Cardiac Datasets Research Articles

Enhancing data security of cardiac patients in IoMT with Twin-Shield Encryption

<p>Cardiac disease kills most people worldwide. Predicting and monitoring cardiac problems early improves disease treatment and patient outcomes. The Internet of Medical Things (IoMT) can monitor and analyze physiological data in real-time, changing healthcare. Many researchers find data generation problematic. Encryption is needed to secure a massive amount of data. This paper presents a Twin-Shield Encryption (TSE) that combines Elliptic Curve Cryptography (HECC) and Rivest-Shamir-Adleman (RSA) IoMT assistance for heart illness patient monitoring. Cleveland cardiac dataset from the University of California Irvine (UCI) research repository is collected. It has 12 qualities and 303 occurrences. The data is pre-processed using normalization; feature extracted using Principal Component Analysis (PCA), and securely transmitted to the cloud infrastructure for further processing and analysis. TSE encrypts patient data to prevent unauthorized access and maintain data integrity during transmission and storage. The framework could enhance cardiac ailment diagnosis, treatment, and management by giving clinicians and patients individualized care based on physiological profiles.</p>

A synthetic cardiac episode generator for explainable, pathology based action potential using heuristic polynomial signatures

A synthetic cardiac episode generator for explainable, pathology based action potential using heuristic polynomial signatures

Attractive deep morphology-aware active contour network for vertebral body contour extraction with extensions to heterogeneous and semi-supervised scenarios.

Automatic vertebral body contour extraction (AVBCE) from heterogeneous spinal MRI is indispensable for the comprehensive diagnosis and treatment of spinal diseases. However, AVBCE is challenging due to data heterogeneity, image characteristics complexity, and vertebral body morphology variations, which may cause morphology errors in semantic segmentation. Deep active contour-based (deep ACM-based) methods provide a promising complement for tackling morphology errors by directly parameterizing the contour coordinates. Extending the target contours' capture range and providing morphology-aware parameter maps are crucial for deep ACM-based methods. For this purpose, we propose a novel Attractive Deep Morphology-aware actIve contouR nEtwork (ADMIRE) that embeds an elaborated contour attraction term (CAT) and a comprehensive contour quality (CCQ) loss into the deep ACM-based framework. The CAT adaptively extends the target contours' capture range by designing an all-to-all force field to enable the target contours' energy to contribute to farther locations. Furthermore, the CCQ loss is carefully designed to generate morphology-aware active contour parameters by simultaneously supervising the contour shape, tension, and smoothness. These designs, in cooperation with the deep ACM-based framework, enable robustness to data heterogeneity, image characteristics complexity, and target contour morphology variations. Furthermore, the deep ACM-based ADMIRE is able to cooperate well with semi-supervised strategies such as mean teacher, which enables its function in semi-supervised scenarios. ADMIRE is trained and evaluated on four challenging datasets, including three spinal datasets with more than 1000 heterogeneous images and more than 10000 vertebrae bodies, as well as a cardiac dataset with both normal and pathological cases. Results show ADMIRE achieves state-of-the-art performance on all datasets, which proves ADMIRE's accuracy, robustness, and generalization ability.

Low-rank plus sparse joint smoothing model based on tensor singular value decomposition for dynamic MRI reconstruction

Dynamic magnetic resonance imaging (DMRI) is an important medical imaging modality, but the long imaging time limits its practical applications. This paper proposes a low-rank plus sparse joint smoothing model based on tensor singular value decomposition (T-SVD) to reconstruct DMR images from highly under-sampled k-t space data. The low-rank plus sparse tensor (ℒ+S) model decomposes the DMR data into a low-rank and sparse tensor, which naturally fits the dynamic MR images characteristics and exploits the spatiotemporal correlation of DMRI data to improve reconstruction effect. T-SVD is utilized in the ℒ+S model to maintain the intrinsic structure of the low-rank tensor and further enhance the low-rank property. In addition, considering the global multi-dimensional smoothness of the DMR images, the proposed method joint tensor total variation (TTV) constraints to utilize the smoothness of DMR images to obtain more reconstruction details while protecting the global structure. We conducted experiments on the dynamic cardiac datasets, and the experiment results show that the proposed method has superior performance to several state-of-the-art imaging methods.

