Benchmarking framework for myocardial tracking and deformation algorithms: an open access database

Biventricular finite element modeling of the fetal heart in health and during critical aortic stenosis

Finite Element simulations are a robust way of investigating cardiac biomechanics. To date, it has only been performed with the left ventricle (LV) alone for fetal hearts, even though results are likely different with biventricular (BiV) simulations. In this research, we conduct BiV simulations of the fetal heart based on 4D echocardiography images to show that it can capture the biomechanics of the normal healthy fetal heart, as well as those of fetal aortic stenosis better than the LV alone simulations. We found that performing LV alone simulations resulted in overestimation of LV stresses and pressures, compared to BiV simulations. Interestingly, inserting a compliance between the LV and right ventricle (RV) in the lumped parameter model of the LV only simulation effectively resolved these overestimations, demonstrating that the septum could be considered to play a LV-RV pressure communication role. However, stresses and strains spatial patterns remained altered from BiV simulations after the addition of the compliance. The BiV simulations corroborated previous studies in showing disease effects on the LV, where fetal aortic stenosis (AS) drastically elevated LV pressures and reduced strains and stroke volumes, which were moderated down with the addition of mitral regurgitation (MR). However, BiV simulations enabled an evaluation of the RV as well, where we observed that effects of the AS and MR on pressures and stroke volumes were generally much smaller and less consistent. The BiV simulations also enabled investigations of septal dynamics, which showed a rightward shift with AS, and partial restoration with MR. Interestingly, AS tended to enhance RV stroke volume, but MR moderated that down.

DeepMesh: Mesh-Based Cardiac Motion Tracking Using Deep Learning

3D motion estimation from cine cardiac magnetic resonance (CMR) images is important for the assessment of cardiac function and the diagnosis of cardiovascular diseases. Current state-of-the art methods focus on estimating dense pixel-/voxel-wise motion fields in image space, which ignores the fact that motion estimation is only relevant and useful within the anatomical objects of interest, e.g., the heart. In this work, we model the heart as a 3D mesh consisting of epi- and endocardial surfaces. We propose a novel learning framework, DeepMesh, which propagates a template heart mesh to a subject space and estimates the 3D motion of the heart mesh from CMR images for individual subjects. In DeepMesh, the heart mesh of the end-diastolic frame of an individual subject is first reconstructed from the template mesh. Mesh-based 3D motion fields with respect to the end-diastolic frame are then estimated from 2D short- and long-axis CMR images. By developing a differentiable mesh-to-image rasterizer, DeepMesh is able to leverage 2D shape information from multiple anatomical views for 3D mesh reconstruction and mesh motion estimation. The proposed method estimates vertex-wise displacement and thus maintains vertex correspondences between time frames, which is important for the quantitative assessment of cardiac function across different subjects and populations. We evaluate DeepMesh on CMR images acquired from the UK Biobank. We focus on 3D motion estimation of the left ventricle in this work. Experimental results show that the proposed method quantitatively and qualitatively outperforms other image-based and mesh-based cardiac motion tracking methods.

Target-oriented deep learning-based image registration with individualized test-time adaptation

BACKGROUND

A classic approach in medical image registration is to formulate an optimization problem based on the image pair of interest, and seek a deformation vector field (DVF) to minimize the corresponding objective, often iteratively. It has a clear focus on the targeted pair, but is typically slow. In contrast, more recent deep-learning-based registration offers a much faster alternative and can benefit from data-driven regularization. However, learning is a process to "fit" the training cohort, whose image or motion characteristics or both may differ from the pair of images to be tested, which is the ultimate goal of registration. Therefore, generalization gap poses a high risk with direct inference alone.

PURPOSE

In this study, we propose an individualized adaptation to improve test sample targeting, to achieve a synergy of efficiency and performance in registration.

METHODS

Using a previously developed network with an integrated motion representation prior module as the implementation backbone, we propose to adapt the trained registration network further for image pairs at test time to optimize the individualized performance. The adaptation method was tested against various characteristics shifts caused by cross-protocol, cross-platform, and cross-modality, with test evaluation performed on lung CBCT, cardiac MRI, and lung MRI, respectively.

RESULTS

Landmark-based registration errors and motion-compensated image enhancement results demonstrated significantly improved test registration performance from our method, compared to tuned classic B-spline registration and network solutions without adaptation.

CONCLUSIONS

We have developed a method to synergistically combine the effectiveness of pre-trained deep network and the target-centric perspective of optimization-based registration to improve performance on individual test data.

WarpPINN: Cine-MR image registration with physics-informed neural networks

The diagnosis of heart failure usually includes a global functional assessment, such as ejection fraction measured by magnetic resonance imaging. However, these metrics have low discriminate power to distinguish different cardiomyopathies, which may not affect the global function of the heart. Quantifying local deformations in the form of cardiac strain can provide helpful information, but it remains a challenge. In this work, we introduce WarpPINN, a physics-informed neural network to perform image registration to obtain local metrics of heart deformation. We apply this method to cine magnetic resonance images to estimate the motion during the cardiac cycle. We inform our neural network of the near-incompressibility of cardiac tissue by penalizing the Jacobian of the deformation field. The loss function has two components: an intensity-based similarity term between the reference and the warped template images, and a regularizer that represents the hyperelastic behavior of the tissue. The architecture of the neural network allows us to easily compute the strain via automatic differentiation to assess cardiac activity. We use Fourier feature mappings to overcome the spectral bias of neural networks, allowing us to capture discontinuities in the strain field. The algorithm is tested on synthetic examples and on a cine SSFP MRI benchmark of 15 healthy volunteers, where it is trained to learn the deformation mapping of each case. We outperform current methodologies in landmark tracking and provide physiological strain estimations in the radial and circumferential directions. WarpPINN provides precise measurements of local cardiac deformations that can be used for a better diagnosis of heart failure and can be used for general image registration tasks. Source code is available at https://github.com/fsahli/WarpPINN.

Multi-modality cardiac image computing: A survey

Multi-modality cardiac imaging plays a key role in the management of patients with cardiovascular diseases. It allows a combination of complementary anatomical, morphological and functional information, increases diagnosis accuracy, and improves the efficacy of cardiovascular interventions and clinical outcomes. Fully-automated processing and quantitative analysis of multi-modality cardiac images could have a direct impact on clinical research and evidence-based patient management. However, these require overcoming significant challenges including inter-modality misalignment and finding optimal methods to integrate information from different modalities. This paper aims to provide a comprehensive review of multi-modality imaging in cardiology, the computing methods, the validation strategies, the related clinical workflows and future perspectives. For the computing methodologies, we have a favored focus on the three tasks, i.e., registration, fusion and segmentation, which generally involve multi-modality imaging data, either combining information from different modalities or transferring information across modalities. The review highlights that multi-modality cardiac imaging data has the potential of wide applicability in the clinic, such as trans-aortic valve implantation guidance, myocardial viability assessment, and catheter ablation therapy and its patient selection. Nevertheless, many challenges remain unsolved, such as missing modality, modality selection, combination of imaging and non-imaging data, and uniform analysis and representation of different modalities. There is also work to do in defining how the well-developed techniques fit in clinical workflows and how much additional and relevant information they introduce. These problems are likely to continue to be an active field of research and the questions to be answered in the future.

