, with delays in some platforms that do not have correspondence with its price in the market. We also contribute a parallel groupwise registration subsystem for motion estimation/compensation and a parallel multicoil NESTA subsystem for l1-l2-norm problem solving.

Reconstruction techniques for cardiac cine MRI.

The present survey describes the state-of-the-art techniques for dynamic cardiac magnetic resonance image reconstruction. Additionally, clinical relevance, main challenges, and future trends of this image modality are outlined. Thus, this paper aims to provide a general vision about cine MRI as the standard procedure in functional evaluation of the heart, focusing on technical methodologies.

Space-time variant weighted regularization in compressed sensing cardiac cine MRI.

PURPOSE: To analyze the impact on image quality and motion fidelity of a motion-weighted space-time variant regularization term in compressed sensing cardiac cine MRI. METHODS: k-t SPARSE-SENSE with temporal total variation (tTV) is used as the base reconstruction algorithm. Motion in the dynamic image is estimated by means of a robust registration technique for non-rigid motion. The resulting deformation fields are used to leverage the regularization term. The results are compared with standard k-t SPARSE-SENSE with tTV regularization as well as with an improved version of this algorithm that makes use of tTV and temporal Fast Fourier Transform regularization in x-f domain. RESULTS: The proposed method with space-time variant regularization provides higher motion fidelity and image quality than the two previously reported methods. Difference images between undersampled reconstruction and fully sampled reference images show less systematic errors with the proposed approach. CONCLUSIONS: Usage of a space-time variant regularization offers reconstructions with better image quality than the state of the art approaches used for comparison.

Bioinspired Architecture Selection for Multitask Learning.

Faced with a new concept to learn, our brain does not work in isolation. It uses all previously learned knowledge. In addition, the brain is able to isolate the knowledge that does not benefit us, and to use what is actually useful. In machine learning, we do not usually benefit from the knowledge of other learned tasks. However, there is a methodology called Multitask Learning (MTL), which is based on the idea that learning a task along with other related tasks produces a transfer of information between them, what can be advantageous for learning the first one. This paper presents a new method to completely design MTL architectures, by including the selection of the most helpful subtasks for the learning of the main task, and the optimal network connections. In this sense, the proposed method realizes a complete design of the MTL schemes. The method is simple and uses the advantages of the Extreme Learning Machine to automatically design a MTL machine, eliminating those factors that hinder, or do not benefit, the learning process of the main task. This architecture is unique and it is obtained without testing/error methodologies that increase the computational complexity. The results obtained over several real problems show the good performances of the designed networks with this method.

Automatic detection of the intima-media thickness in ultrasound images of the common carotid artery using neural networks.

Atherosclerosis is the leading underlying pathologic process that results in cardiovascular diseases, which represents the main cause of death and disability in the world. The atherosclerotic process is a complex degenerative condition mainly affecting the medium- and large-size arteries, which begins in childhood and may remain unnoticed during decades. The intima-media thickness (IMT) of the common carotid artery (CCA) has emerged as one of the most powerful tool for the evaluation of preclinical atherosclerosis. IMT is measured by means of B-mode ultrasound images, which is a non-invasive and relatively low-cost technique. This paper proposes an effective image segmentation method for the IMT measurement in an automatic way. With this purpose, segmentation is posed as a pattern recognition problem, and a combination of artificial neural networks has been trained to solve this task. In particular, multi-layer perceptrons trained under the scaled conjugate gradient algorithm have been used. The suggested approach is tested on a set of 60 longitudinal ultrasound images of the CCA by comparing the automatic segmentation with four manual tracings. Moreover, the intra- and inter-observer errors have also been assessed. Despite of the simplicity of our approach, several quantitative statistical evaluations have shown its accuracy and robustness.