Medical Image Segmentation Method Based on Improved Unet

This paper is an attempt to apply 3DUnet system to medical image segmentation. The classifying model is built based on actual medical images from MSD Cardiac dataset. The 3DUnet system, which is developed on Convolutional Neural Networks will be of great significance in medical diagnosis and analysis. The paper analyzes and contains details of the 3DUnet system we built and the algorithms we applied. We applied the method of cutting the input images into patches and K-fold cross validation to obtain better results. The final average value of Dice is over 87%. Codes are available: https://github.com/LRXuanxuan/jubilant-chainsaw.

Partial Unbalanced Feature Transport for Cross-Modality Cardiac Image Segmentation.

Deep learning based approaches have achieved great success on the automatic cardiac image segmentation task. However, the achieved segmentation performance remains limited due to the significant difference across image domains, which is referred to as domain shift. Unsupervised domain adaptation (UDA), as a promising method to mitigate this effect, trains a model to reduce the domain discrepancy between the source (with labels) and the target (without labels) domains in a common latent feature space. In this work, we propose a novel framework, named Partial Unbalanced Feature Transport (PUFT), for cross-modality cardiac image segmentation. Our model facilities UDA leveraging two Continuous Normalizing Flow-based Variational Auto-Encoders (CNF-VAE) and a Partial Unbalanced Optimal Transport (PUOT) strategy. Instead of directly using VAE for UDA in previous works where the latent features from both domains are approximated by a parameterized variational form, we introduce continuous normalizing flows (CNF) into the extended VAE to estimate the probabilistic posterior and alleviate the inference bias. To remove the remaining domain shift, PUOT exploits the label information in the source domain to constrain the OT plan and extracts structural information of both domains, which are often neglected in classical OT for UDA. We evaluate our proposed model on two cardiac datasets and an abdominal dataset. The experimental results demonstrate that PUFT achieves superior performance compared with state-of-the-art segmentation methods for most structural segmentation.

Accelerating GRAPPA reconstruction using SoC design for real-time cardiac MRI

Real-time cardiac MRI is a rapidly developing area of research that has the potential to improve the diagnosis and treatment of cardiovascular diseases. However, the acquisition of high-quality real-time cardiac MR (CMR) images is challenging as it requires a high frame rate and temporal resolution. To overcome this challenge, there have been recent efforts on several approaches including hardware-based improvements and image reconstruction techniques such as compressed sensing and parallel MRI. The use of parallel MRI techniques such as GRAPPA (Generalized Autocalibrating Partial Parallel Acquisition) is a promising approach for improving the temporal resolution of MRI and expanding its applications in clinical practice. However, the GRAPPA algorithm involves a significant amount of computation, particularly for high acceleration factors and large datasets. This can result in long reconstruction times, which can limit the ability to achieve real-time imaging or high frame rates. One solution to this challenge is to use specialized hardware i.e. field-programmable gate arrays (FPGAs). In this work, a novel 32-bit floating-point FPGA-based GRAPPA accelerator is proposed with an aim to reconstruct high-quality cardiac MR images at higher frame rates, making it well suited for real-time clinical applications. The proposed FPGA-based accelerator consists of custom-designed data processing units named as dedicated computational engines (DCEs) that allow for a continuous flow of data between the calibration and synthesis stages of GRAPPA reconstruction process. This greatly increases the throughput and reduces the latency of the overall proposed system. Moreover, a high-speed memory module (DDR4-SDRAM) is integrated with the proposed architecture to store the multi-coil MR data. An on-chip quad-core ARM Cortex-A53 processor is used to manage access control information required for data transfer between the DCEs and DDR4-SDRAM. The proposed accelerator is implemented on Xilinx Zynq UltraScale+MPSoC using high-level synthesis (HLS) and hardware descriptive language (HDL) with an aim to explore the trade-offs between the reconstruction time, resource utilization and design effort. Several experiments have been performed using in-vivo cardiac datasets i.e. 18-receiver coil and 30-receiver coil to evaluate the performance of the proposed accelerator. A comparison is performed with the contemporary CPU and GPU-based GRAPPA reconstruction methods in terms of reconstruction time, frames-per-second and reconstruction accuracy (RMSE and SNR). The results show that the proposed accelerator achieves speed-up factors up to 121× and 9× as compared to the contemporary CPU-based and GPU-based GRAPPA reconstruction methods, respectively. Moreover, it has been demonstrated that the proposed accelerator can achieve reconstruction rates of up to ∼27 frames-per-second while maintaining the visual quality of the reconstructed images.