Effects of spatial and temporal resolution on cardiovascular magnetic resonance feature tracking measurements using a simple realistic numerical phantom

OBJECTIVES

To develop a single-slice numerical phantom with known myocardial motion, at several temporal and in-plane spatial resolutions, for testing and comparison of Cardiovascular Magnetic Resonance (CMR) feature tracking (FT) software.

METHODS

The phantom was developed based on CMR acquisitions of one volunteer (acquired cine, tagging cine, T1 map, T2 map, proton density weighted image). The numerical MRI simulator JEMRIS was used, and the phantom was generated at several in-plane spatial resolutions (1.4 × 1.4 mm2 to 3.0 × 3.0 mm2) and temporal resolutions (20 to 40 cardiac phases). Two feature tracking software packages were tested: Medical Image Tracking Toolbox (MITT) and two versions of cvi42 (v5.3.8 and v5.13.7). The effect of resolution on strain results was investigated with reference to ground-truth radial and circumferential strain.

RESULTS

Peak radial strain was consistently undermeasured more for cvi42 v5.13.7 than for v5.3.8. Increased pixel size produced a trend of increased difference from ground-truth peak strain, with the largest changes for cvi42 obtained using v5.13.7 between 1.4 × 1.4 mm2 and 3.0 × 3.0 mm2, at 9.17 percentage points (radial) and 8.42 percentage points (circumferential).

CONCLUSIONS

The results corroborate the presence of intervendor differences in feature tracking results and show the magnitude of strain differences between software versions.

ADVANCES IN KNOWLEDGE

This study shows how temporal and in-plane spatial resolution can affect feature tracking with reference to the ground-truth strain of a numerical phantom. Results reaffirm the need for numerical phantom development for the validation and testing of FT software.

Deformable cardiac surface tracking by adaptive estimation algorithms

This study presents a particle filter based framework to track cardiac surface from a time sequence of single magnetic resonance imaging (MRI) slices with the future goal of utilizing the presented framework for interventional cardiovascular magnetic resonance procedures, which rely on the accurate and online tracking of the cardiac surface from MRI data. The framework exploits a low-order parametric deformable model of the cardiac surface. A stochastic dynamic system represents the cardiac surface motion. Deformable models are employed to introduce shape prior to control the degree of the deformations. Adaptive filters are used to model complex cardiac motion in the dynamic model of the system. Particle filters are utilized to recursively estimate the current state of the system over time. The proposed method is applied to recover biventricular deformations and validated with a numerical phantom and multiple real cardiac MRI datasets. The algorithm is evaluated with multiple experiments using fixed and varying image slice planes at each time step. For the real cardiac MRI datasets, the average root-mean-square tracking errors of 2.61 mm and 3.42 mm are reported respectively for the fixed and varying image slice planes. This work serves as a proof-of-concept study for modeling and tracking the cardiac surface deformations via a low-order probabilistic model with the future goal of utilizing this method for the targeted interventional cardiac procedures under MR image guidance. For the real cardiac MRI datasets, the presented method was able to track the points-of-interests located on different sections of the cardiac surface within a precision of 3 pixels. The analyses show that the use of deformable cardiac surface tracking algorithm can pave the way for performing precise targeted intracardiac ablation procedures under MRI guidance. The main contributions of this work are twofold. First, it presents a framework for the tracking of whole cardiac surface from a time sequence of single image slices. Second, it employs adaptive filters to incorporate motion information in the tracking of nonrigid cardiac surface motion for temporal coherence.

Contribution of Ventricular Motion and Sampling Location to Discrepancies in Two-Dimensional Versus Three-Dimensional Fetal Ventricular Strain Measures

BACKGROUND

Echocardiographic quantification of fetal cardiac strain is important to evaluate function and the need for intervention, with both two-dimensional (2D) and three-dimensional (3D) strain measurements currently feasible. However, discrepancies between 2D and 3D measurements have been reported, the etiologies of which are unclear. This study sought to determine the etiologies of the differences between 2D and 3D strain measurements.

METHODS

A validated cardiac motion-tracking algorithm was used on 3D cine ultrasound images acquired in 26 healthy fetuses. Both 2D and 3D myocardial strain quantifications were performed on each image set for controlled comparisons. Finite element modeling of 2 left ventricle (LV) models with minor geometrical differences were performed with various helix angle configurations for validating image processing results.

RESULTS

Three-dimensional longitudinal strain (LS) was significantly lower than 2D LS for the LV free wall and septum but not for the right ventricular (RV) free wall, while 3D circumferential strain (CS) was significantly higher than 2D CS for the LV, RV, and septum. The LS discrepancy was due to 2D long-axis imaging not capturing the out-of-plane motions associated with LV twist, while the CS discrepancy was due to the systolic motion of the heart toward the apex that caused out-of-plane motions in 2D short-axis imaging. A timing mismatch between the occurrences of peak longitudinal and circumferential dimensions caused a deviation in zero-strain referencing between 2D and 3D strain measurements, contributing to further discrepancies between the 2.

CONCLUSIONS

Mechanisms for discrepancies between 2D and 3D strain measurements in fetal echocardiography were identified, and inaccuracies associated with 2D strains were highlighted. Understanding of this mechanism is useful and important for future standardization of fetal cardiac strain measurements, which we propose to be important in view of large discrepancies in measured values in the literature.

Generative myocardial motion tracking via latent space exploration with biomechanics-informed prior

Myocardial motion and deformation are rich descriptors that characterize cardiac function. Image registration, as the most commonly used technique for myocardial motion tracking, is an ill-posed inverse problem which often requires prior assumptions on the solution space. In contrast to most existing approaches which impose explicit generic regularization such as smoothness, in this work we propose a novel method that can implicitly learn an application-specific biomechanics-informed prior and embed it into a neural network-parameterized transformation model. Particularly, the proposed method leverages a variational autoencoder-based generative model to learn a manifold for biomechanically plausible deformations. The motion tracking then can be performed via traversing the learnt manifold to search for the optimal transformations while considering the sequence information. The proposed method is validated on three public cardiac cine MRI datasets with comprehensive evaluations. The results demonstrate that the proposed method can outperform other approaches, yielding higher motion tracking accuracy with reasonable volume preservation and better generalizability to varying data distributions. It also enables better estimates of myocardial strains, which indicates the potential of the method in characterizing spatiotemporal signatures for understanding cardiovascular diseases.

Quantification of left ventricular strain and torsion by joint analysis of 3D tagging and cine MR images

Cardiovascular magnetic resonance (CMR) imaging is the gold standard for the non-invasive assessment of left-ventricular (LV) function. Prognostic value of deformation metrics extracted directly from regular SSFP CMR images has been shown by numerous studies in the clinical setting, but with some limitations to detect torsion of the myocardium. Tagged CMR introduces trackable features in the myocardium that allow for the assessment of local myocardial deformation, including torsion; it is, however, limited in the quantification of radial strain, which is a decisive metric for assessing the contractility of the heart. In order to improve SSFP-only and tagged-only approaches, we propose to combine the advantages of both image types by fusing global shape motion obtained from SSFP images with the local deformation obtained from tagged images. To this end, tracking is first performed on SSFP images, and subsequently, the resulting motion is utilized to mask and track tagged data. Our implementation is based on a recent finite element-based motion tracking tool with mechanical regularization. Joint SSFP and tagged images registration performance is assessed based on deformation metrics including LV strain and twist using human and in-house porcine datasets. Results show that joint analysis of SSFP and 3DTAG images provides better quantification of LV strain and twist as either data source alone.