Regional perception and multi-scale feature fusion network for cardiac segmentation

Objective. Cardiovascular disease (CVD) is a group of diseases affecting cardiac and blood vessels, and short-axis cardiac magnetic resonance (CMR) images are considered the gold standard for the diagnosis and assessment of CVD. In CMR images, accurate segmentation of cardiac structures (e.g. left ventricle) assists in the parametric quantification of cardiac function. However, the dynamic beating of the heart renders the location of the heart with respect to other tissues difficult to resolve, and the myocardium and its surrounding tissues are similar in grayscale. This makes it challenging to accurately segment the cardiac images. Our goal is to develop a more accurate CMR image segmentation approach. Approach. In this study, we propose a regional perception and multi-scale feature fusion network (RMFNet) for CMR image segmentation. We design two regional perception modules, a window selection transformer (WST) module and a grid extraction transformer (GET) module. The WST module introduces a window selection block to adaptively select the window of interest to perceive information, and a windowed transformer block to enhance global information extraction within each feature window. The WST module enhances the network performance by improving the window of interest. The GET module grids the feature maps to decrease the redundant information in the feature maps and enhances the extraction of latent feature information of the network. The RMFNet further introduces a novel multi-scale feature extraction module to improve the ability to retain detailed information. Main results. The RMFNet is validated with experiments on three cardiac data sets. The results show that the RMFNet outperforms other advanced methods in overall performance. The RMFNet is further validated for generalizability on a multi-organ data set. The results also show that the RMFNet surpasses other comparison methods. Significance. Accurate medical image segmentation can reduce the stress of radiologists and play an important role in image-guided clinical procedures.

3D Echocardiogram Reconstruction Employing a Flip Directional Texture Pyramid

Three dimensional (3D) echocardiogram enables cardiologists to visualize suspicious cardiac structures in detail. In recent years, this three-dimensional echocardiogram carries important clinical value in virtual surgical simulation. However, this 3D echocardiogram involves a trade-off difficulty between accuracy and efficient computation in clinical diagnosis. This paper presents a novel Flip Directional 3D Volume Reconstruction (FD-3DVR) method for the reconstruction of echocardiogram images. The proposed method consists of two main steps: multiplanar volumetric imaging and 3D volume reconstruction. In the creation of multiplanar volumetric imaging, two-dimensional (2D) image pixels are mapped into voxels of the volumetric grid. As the obtained slices are discontinuous, there are some missing voxels in the volume data. To restore the structural and textural information of 3D ultrasound volume, the proposed method creates a volume pyramid in parallel with the flip directional texture pyramid. Initially, the nearest neighbors of missing voxels in the multiplanar volumetric imaging are identified by 3D ANN (Approximate Nearest Neighbor) patch matching method. Furthermore, a flip directional texture pyramid is proposed and aggregated with distance in patch matching to find out the most similar neighbors. In the reconstruction step, structural and textural information obtained from different flip angle directions can reconstruct 3D volume well with the desired accuracy. Compared with existing 3D reconstruction methods, the proposed Flip Directional 3D Volume Reconstruction (FD-3DVR) method provides superior performance for the mean peak signal-to-noise ratio (40.538 for the proposed method I and 39.626 for the proposed method II). Experimental results performed on the cardiac datasets demonstrate the efficiency of the proposed method for the reconstruction of echocardiogram images.

Heart disease prediction using scaled conjugate gradient backpropagation of artificial neural network

Heart disease is a deadly disease in human life. The mortality rate from any disease is the highest in the world. Therefore, before reaching the final stage of this heart disease, all precautionary measures must be taken. For this reason without the help of any kind of traditional methods, if we can scientifically diagnose heart disease at an early stage through various decision support systems, then surely death rate of this disease will decrease in the whole world. Many researchers investigate the diagnosis of heart disease by creating various intelligent medical decision support systems. Artificial neural network concepts represent the highest predictive accuracy over medical data compared to other decision support systems. In this paper, we propose a better prediction method for the existence of heart disease through the scaled conjugate gradient backpropagation of artificial neural networks using K-fold cross-validation. For cardiac datasets, the University of California Irvine (UCI) Machine Learning Repository and IEEE data port have been used. For Cleveland processed heart dataset, the proposed system uses 13 input attributes and provides minimum 63.3803% and maximum 100% accurate results; similarly, for Cleveland Hungarian Statlog heart dataset, the proposed system uses 11 input attributes and provides minimum 88.4754% and maximum 100% accurate results by estimating the presence and absence of heart disease during testing.

Segmentation of human aorta using 3D nnU-net-oriented deep learning.

Computed tomography angiography (CTA) has become the main imaging technique for cardiovascular diseases. Before performing the transcatheter aortic valve intervention operation, segmenting images of the aortic sinus and nearby cardiovascular tissue from enhanced images of the human heart is essential for auxiliary diagnosis and guiding doctors to make treatment plans. This paper proposes a nnU-Net (no-new-Net) framework based on deep learning (DL) methods to segment the aorta and the heart tissue near the aortic valve in cardiac CTA images, and verifies its accuracy and effectiveness. A total of 130 sets of cardiac CTA image data (88 training sets, 22 validation sets, and 20 test sets) of different subjects have been used for the study. The advantage of the nnU-Net model is that it can automatically perform preprocessing and data augmentation according to the input image data, can dynamically adjust the network structure and parameter configuration, and has a high model generalization ability. Experimental results show that the DL method based on nnU-Net can accurately and effectively complete the segmentation task of cardiac aorta and cardiac tissue near the root on the cardiac CTA dataset, and achieves an average Dice similarity coefficient of 0.9698 ± 0.0081. The actual inference segmentation effect basically meets the preoperative needs of the clinic. Using the DL method based on the nnU-Net model solves the problems of low accuracy in threshold segmentation, bad segmentation of organs with fuzzy edges, and poor adaptability to different patients' cardiac CTA images. nnU-Net will become an excellent DL technology in cardiac CTA image segmentation tasks.

Capability of CT aortic regurgitant orifice to predict aortic regurgitation severity with cardiovascular magnetic resonance as reference