MulViMotion: Shape-Aware 3D Myocardial Motion Tracking From Multi-View Cardiac MRI

Recovering the 3D motion of the heart from cine cardiac magnetic resonance (CMR) imaging enables the assessment of regional myocardial function and is important for understanding and analyzing cardiovascular disease. However, 3D cardiac motion estimation is challenging because the acquired cine CMR images are usually 2D slices which limit the accurate estimation of through-plane motion. To address this problem, we propose a novel multi-view motion estimation network (MulViMotion), which integrates 2D cine CMR images acquired in short-axis and long-axis planes to learn a consistent 3D motion field of the heart. In the proposed method, a hybrid 2D/3D network is built to generate dense 3D motion fields by learning fused representations from multi-view images. To ensure that the motion estimation is consistent in 3D, a shape regularization module is introduced during training, where shape information from multi-view images is exploited to provide weak supervision to 3D motion estimation. We extensively evaluate the proposed method on 2D cine CMR images from 580 subjects of the UK Biobank study for 3D motion tracking of the left ventricular myocardium. Experimental results show that the proposed method quantitatively and qualitatively outperforms competing methods.

A systematic review of multi-slice and multi-frame descriptors in cardiac MRI exams

Computer-Aided Diagnosis systems have been developed to help medical professional in their decision making routines towards a more accurate diagnosis. These systems process medical exams such as Magnetic Resonance (MRI) in order to quantify meaningful features. These can be used with similarity-measuring techniques in a Content-Based Image Retrieval context, or inputted into a machine learning classifier in order to support early disease detection. For cardiac MRIs, single slice descriptors have been proposed in the two-dimensional domain, shape descriptors have been proposed in the three-dimensional domain, and previous reviews have mapped these two descriptor categories. Nonetheless, no systematic review on these descriptors have looked at full cardiac MRI images sets. We have reviewed the literature by searching for descriptors that consider the whole slice set (multi-slice) or frames (multi-frame) in cardiac MRI exams. We discuss descriptors and techniques, the datasets that were used, and the different evaluation metrics. Finally, we highlight literature gaps and research opportunities.

Characterization of motion patterns by a spatio-temporal saliency descriptor in cardiac cine MRI

BACKGROUND AND OBJECTIVE

Abnormalities of the heart motion reveal the presence of a disease. However, a quantitative interpretation of the motion is still a challenge due to the complex dynamics of the heart. This work proposes a quantitative characterization of regional cardiac motion patterns in cine magnetic resonance imaging (MRI) by a novel spatio-temporal saliency descriptor.

METHOD

The strategy starts by dividing the cardiac sequence into a progression of scales which are in due turn mapped to a feature space of regional orientation changes, mimicking the multi-resolution decomposition of oriented primitive changes of visual systems. These changes are estimated as the difference between a particular time and the rest of the sequence. This decomposition is then temporarily and regionally integrated for a particular orientation and then for the set of different orientations. A final spatio-temporal 4D saliency map is obtained as the summation of the previously integrated information for the available scales. The saliency dispersion of this map was computed in standard cardiac locations as a measure of the regional motion pattern and was applied to discriminate control and hypertrophic cardiomyopathy (HCM) subjects during the diastolic phase.

RESULTS

Salient motion patterns were estimated from an experimental set, which consisted of 3D sequences acquired by MRI from 108 subjects (33 control, 35 HCM, 20 dilated cardiomyopathy (DCM), and 20 myocardial infarction (MINF) from heterogeneous datasets). HCM and control subjects were classified by an SVM that learned the salient motion patterns estimated from the presented strategy, by achieving a 94% AUC. In addition, statistical differences (test t-student, p<0.05) were found among groups of disease in the septal and anterior ventricular segments at both the ED and ES, with salient motion characteristics aligned with existing knowledge on the diseases.

CONCLUSIONS

Regional wall motion abnormality in the apical, anterior, basal, and inferior segments was associated with the saliency dispersion in HCM, DCM, and MINF compared to healthy controls during the systolic and diastolic phases. This saliency analysis may be used to detect subtle changes in heart function.

DeepStrain Evidence of Asymptomatic Left Ventricular Diastolic and Systolic Dysfunction in Young Adults With Cardiac Risk Factors

Purpose

To evaluate if a fully-automatic deep learning method for myocardial strain analysis based on magnetic resonance imaging (MRI) cine images can detect asymptomatic dysfunction in young adults with cardiac risk factors.

Methods

An automated workflow termed DeepStrain was implemented using two U-Net models for segmentation and motion tracking. DeepStrain was trained and tested using short-axis cine-MRI images from healthy subjects and patients with cardiac disease. Subsequently, subjects aged 18–45 years were prospectively recruited and classified among age- and gender-matched groups: risk factor group (RFG) 1 including overweight without hypertension or type 2 diabetes; RFG2 including hypertension without type 2 diabetes, regardless of overweight; RFG3 including type 2 diabetes, regardless of overweight or hypertension. Subjects underwent cardiac short-axis cine-MRI image acquisition. Differences in DeepStrain-based left ventricular global circumferential and radial strain and strain rate among groups were evaluated.

Results

The cohort consisted of 119 participants: 30 controls, 39 in RFG1, 30 in RFG2, and 20 in RFG3. Despite comparable (>0.05) left-ventricular mass, volumes, and ejection fraction, all groups (RFG1, RFG2, RFG3) showed signs of asymptomatic left ventricular diastolic and systolic dysfunction, evidenced by lower circumferential early-diastolic strain rate (<0.05, <0.001, <0.01), and lower septal circumferential end-systolic strain (<0.001, <0.05, <0.001) compared with controls. Multivariate linear regression showed that body surface area correlated negatively with all strain measures (<0.01), and mean arterial pressure correlated negatively with early-diastolic strain rate (<0.01).

Conclusion

DeepStrain fully-automatically provided evidence of asymptomatic left ventricular diastolic and systolic dysfunction in asymptomatic young adults with overweight, hypertension, and type 2 diabetes risk factors.

Inter-phase 4D Cardiac MRI Registration with a Motion Prior Derived from CTA

OBJECTIVE

Registration between phases in 4D cardiac MRI is essential for reconstructing high-quality images and appreciating the dynamics. Complex motion and limited image quality make it challenging to design regularization functionals. We propose to introduce a motion representation model (MRM) into a registration network to impose customized, site-specific, and spatially variant prior for cardiac motion.

METHODS

We propose a novel approach to regularize deep registration with a DVF representation model using CTA. In the form of a convolutional auto-encoder, the MRM was trained to capture the spatially variant pattern of feasible DVF Jacobian. The CTA-derived MRM was then incorporated into an unsupervised network to facilitate MRI registration. In the experiment, 10 CTAs were used to derive the MRM. The method was tested on 10 0.35T scans in long-axis view with manual segmentation and 15 3T scans in short-axis view with tagging-based landmarks.

RESULTS

Introducing the MRM improved registration accuracy and achieved 2.23, 7.21, and 4.42mm 80% Hausdorff distance on left ventricle, right ventricle, and pulmonary artery, respectively, and 2.23mm landmark registration error. The results were comparable to carefully tuned SimpleElastix, but reduced the registration time from 40 to 0.02s. The MRM presented good robustness to different DVF sample generation methods.

CONCLUSION

The model enjoys high accuracy as meticulously tuned optimization model and the efficiency of deep networks.

SIGNIFICANCE

The method enables model to go beyond the quality limitation of MRI. The robustness to training DVF generation scheme makes the method attractive to adapting to the available data and software resources in various clinics.

In-silico study of accuracy and precision of left-ventricular strain quantification from 3D tagged MRI

Cardiac Magnetic Resonance Imaging (MRI) allows quantifying myocardial tissue deformation and strain based on the tagging principle. In this work, we investigate accuracy and precision of strain quantification from synthetic 3D tagged MRI using equilibrated warping. To this end, synthetic biomechanical left-ventricular tagged MRI data with varying tag distance, spatial resolution and signal-to-noise ratio (SNR) were generated and processed to quantify errors in radial, circumferential and longitudinal strains relative to ground truth. Results reveal that radial strain is more sensitive to image resolution and noise than the other strain components. The study also shows robustness of quantifying circumferential and longitudinal strain in the presence of geometrical inconsistencies of 3D tagged data. In conclusion, our study points to the need for higher-resolution 3D tagged MRI than currently available in practice in order to achieve sufficient accuracy of radial strain quantification.

Full cardiac cycle asynchronous temporal compounding of 3D echocardiography images

It is important to improve echocardiography image quality, because the accuracy of echocardiographic assessment and diagnosis relies on image quality. Previous work on 2D temporal image compounding for image frames with matching cardiac phases (synchronous), and for temporally neighbouring image frames (asynchronous) over small ranges of time frames showed good improvement to image quality. Here, we extend this by performing asynchronous temporal compounding to echocardiographic images in 3D, involving all frames within a cardiac cycle, via a robust 3D cardiac motion estimation algorithm to describe the large image deformations. After compounding, the images can be reanimated via the motion model. Various methods of fusing image frames together are tested, including mean, max, and wavelet methods, and outlier rejection algorithms. The compounding algorithm is applied on 3D human adult, porcine adolescent, and human fetal echocardiography images. Results show significant improvements to contrast-to-noise ratio (CNR) and boundary clarity, and significantly decreased variability in manual quantification of cardiac chamber volumes after compounding. Interestingly, compounding can extend the field of view of the echo images, by reconstructing cardiac structures that momentarily exceeded the field of view, using the motion estimation algorithm to calculate their locations outside the field of view during these time periods. Although all compounding methods provide general improvements, the mean method led to blurred boundaries, while the max methods led to high variability of CNR. Outlier rejection algorithms were found to be useful in addressing these weaknesses.

Using synthetic data generation to train a cardiac motion tag tracking neural network

A CNN based method for cardiac MRI tag tracking was developed and validated. A synthetic data simulator was created to generate large amounts of training data using natural images, a Bloch equation simulation, a broad range of tissue properties, and programmed ground-truth motion. The method was validated using both an analytical deforming cardiac phantom and in vivo data with manually tracked reference motion paths. In the analytical phantom, error was investigated relative to SNR, and accurate results were seen for SNR>10 (displacement error <0.3 mm). Excellent agreement was seen in vivo for tag locations (mean displacement difference = -0.02 pixels, 95% CI [-0.73, 0.69]) and calculated cardiac circumferential strain (mean difference = 0.006, 95% CI [-0.012, 0.024]). Automated tag tracking with a CNN trained on synthetic data is both accurate and precise.

DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics

Myocardial strain analysis from cinematic magnetic resonance imaging (cine-MRI) data provides a more thorough characterization of cardiac mechanics than volumetric parameters such as left-ventricular ejection fraction, but sources of variation including segmentation and motion estimation have limited its wider clinical use. We designed and validated a fast, fully-automatic deep learning (DL) workflow to generate both volumetric parameters and strain measures from cine-MRI data consisting of segmentation and motion estimation convolutional neural networks. The final motion network design, loss function, and associated hyperparameters are the result of a thorough ad hoc implementation that we carefully planned specific for strain quantification, tested, and compared to other potential alternatives. The optimal configuration was trained using healthy and cardiovascular disease (CVD) subjects (n = 150). DL-based volumetric parameters were correlated (>0.98) and without significant bias relative to parameters derived from manual segmentations in 50 healthy and CVD test subjects. Compared to landmarks manually-tracked on tagging-MRI images from 15 healthy subjects, landmark deformation using DL-based motion estimates from paired cine-MRI data resulted in an end-point-error of 2.9 ± 1.5 mm. Measures of end-systolic global strain from these cine-MRI data showed no significant biases relative to a tagging-MRI reference method. On 10 healthy subjects, intraclass correlation coefficient for intra-scanner repeatability was good to excellent (>0.75) for all global measures and most polar map segments. In conclusion, we developed and evaluated the first end-to-end learning-based workflow for automated strain analysis from cine-MRI data to quantitatively characterize cardiac mechanics of healthy and CVD subjects.

Evaluation of strain averaging area and strain estimation errors in a spheroidal left ventricular model using synthetic image data and speckle tracking

BACKGROUND

In majority of studies on speckle tracking echocardiography (STE) the strain estimates are averaged over large areas of the left ventricle. This may impair the diagnostic capability of the STE in the case of e.g. local changes of the cardiac contractility. This work attempts to evaluate, how far one can reduce the averaging area, without sacrificing the estimation accuracy that could be important from the clinical point of view.

METHODS

Synthetic radio frequency (RF) data of a spheroidal left ventricular (LV) model were generated using FIELD II package and meshes obtained from finite element method (FEM) simulation. The apical two chamber (A2C) view and the mid parasternal short axis view (pSAXM) were simulated. The sector encompassed the entire cross-section (full view) of the LV model or its part (partial view). The wall segments obtained according to the American Heart Association (AHA17) were divided into subsegments of area decreasing down to 3 mm2. Longitudinal, circumferential and radial strain estimates, obtained using a hierarchical block-matching method, were averaged over these subsegments. Estimation accuracy was assessed using several error measures, making most use of the prediction of the maximal relative error of the strain estimate obtained using the FEM derived reference. Three limits of this predicted maximal error were studied, namely 16.7%, 33% and 66%. The smallest averaging area resulting in the strain estimation error below one of these limits was considered the smallest allowable averaging area (SAAA) of the strain estimation.

RESULTS

In all AHA17 segments, using the A2C projection, the SAAA ensuring maximal longitudinal strain estimates error below 33% was below 3 mm2, except for the segment no 17 where it was above 278 mm2. The SAAA ensuring maximal circumferential strain estimates error below 33% depended on the AHA17 segment position within the imaging sector and view type and ranged from below 3-287 mm2. The SAAA ensuring maximal radial strain estimates error below 33% obtained in the pSAXM projection was not less than 287 mm2. The SAAA values obtained using other maximal error limits differ from SAAA values observed for the 33% error limit only in limited number of cases. SAAA decreased when using maximal error limit equal to 66% in these cases. The use of the partial view (narrow sector) resulted in a decrease of the SAAA.