Abstract Background Regurgitant orifice area (ROA) measurements by cardiac CT have not been extensively compared with a quantitative classification of aortic regurgitation (AR) severity based on regurgitant fraction (RF) by phase-contrast cardiovascular magnetic resonance (PC-CMR) [1–3]. Purpose To evaluate ROA diagnostic accuracy by 256-slice CT for predicting severe AR with PC-CMR as reference. Material and methods We consecutively enrolled 57 patients with AR prior to surgery assessed by echocardiography, PC-CRM, and CT. Mean age 67.3±15.3 (84% males). Cardiac CT data sets were reconstructed at 75–78% of the R-R interval to measure ROA. According to previous data (4), a cut-off value of 33% by PC-CMR defined severe AR. Receiver operating curve (ROC) were calculated to detect the best CT-ROA cut-off to predict severe AR by CMR. Results There were no differences between both groups of AR patients in terms of age, gender, or anthropometric measures. CT-ROA was significantly smaller in patients with RF<33% by PC-CMR (0.24±0.09 vs 0.49±0.22; p<0.001). AR etiology, jet eccentricity, ascending aorta diameters and ejection fraction (LVEF) also were not significantly different according to AR-RF group (Table 1). CT-ROA significantly correlated with the RF>33% by PC-CMR (Pearson's correlation coefficient (R)=0,48, p<0.001) (Figure 1A). In the ROC curve analysis to predict significant RF, a CT-ROA cut-off of 0.27 cm2 correctly classified 93% of patients with sensitivity of 97.6% (CI95%:87,7–99,6); specificity of 73.33% (CI95%:48–89); PPV 95,3% (CI95%: 84,5–98,7); NPV 91,7% (CI95%: 64,6% a 98,5%) and area under the curve (AUC) of 0.93 (CI95%: 0.85–1.00; p<0.001) (Figure 1B). Conclusion CT-RAO could be useful to distinguish AR severity determined by PC-CMR with a cut-off value of 0.27 cm2 as best predictor. Funding Acknowledgement Type of funding sources: None.

LMISA: A lightweight multi-modality image segmentation network via domain adaptation using gradient magnitude and shape constraint.

In medical image segmentation, supervised machine learning models trained using one image modality (e.g. computed tomography (CT)) are often prone to failure when applied to another image modality (e.g. magnetic resonance imaging (MRI)) even for the same organ. This is due to the significant intensity variations of different image modalities. In this paper, we propose a novel end-to-end deep neural network to achieve multi-modality image segmentation, where image labels of only one modality (source domain) are available for model training and the image labels for the other modality (target domain) are not available. In our method, a multi-resolution locally normalized gradient magnitude approach is firstly applied to images of both domains for minimizing the intensity discrepancy. Subsequently, a dual task encoder-decoder network including image segmentation and reconstruction is utilized to effectively adapt a segmentation network to the unlabeled target domain. Additionally, a shape constraint is imposed by leveraging adversarial learning. Finally, images from the target domain are segmented, as the network learns a consistent latent feature representation with shape awareness from both domains. We implement both 2D and 3D versions of our method, in which we evaluate CT and MRI images for kidney and cardiac tissue segmentation. For kidney, a public CT dataset (KiTS19, MICCAI 2019) and a local MRI dataset were utilized. The cardiac dataset was from the Multi-Modality Whole Heart Segmentation (MMWHS) challenge 2017. Experimental results reveal that our proposed method achieves significantly higher performance with a much lower model complexity in comparison with other state-of-the-art methods. More importantly, our method is also capable of producing superior segmentation results than other methods for images of an unseen target domain without model retraining. The code is available at GitHub (https://github.com/MinaJf/LMISA) to encourage method comparison and further research.

Deep learning-based medical image segmentation of the aorta using XR-MSF-U-Net

This paper proposes a CT images and MRI segmentation technology of cardiac aorta based on XR-MSF-U-Net model. The purpose of this method is to better analyze the patient's condition, reduce the misdiagnosis and mortality rate of cardiovascular disease in inhabitants, and effectively avoid the subjectivity and unrepeatability of manual segmentation of heart aorta, and reduce the workload of doctors. We implement the X ResNet (XR) convolution module to replace the different convolution kernels of each branch of two-layer convolution XR of common model U-Net, which can make the model extract more useful features more efficiently. Meanwhile, a plug and play attention module integrating multi-scale features Multi-scale features fusion module (MSF) is proposed, which integrates global local and spatial features of different receptive fields to enhance network details to achieve the goal of efficient segmentation of cardiac aorta through CT images and MRI. The model is trained on common cardiac CT images and MRI data sets and tested on our collected data sets to verify the generalization ability of the model. The results show that the proposed XR-MSF-U-Net model achieves a good segmentation effect on CT images and MRI. In the CT data set, the XR-MSF-U-Net model improves 7.99% in key index DSC and reduces 11.01mm in HD compared with the benchmark model U-Net, respectively. In the MRI data set, XR-MSF-U-Net model improves 10.19% and reduces 6.86mm error in key index DSC and HD compared with benchmark model U-Net, respectively. And it is superior to similar models in segmentation effect, proving that this model has significant advantages. This study provides new possibilities for the segmentation of aortic CT images and MRI, improves the accuracy and efficiency of diagnosis, and hopes to provide substantial help for the segmentation of aortic CT images and MRI.