CONCLUSIONS

The SAAA varies strongly between strain components. In a vast part of the LV model wall in the A2C view the longitudinal strain could be estimated using SAAA below 3 mm2, which is smaller than the averaging area currently used in clinic, thus with a higher resolution. The SAAA of the circumferential strain estimation strongly depends on the position of the region of interest and the parameters of the acquisition. The SAAA of the radial strain estimation takes the highest values. The use of a narrow sector could increase diagnostic capabilities of 2D STE.

Identifying Myocardial Infarction Using Hierarchical Template Matching-Based Myocardial Strain: Algorithm Development and Usability Study

Background

Myocardial infarction (MI; location and extent of infarction) can be determined by late enhancement cardiac magnetic resonance (CMR) imaging, which requires the injection of a potentially harmful gadolinium-based contrast agent (GBCA). Alternatively, emerging research in the area of myocardial strain has shown potential to identify MI using strain values.

Objective

This study aims to identify the location of MI by developing an applied algorithmic method of circumferential strain (CS) values, which are derived through a novel hierarchical template matching (HTM) method.

Methods

HTM-based CS H-spread from end-diastole to end-systole was used to develop an applied method. Grid-tagging magnetic resonance imaging was used to calculate strain values in the left ventricular (LV) myocardium, followed by the 16-segment American Heart Association model. The data set was used with k-fold cross-validation to estimate the percentage reduction of H-spread among infarcted and noninfarcted LV segments. A total of 43 participants (38 MI and 5 healthy) who underwent CMR imaging were retrospectively selected. Infarcted segments detected by using this method were validated by comparison with late enhancement CMR, and the diagnostic performance of the applied algorithmic method was evaluated with a receiver operating characteristic curve test.

Results

The H-spread of the CS was reduced in infarcted segments compared with noninfarcted segments of the LV. The reductions were 30% in basal segments, 30% in midventricular segments, and 20% in apical LV segments. The diagnostic accuracy of detection, using the reported method, was represented by area under the curve values, which were 0.85, 0.82, and 0.87 for basal, midventricular, and apical slices, respectively, demonstrating good agreement with the late-gadolinium enhancement–based detections.

Conclusions

The proposed applied algorithmic method has the potential to accurately identify the location of infarcted LV segments without the administration of late-gadolinium enhancement. Such an approach adds the potential to safely identify MI, potentially reduce patient scanning time, and extend the utility of CMR in patients who are contraindicated for the use of GBCA.

Harnessing Machine Intelligence in Automatic Echocardiogram Analysis: Current Status, Limitations, and Future Directions

Echocardiography (echo) is a critical tool in diagnosing various cardiovascular diseases. Despite its diagnostic and prognostic value, interpretation and analysis of echo images are still widely performed manually by echocardiographers. A plethora of algorithms has been proposed to analyze medical ultrasound data using signal processing and machine learning techniques. These algorithms provided opportunities for developing automated echo analysis and interpretation systems. The automated approach can significantly assist in decreasing the variability and burden associated with manual image measurements. In this paper, we review the state-of-the-art automatic methods for analyzing echocardiography data. Particularly, we comprehensively and systematically review existing methods of four major tasks: echo quality assessment, view classification, boundary segmentation, and disease diagnosis. Our review covers three echo imaging modes, which are B-mode, M-mode, and Doppler. We also discuss the challenges and limitations of current methods and outline the most pressing directions for future research. In summary, this review presents the current status of automatic echo analysis and discusses the challenges that need to be addressed to obtain robust systems suitable for efficient use in clinical settings or point-of-care testing.

Spatiotemporal Free-Form Registration Method Assisted by a Minimum Spanning Tree During Discontinuous Transformations

The sliding motion along the boundaries of discontinuous regions has been actively studied in B-spline free-form deformation framework. This study focusses on the sliding motion for a velocity field-based 3D+t registration. The discontinuity of the tangent direction guides the deformation of the object region, and a separate control of two regions provides a better registration accuracy. The sliding motion under the velocity field-based transformation is conducted under the [Formula: see text]-Rényi entropy estimator using a minimum spanning tree (MST) topology. Moreover, a new topology changing method of the MST is proposed. The topology change is performed as follows: inserting random noise, constructing the MST, and removing random noise while preserving a local connection consistency of the MST. This random noise process (RNP) prevents the [Formula: see text]-Rényi entropy-based registration from degrading in sliding motion, because the RNP creates a small disturbance around special locations. Experiments were performed using two publicly available datasets: the DIR-Lab dataset, which consists of 4D pulmonary computed tomography (CT) images, and a benchmarking framework dataset for cardiac 3D ultrasound. For the 4D pulmonary CT images, RNP produced a significantly improved result for the original MST with sliding motion (p<0.05). For the cardiac 3D ultrasound dataset, only a discontinuity-based registration indicated activity of the RNP. In contrast, the single MST without sliding motion did not show any improvement. These experiments proved the effectiveness of the RNP for sliding motion.

CardIAc: an open-source application for myocardial strain analysis

PURPOSE

This paper presents CardIAc, an open-source application designed as an alternative to commercial software for left ventricle myocardial strain quantification in short-axis cardiac magnetic resonance images. The aim is to provide a useful extension for myocardial strain analysis that can be easily adapted to incorporate different strategies of motion tracking to improve the strain accuracy. In this way, users with programming skills can easily modify the code and adjust the program's performance according to their own scientific or clinical requirements. The software is intended for research and clinical use is not advised.

METHODS

CardIAc was developed as a 3D Slicer extension for an easy installation and usability. The main contribution of this article is to provide a general workflow, going from data and segmentation loading, 3D heart modeling, analysis and several options for visualization of the myocardial strain.

RESULTS

CardIAc strain feature was evaluated on a public dataset (Cardiac Motion Analysis Challenge-STACOM 2011) of 15 volunteers, and a synthetic one generated from this real dataset. Results on the real dataset show that cardIAc achieves suitable accuracy for myocardial motion estimation with a median error of 3.66 mm. In particular, global strain curves show strong correlation with the bibliography for healthy patients and similar approaches. On the other hand, results on the synthetic dataset show a mean global error of 4.07%, 7.76% and 8.18% for circumferential, radial and longitudinal strain.

CONCLUSION

This paper introduces a new open-source application for strain analysis distributed under a BSD-style open-source license. Results demonstrate the capability and merits of the proposed application for strain analysis.

Cardiac motion estimation from medical images: a regularisation framework applied on pairwise image registration displacement fields

Accurate cardiac motion estimation from medical images such as ultrasound is important for clinical evaluation. We present a novel regularisation layer for cardiac motion estimation that will be applied after image registration and demonstrate its effectiveness. The regularisation utilises a spatio-temporal model of motion, b-splines of Fourier, to fit to displacement fields from pairwise image registration. In the process, it enforces spatial and temporal smoothness and consistency, cyclic nature of cardiac motion, and better adherence to the stroke volume of the heart. Flexibility is further given for inclusion of any set of registration displacement fields. The approach gave high accuracy. When applied to human adult Ultrasound data from a Cardiac Motion Analysis Challenge (CMAC), the proposed method is found to have 10% lower tracking error over CMAC participants. Satisfactory cardiac motion estimation is also demonstrated on other data sets, including human fetal echocardiography, chick embryonic heart ultrasound images, and zebrafish embryonic microscope images, with the average Dice coefficient between estimation motion and manual segmentation at 0.82-0.87. The approach of performing regularisation as an add-on layer after the completion of image registration is thus a viable option for cardiac motion estimation that can still have good accuracy. Since motion estimation algorithms are complex, dividing up regularisation and registration can simplify the process and provide flexibility. Further, owing to a large variety of existing registration algorithms, such an approach that is usable on any algorithm may be useful.

In vivo estimation of normal left ventricular stiffness and contractility based on routine cine MR acquisition

Post-myocardial infarction remodeling process is known to alter the mechanical properties of the heart. Biomechanical parameters, such as tissue stiffness and contractility, would be useful for clinicians to better assess the severity of the diseased heart. However, these parameters are difficult to obtain in the current clinical practice. In this paper, we estimated subject-specific in vivo myocardial stiffness and contractility from 21 healthy volunteers, based on left ventricle models constructed from data acquired from routine cardiac MR acquisition only. The subject-specific biomechanical parameters were quantified using an inverse finite-element modelling approach. The personalized models were evaluated against relevant clinical metrics extracted from the MR data, such as circumferential strain, wall thickness and fractional thickening. We obtained the ranges of healthy biomechanical indices of 1.60 ± 0.22 kPa for left ventricular stiffness and 95.13 ± 14.56 kPa for left ventricular contractility. These reference normal values can be used for future model-based investigation on the stiffness and contractility of ischemic myocardium.

A survey of pathways for mechano-electric coupling in the atria

Mechano-electric coupling (MEC) in atrial tissue has received sparse investigation to date, despite the well-known association between chronic atrial dilation and atrial fibrillation (AF). Of note, no fewer than six different mechanisms pertaining to stretch-activated channels, cellular capacitance and geometric effects have been identified in the literature as potential players. In this mini review, we briefly survey each of these pathways to MEC. We then perform computational simulations using single cell and tissue models in presence of various stretch regimes and MEC pathways. This allows us to assess the relative significance of each pathway in determining action potential duration, conduction velocity and rotor stability. For chronic atrial stretch, we find that stretch-induced alterations in membrane capacitance decrease conduction velocity and increase action potential duration, in agreement with experimental findings. In the presence of time-dependent passive atrial stretch, stretch-activated channels play the largest role, leading to after-depolarizations and rotor hypermeandering. These findings suggest that physiological atrial stretches, such as passive stretch during the atrial reservoir phase, may play an important part in the mechanisms of atrial arrhythmogenesis.

•

Passive strains caused by ventricular contraction need to be considered when incorporating mechano-electro feedback in atrial electrophysiology models.

•

In chronic stretch, stretch-induced capacitance changes dominate.

•

Chronic stretch leads to an increase in action potential duration and a reduction in conduction velocity, consistent with experimental studies.

•

In the presence of passive stretch, stretch-activated channels can induce delayed after-depolarisations and lead to rotor hypermeandering.

•

Mechano-electro feedback is thus likely to have implications for the genesis and maintenance of atrial arrhythmias.

A population-based phenome-wide association study of cardiac and aortic structure and function

Differences in cardiac and aortic structure and function are associated with cardiovascular diseases and a wide range of other types of disease. Here we analyzed cardiovascular magnetic resonance images from a population-based study, the UK Biobank, using an automated machine-learning-based analysis pipeline. We report a comprehensive range of structural and functional phenotypes for the heart and aorta across 26,893 participants, and explore how these phenotypes vary according to sex, age and major cardiovascular risk factors. We extended this analysis with a phenome-wide association study, in which we tested for correlations of a wide range of non-imaging phenotypes of the participants with imaging phenotypes. We further explored the associations of imaging phenotypes with early-life factors, mental health and cognitive function using both observational analysis and Mendelian randomization. Our study illustrates how population-based cardiac and aortic imaging phenotypes can be used to better define cardiovascular disease risks as well as heart-brain health interactions, highlighting new opportunities for studying disease mechanisms and developing image-based biomarkers.

Segmentation of the distal femur in ultrasound images

Objectives

Ultrasound is a widely used imaging technology that allows for fast diagnosis of a broad range of illnesses and injuries of the musculoskeletal system. However, interpreting ultrasound images remains a challenging task that requires expert knowledge and years of training for each exam. One crucial step for the long-term goal of automatic diagnosis is pixel wise semantic segmentation.

Methods

In this work, several state-of-the-art semantic segmentation networks were trained on a new dataset of manually annotated ultrasound images depicting the distal femur.

Results

PSP-Net achieved the best overall performance with an average surface distance error (SDE) of 0.64 mm.

Conclusions

We recommend the PSP-Net architecture for semantic segmentation of bone surfaces.

Temporally coherent cardiac motion tracking from cine MRI: Traditional registration method and modern CNN method

Purpose

Cardiac motion tracking enables quantitative evaluation of myocardial strain, which is clinically interesting in cardiovascular disease research. However, motion tracking is difficult to perform manually. In this paper, we aim to develop and compare two fully automated motion tracking methods for the steady state free precession (SSFP) cine magnetic resonance imaging (MRI), and explore their use in real clinical scenario with different patient groups.

Methods

We proposed two automated cardiac motion tracking method: (a) a traditional registration‐based method, named full cardiac cycle registration, which simultaneously tracks all cine frames within a full cardiac cycle by joint registration of all frames; and (b) a modern convolutional neural network (CNN)‐based method, named Groupwise MotionNet, which enhances the temporal coherence by fusing motion along a continuous time scale. Both methods were evaluated on the healthy volunteer data from the MICCAI 2011 STACOM Challenge, as well as on patient data including hypertrophic cardiomyopathy (HCM) and myocardial infarction (MI).

Results

The full cardiac cycle registration method achieved an average end‐point error (EPE) 2.89 ± 1.57 mm for cardiac motion tracking, with computation time of around 9 min per short‐axis cine MRI (size 128 × 128, 30 cardiac phases). In comparison, the Groupwise MotionNet achieved an average EPE of 0.94 ± 1.59 mm, taking < 1 s for a full cardiac phases. Further experiments showed that registration method had stable performance, independent of patient cohort and MRI machine, while the CNN‐based method relied on the training data to deliver consistently accurate results.

Conclusion

Both registration‐based and CNN‐based method can track the cardiac motion from SSFP cine MRI in a fully automated manner, while taking temporal coherence into account. The registration method is generic, robust, but relatively slow; the CNN‐based method trained with heterogeneous data was able to achieve high tracking accuracy with real‐time performance.

Left ventricle segmentation using a Bayesian approach with distance dependent shape priors

We propose a method for segmentation of the left ventricle in magnetic resonance cardiac images. The framework consists of an initial Bayesian segmentation of the central slice of the volume. This segmentation is used to locate a shape prior for the LV myocardial tissue. This shape prior is determined using the fact that the myocardium is approximately annular as seen in the short-axis. Then a second Bayesian segmentation is performed to obtain the final result. This procedure is repeated for the rest of the slices. An extrapolation of the area of the LV is used to determine a stopping criterion. The method was evaluated on the databases of the Cardiac Atlas project. Our results demonstrate a suitable accuracy for myocardial segmentation (≈0.8 Dice's coefficient). For the endocardium and the epicardium the Dice's coefficients are 0.94 and 0.9 respectively. The accuracy was also evaluated in terms of the Hausdorff distance and the average distance. For the myocardium we obtain 8 mm and 2 mm respectively. Our results demonstrate the capability and merits of the proposed method to estimate the structure of the LV. The method requires minimal user input and generates results with quality comparable to more complex approaches. This paper suggests a new efficient approach for automatic LV quantification based on a Bayesian technique with shape priors with errors comparable to state-of-the-art techniques.