Unsupervised domain adaptive myocardial infarction MRI classification diagnostics model based on target domain confused sample resampling

Inefficient circulatory system due to blockage of blood vessels leads to myocardial infarction and acute blockage. Myocardial infarction is frequently classified and diagnosed in medical treatment using MRI, yet this method is ineffective and prone to error. As a result, there are several implementation scenarios and clinical significance for employing deep learning to develop computer-aided algorithms to aid cardiologists in the routine examination of cardiac MRI. This research uses two distinct domain classifiers to address this issue and achieve domain adaptation between the particular field and the specific part is a problem Current research on environment adaptive systems cannot effectively obtain and apply classification information for unsupervised scenes of target domain images. Insufficient information interchange between specific domains and specific domains is a problem. In this study, two different domain classifiers are used to solve this problem and achieve domain adaption. To effectively mine the source domain images for classification understanding, an unsupervised MRI classification technique for myocardial infarction called CardiacCN is proposed, which relies on adversarial instructions related to the interpolation of confusion specimens in the target domain for the conflict of confusion specimens for the target domain classification task. The experimental results demonstrate that the CardiacCN model in this study performs better on the six domain adaption tasks of the Sunnybrook Cardiac Dataset (SCD) dataset and increases the mean target area myocardial infarction MRI classification accuracy by approximately 1.2 percent. The classification performance of the CardiacCN model on the target domain does not vary noticeably when the temperature-controlled duration hyper-parameter rl falls in the region of 5-30. According to the experimental findings, the CardiacCN model is more resistant to the excitable rl. The CardiacCN model suggested in this research may successfully increase the accuracy of the source domain predictor for the target domain myocardial infarction clinical scanning classification in unsupervised learning, as shown by the visualization analysis infrastructure provision nurture. It is evident from the visualization assessment of embedded features that the CardiacCN model may significantly increase the source domain classifier's accuracy for the target domain's classification of myocardial infarction in clinical scans under unsupervised conditions. To address misleading specimens with the inconsistent classification of target-domain myocardial infarction medical scans, this paper introduces the CardiacCN unsupervised domain adaptive MRI classification model, which relies on adversarial learning associated with resampling target-domain confusion samples. With this technique, implicit image classification information from the target domain is fully utilized, knowledge transfer from the target domain to the specific domain is encouraged, and the classification effect of the myocardial ischemia medical scan is improved in the target domain of the unsupervised scene.

Computed tomography reference dimensions for identification of stented surgical mitral bioprostheses valve size

Selection of the transcatheter heart valve size for a mitral valve-in-valve procedure is based on the type and manufacturer's labelled size. However, accurate information of surgical heart valve (SHV) size may not be available in the patient's medical record. The purpose of this study is to establish reference data for computed tomography (CT) dimensions of commonly used mitral SHV in order to determine the manufacturer's labelled size from a cardiac CT data set. CT datasets of 105 patients with surgical mitral bioprosthesis and available manufacturer labeled datasets were included in the analysis. CT derived valve dimensions were assessed by two observers using multiplanar reformats aligned with the basal sewing ring. A circular region of interest was used in a standardized fashion to minimize influence of image acquisition and reconstruction parameters. Interobserver variability was assessed by Bland-Altman analysis. The CT-derived dimensions were stratified by valve size and type, and SHV properties were demonstrated for 5 common valve types. Variability of measurements was small and inter-observer limits of agreement were narrow. Stratified by SHV type, no overlap was noted for CT-derived dimensions among different SHV sizes . A reference table of CT characteristics of surgical mitral bioprosthesis types was created. The study provides reference CT data for determining the manufacturers' labeled SHV size across a range of commonly used mitral SHVs. The findings will be important to help identify types of surgical mitral bioprosthesis utilizing CT characteristics for patients without SHV size documentation.