An extensible software platform for interdisciplinary cardiovascular imaging research

BACKGROUND AND OBJECTIVE

Cardiovascular imaging is an exponentially growing field with aspects ranging from image acquisition and analysis to disease characterization, and evaluation of therapy approaches.The transfer of innovative new technological and algorithmic solutions into clinical practice is still slow. In addition to the verification of solutions, their integration in the clinical processing workflow must be enabled for the assessment of clinical impact and risks. The goal of our software platform for cardiac image processing - CAIPI - is to support researchers from different specialties such as imaging physics, computer science, and medicine by a common extensible platform to address typical challenges and hurdles in interdisciplinary cardiovascular imaging research. It provides an integrated solution for method comparison, integrated analysis, and validation in the clinical context. The interface concept enables a combination with existing frameworks that address specific aspects of the pipeline, such as modeling (e.g., OpenCMISS, CARP) or image reconstruction (Gadgetron).

METHODS

In our platform, we developed a concept for import, integration, and management of cardiac image data. The integration approach considers the spatiotemporal properties of the beating heart through a specific data model. The solution is based on MeVisLab and provides functionalities for data retrieval and storage. Two types of plugins can be added. While ToolPlugins usually provide processing algorithms such as image correction and segmentation, AnalysisPlugins enable interactive data exploration and reporting. GUI integration concepts are presented for both plugin types. We developed domain-specific reporting and visualization tools (e.g., AHA segment model) to enable validation studies by clinical experts. The platform offers plugins for calculating and reporting quantitative parameters such as cardiac function, which can be used to, e.g., evaluate the effect of processing algorithms on clinical parameters. Export functionalities include quantitative measurements to Excel, image data to PACS, and STL models to modeling and simulation tools.

RESULTS

To demonstrate the applicability of this concept both for method development and clinical application, we present use cases representing different problems along the innovation chain in cardiac MR imaging. Validation of an image reconstruction method (MRI T1 mapping) Validation of an image correction method for real-time 2D-PC MRI Comparison of quantification methods for blood flow analysis Training and integration of machine learning solutions with expert annotations Clinical studies with new imaging techniques (flow measurements in the carotid arteries and peripheral veins as well as cerebral spinal fluid).

CONCLUSION

The presented platform can be used in interdisciplinary teams, in which engineers or data scientists perform the method validation, followed by clinical research studies in patient collectives. The demonstrated use cases show how it enables the transfer of innovations through validation in the cardiovascular application context.

Improved tagged cardiac MRI myocardium strain analysis by leveraging cine segmentation

BACKGROUND AND OBJECTIVES

Tagged MR images provide an effective way for regional analysis of the myocardium strain. A reliable myocardium strain analysis requires both correct segmentation and accurate motion tracking of the myocardium during the cardiac cycle. While many algorithms have been proposed for accurate tracking of the myocardium in tagged MR images, little focus has been placed on ensuring correct segmentation of the tagged myocardium during the cardiac cycle. Myocardial strain analysis is usually done by segmenting the myocardium in end-diastole, generating a mesh from the segmentation, propagating the mesh through the cardiac cycle using the output deformation field from motion tracking, and measuring strain on the deforming mesh. Due to the imposed tag strips on the anatomy, identification of the myocardium boundaries is challenging in tagged MR images. As a result, there is no guarantee that the propagated mesh is annotating the myocardium accurately through the cardiac cycle. Moreover, clinical studies indicate that incorrect myocardium annotation can result in overestimation of myocardial strains.

METHODS

We introduce a method to improve reliability of strain analysis by proposing a mesh which correctly segments the myocardium in tagged MRI by leveraging the available cine MRI segmentation. In particular, we generate a series of mesh proposals using the cine MRI segmentation and find the propagated mesh proposal which gives the most accurate full-cycle myocardium segmentation.

RESULTS

The mesh selection algorithm was tested on 22 2D MRI scans of diseased and healthy hearts. The proposed algorithm provided more accurate whole-cycle myocardium segmentation compared to the propagated end-diastolic mesh. Regional myocardium strain was measured for 10 3D MRI scans of healthy volunteers using the proposed mesh and the end-diastolic mesh. The measured strain using the proposed mesh was more similar to the expected myocardium strain for a healthy heart than the measured strain using the end-diastolic mesh.

CONCLUSION

The proposed approach provides accurate whole-cycle tagged myocardium segmentation and more reliable myocardium strain analysis.

Quantitative Validation of MRI-Based Motion Estimation for Brain Impact Biomechanics

Head impact can cause traumatic brain injury (TBI) through axonal overstretch or subsequent inflammation and understanding the biomechanics of the impact event is useful for TBI prevention research. Tagged magnetic resonance imaging (MRI) acquired during a mild-acceleration impact has enabled measurement and visualization of brain deformation in vivo. However, measurements using MRI are subject to error, and having independent validation while imaging in vivo is very difficult. Thus, characterizing the accuracy of these measurements needs to be done in a separate experiment using a phantom where a gold standard is available. This study describes a method for error quantification using a calibration phantom compatible with MRI and high-speed video (the gold standard). During linear acceleration, the maximum shear strain (MSS) in the phantom ranged from 0 to 12%, which is similar to in vivo brain deformation at a similar acceleration. The mean displacement error against video was 0.3±0.3 mm, and the MSS error was 1.4±0.3%. To match resolutions, video data was filtered temporally using an averaging filter. Compared to the unfiltered results, resolution matching improved the agreement between MRI and video results by 15%. In conclusion, tagged MRI analysis compares well to video data provided that resolutions are matched-a finding that is also applicable when using MRI to validate simulations.

Myocardial Radiomics in Cardiac MRI

OBJECTIVE. The purpose of this article is to review the nascent field of radiomics in cardiac MRI. CONCLUSION. Cardiac MRI produces a large number of images in a fairly inefficient manner with sometimes limited clinical application. In the era of precision medicine, there is increasing need for imaging to account for a broader array of diseases in an efficient and objective manner. Radiomics, the extraction and analysis of quantitative imaging features from medical imaging, may offer potential solutions to this need.

Fusion of 3D real-time echocardiography and cine MRI using a saliency analysis

PURPOSE

This paper presents a novel 3D multimodal registration strategy to fuse 3D real-time echocardiography images with cardiac cine MRI images. This alignment is performed in a saliency space, which is designed to maximize similarity between the two imaging modalities. This fusion improves the quality of the available information.

METHODS

The method performs in two steps: temporal and spatial registrations. A temporal alignment is firstly achieved by nonlinearly matching pairs of correspondences between the two modalities using a dynamic time warping. A temporal registration is then carried out by applying nonrigid transformations in a common saliency space where normalized cross correlation between temporal pairs of salient volumes is maximized.

RESULTS

The alignment performance was evaluated with a set of 18 subjects, 3 with cardiomyopathies and 15 healthy, by computing the Dice score and Hausdorff distance with respect to manual delineations of the left ventricle cavity in both modalities. A Dice score and Hausdorff distance of [Formula: see text] and [Formula: see text], respectively, were obtained. In addition, the deformation field was estimated by quantifying its foldings, obtaining a 98% of regularity in the deformation field.