GraformerDIR: Graph convolution transformer for deformable image registration

Deformable image registration (DIR) plays an important role in assisting disease diagnosis. The emergence of the Transformer enables the DIR framework to extract long-range dependencies, which relieves the limitations of intrinsic locality caused by convolution operation. However, suffering from the interference of missing or spurious connections, it is a challenging task for Transformer-based methods to capture the high-quality long-range dependencies. In this paper, by staking the graph convolution Transformer (Graformer) layer at the bottom of the feature extraction network, we propose a Graformer-based DIR framework, named GraformerDIR. The Graformer layer is consist of the Graformer module and the Cheby-shev graph convolution module. Among them, the Graformer module is designed to capture high-quality long-range dependencies. Cheby-shev graph convolution module is employed to further enlarge the receptive field. The performance and generalizability of GraformerDIR have been evaluated on publicly available brain datasets including the OASIS, LPBA40, and MGH10 datasets. Compared with VoxelMorph, the GraformerDIR has obtained performance improvements of 4.6% in Dice similarity coefficient (DSC) and 0.055mm in the average symmetric surface distance (ASD) while reducing the non-positive rate of Jacobin determinant (Npr.Jac) index about 60 times on publicly available OASIS dataset. On unseen dataset MGH10, the GraformerDIR has obtained the performance improvements of 4.1% in DSC and 0.084mm in ASD compared with VoxelMorph, which demonstrates the GraformerDIR with better generalizability. The promising performance on the clinical cardiac dataset ACDC indicates the GraformerDIR is practicable. With the advantage of Transformer and graph convolution, the GraformerDIR has obtained comparable performance with the state-of-the-art method VoxelMorph.

Real-time MRI motion estimation through an unsupervised k-space-driven deformable registration network (KS-RegNet)

Purpose. Real-time three-dimensional (3D) magnetic resonance (MR) imaging is challenging because of slow MR signal acquisition, leading to highly under-sampled k-space data. Here, we proposed a deep learning-based, k-space-driven deformable registration network (KS-RegNet) for real-time 3D MR imaging. By incorporating prior information, KS-RegNet performs a deformable image registration between a fully-sampled prior image and on-board images acquired from highly-under-sampled k-space data, to generate high-quality on-board images for real-time motion tracking. Methods. KS-RegNet is an end-to-end, unsupervised network consisting of an input data generation block, a subsequent U-Net core block, and following operations to compute data fidelity and regularization losses. The input data involved a fully-sampled, complex-valued prior image, and the k-space data of an on-board, real-time MR image (MRI). From the k-space data, under-sampled real-time MRI was reconstructed by the data generation block to input into the U-Net core. In addition, to train the U-Net core to learn the under-sampling artifacts, the k-space data of the prior image was intentionally under-sampled using the same readout trajectory as the real-time MRI, and reconstructed to serve an additional input. The U-Net core predicted a deformation vector field that deforms the prior MRI to on-board real-time MRI. To avoid adverse effects of quantifying image similarity on the artifacts-ridden images, the data fidelity loss of deformation was evaluated directly in k-space. Results. Compared with Elastix and other deep learning network architectures, KS-RegNet demonstrated better and more stable performance. The average (±s.d.) DICE coefficients of KS-RegNet on a cardiac dataset for the 5- , 9- , and 13-spoke k-space acquisitions were 0.884 ± 0.025, 0.889 ± 0.024, and 0.894 ± 0.022, respectively; and the corresponding average (±s.d.) center-of-mass errors (COMEs) were 1.21 ± 1.09, 1.29 ± 1.22, and 1.01 ± 0.86 mm, respectively. KS-RegNet also provided the best performance on an abdominal dataset. Conclusion. KS-RegNet allows real-time MRI generation with sub-second latency. It enables potential real-time MR-guided soft tissue tracking, tumor localization, and radiotherapy plan adaptation.

Compressed sensing based dynamic MR image reconstruction by using 3D-total generalized variation and tensor decomposition: k-t TGV-TD

PurposeCompressed Sensing Magnetic Resonance Imaging (CS-MRI) is a promising technique to accelerate dynamic cardiac MR imaging (DCMRI). For DCMRI, the CS-MRI usually exploits image signal sparsity and low-rank property to reconstruct dynamic images from the undersampled k-space data. In this paper, a novel CS algorithm is investigated to improve dynamic cardiac MR image reconstruction quality under the condition of minimizing the k-space recording.MethodsThe sparse representation of 3D cardiac magnetic resonance data is implemented by synergistically integrating 3D total generalized variation (3D-TGV) algorithm and high order singular value decomposition (HOSVD) based Tensor Decomposition, termed k-t TGV-TD method. In the proposed method, the low rank structure of the 3D dynamic cardiac MR data is performed with the HOSVD method, and the localized image sparsity is achieved by the 3D-TGV method. Moreover, the Fast Composite Splitting Algorithm (FCSA) method, combining the variable splitting with operator splitting techniques, is employed to solve the low-rank and sparse problem. Two different cardiac MR datasets (cardiac perfusion and cine MR datasets) are used to evaluate the performance of the proposed method.ResultsCompared with the state-of-art methods, such as k-t SLR, 3D-TGV, HOSVD based tensor decomposition and low-rank plus sparse method, the proposed k-t TGV-TD method can offer improved reconstruction accuracy in terms of higher peak SNR (PSNR) and structural similarity index (SSIM). The proposed k-t TGV-TD method can achieve significantly better and stable reconstruction results than state-of-the-art methods in terms of both PSNR and SSIM, especially for cardiac perfusion MR dataset.ConclusionsThis work proved that the k-t TGV-TD method was an effective sparse representation way for DCMRI, which was capable of significantly improving the reconstruction accuracy with different acceleration factors.

Old and new equations for maximal heart rate prediction in patients with heart failure and reduced ejection fraction on beta-blockers treatment: results from the MECKI score data set.

Predicting maximal heart rate (MHR) in heart failure with reduced ejection fraction (HFrEF) still remains a major concern. In such a context, the Keteyian equation is the only one derived in a HFrEF cohort on optimized β-blockers treatment. Therefore, using the Metabolic Exercise combined with Cardiac and Kidney Indexes (MECKI) data set, we looked for a possible MHR equation, for an external validation of Keteyien formula and, contextually, for accuracy of the historical MHR formulas and their relationship with the HR measured at the anaerobic threshold (AT). Data from 3487 HFrEF outpatients on optimized β-blockers treatment from the MECKI data set were analyzed. Besides excluding all possible confounders, the new equation was derived by using HR data coming from maximal cardiopulmonary exercise test. The simplified derived equation was [109-(0.5*age) + (0.5*HR rest) + (0.2*LVEF)-(5 if haemoglobin <11 g/dL)]. The R2 and the standard error of the estimate were 0.24 and 17.5 beats min-1 with a mean absolute percentage error (MAPE) = 11.9%. The Keteyian equation had a slightly higher MAPE = 12.3%. Conversely, the Fox and Tanaka equations showed extremely higher MAPE values. The range 75-80% of MHR according to the new and the Keteyian equations was the most accurate in identifying the HR at the AT (MAPEs = 11.3-11.6%). The derived equation to estimate the MHR in HFrEF patients, by accounting also for the systolic dysfunction degree and anaemia, improved slightly the Keteyian formula. Both formulas might be helpful in identifying the true maximal effort during an exercise test and the intensity domain during a rehabilitation programme.