CONCLUSIONS

The 3D multimodal registration strategy presented is performed in a saliency space. Unlike state-of-the-art methods, the presented one takes advantage of the temporal information of the heart to construct this common space, ending up with two well-aligned modalities and regular deformation fields. This preliminary study was evaluated on heterogeneous data composed of two different datasets, healthy and pathological cases, showing similar performances in both cases. Future work will focus on testing the presented strategy in a larger dataset with a balanced number of classes.

Hierarchical Template Matching for 3D Myocardial Tracking and Cardiac Strain Estimation

Myocardial tracking and strain estimation can non-invasively assess cardiac functioning using subject-specific MRI. As the left-ventricle does not have a uniform shape and functioning from base to apex, the development of 3D MRI has provided opportunities for simultaneous 3D tracking, and 3D strain estimation. We have extended a Local Weighted Mean (LWM) transformation function for 3D, and incorporated in a Hierarchical Template Matching model to solve 3D myocardial tracking and strain estimation problem. The LWM does not need to solve a large system of equations, provides smooth displacement of myocardial points, and adapt local geometric differences in images. Hence, 3D myocardial tracking can be performed with 1.49 mm median error, and without large error outliers. The maximum error of tracking is up to 24% reduced compared to benchmark methods. Moreover, the estimated strain can be insightful to improve 3D imaging protocols, and the computer code of LWM could also be useful for geo-spatial and manufacturing image analysis researchers.

Challenges in diffusion MRI tractography - Lessons learned from international benchmark competitions

Diffusion MRI (dMRI) fiber tractography has become a pillar of the neuroimaging community due to its ability to noninvasively map the structural connectivity of the brain. Despite widespread use in clinical and research domains, these methods suffer from several potential drawbacks or limitations. Thus, validating the accuracy and reproducibility of techniques is critical for sound scientific conclusions and effective clinical outcomes. Towards this end, a number of international benchmark competitions, or "challenges", has been organized by the diffusion MRI community in order to investigate the reliability of the tractography process by providing a platform to compare algorithms and results in a fair manner, and evaluate common and emerging algorithms in an effort to advance the state of the field. In this paper, we summarize the lessons from a decade of challenges in tractography, and give perspective on the past, present, and future "challenges" that the field of diffusion tractography faces.

Guideline-based learning for standard plane extraction in 3-D echocardiography

The extraction of six standard planes in 3-D cardiac ultrasound plays an important role in clinical examination to analyze cardiac function. A guideline-based learning method for efficient and accurate standard plane extraction is proposed. A cardiac ultrasound guideline determines appropriate operation steps for clinical examinations. The idea of guideline-based learning is incorporating machine learning approaches into each stage of the guideline. First, Hough forest with hierarchical search is applied for 3-D feature point detection. Second, initial planes are determined using anatomical regularities according to the guideline. Finally, a regression forest integrated with constraints of plane regularities is applied for refining each plane. The proposed method was evaluated on a 3-D cardiac ultrasound dataset and a synthetic dataset. Compared with other plane extraction methods, it demonstrated an improved accuracy with a significantly faster running time of 0.8    s / volume . Furthermore, it showed the proposed method was robust for a range abnormalities and image qualities, which would be seen in clinical practice.

Cardiac motion and spillover correction for quantitative PET imaging using dynamic MRI

PURPOSE

Cardiac positron emission tomography/magnetic resonance imaging (PET/MRI) acquisition presents novel clinical applications thanks to the combination of viability and metabolic imaging (PET) and functional and structural imaging (MRI). However, the resolution of PET, as well as cardiac and respiratory motion in nongated cardiac imaging acquisition protocols, leads to a reduction in image quality and severe quantitative bias. Respiratory or cardiac motion is customarily addressed with gated reconstruction which results in higher noise.

METHODS

Inspired by a method that has been used in brain PET, a practical correction approach, designed to overcome these existing limitations for quantitative PET imaging, was developed and applied in the context of cardiac PET/MRI. The correction approach for PET data consists of computing the mean density map of each underlying moving region, as obtained with MRI, and translating them to the PET space taking into account the PET spatial and temporal resolution. Using these tissue density maps, the method then constructs a system of linear equations that models the activity recovery and cross-contamination coefficients, which can be solved for the true activity values. Physical and numerical cardiac phantoms were employed in order to quantify the proposed correction. The full correction pipeline was then used to assess differences in metabolic function between scar and healthy myocardium in eight patients with recent acute myocardial infarction using [¹¹ C]-acetate. Data from ten additional patients, injected with [¹⁸ F]-FDG, were used to compare the method to the standard electrocardiography (ECG)-gated approach.

RESULTS

The proposed method resulted in better recovery (from 32% to 95% on the simulated phantom model) and less residual activity than the standard approach. Higher signal-to-noise and contrast-to-noise ratios than ECG-gating were also witnessed (Signal-to-noise ratio (SNR) increased from 2.92 to 5.24, contrast-to-noise ratio (CNR) increased from 62.9 to 145.9 when compared to a four-gate reconstruction). Finally, the relevance of this correction using [¹¹ C]-acetate PET patient data, for which erroneous physiological conclusions could have been made based on the uncorrected data, was established as the correction led to the expected clinical results.

CONCLUSIONS

An efficient and simple method to correct for the quantitative biases in PET measurements caused by cardiac motion has been developed. Validation experiments using phantom and patient data showed improved accuracy and reliability with this approach when compared to simpler strategies such as gated acquisition or optimal regions of interest (ROI).

Why rankings of biomedical image analysis competitions should be interpreted with care

International challenges have become the standard for validation of biomedical image analysis methods. Given their scientific impact, it is surprising that a critical analysis of common practices related to the organization of challenges has not yet been performed. In this paper, we present a comprehensive analysis of biomedical image analysis challenges conducted up to now. We demonstrate the importance of challenges and show that the lack of quality control has critical consequences. First, reproducibility and interpretation of the results is often hampered as only a fraction of relevant information is typically provided. Second, the rank of an algorithm is generally not robust to a number of variables such as the test data used for validation, the ranking scheme applied and the observers that make the reference annotations. To overcome these problems, we recommend best practice guidelines and define open research questions to be addressed in the future.

Algorithms for left atrial wall segmentation and thickness - Evaluation on an open-source CT and MRI image database

Structural changes to the wall of the left atrium are known to occur with conditions that predispose to Atrial fibrillation. Imaging studies have demonstrated that these changes may be detected non-invasively. An important indicator of this structural change is the wall's thickness. Present studies have commonly measured the wall thickness at few discrete locations. Dense measurements with computer algorithms may be possible on cardiac scans of Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). The task is challenging as the atrial wall is a thin tissue and the imaging resolution is a limiting factor. It is unclear how accurate algorithms may get and how they compare in this new emerging area. We approached this problem of comparability with the Segmentation of Left Atrial Wall for Thickness (SLAWT) challenge organised in conjunction with MICCAI 2016 conference. This manuscript presents the algorithms that had participated and evaluation strategies for comparing them on the challenge image database that is now open-source. The image database consisted of cardiac CT (n=10) and MRI (n=10) of healthy and diseased subjects. A total of 6 algorithms were evaluated with different metrics, with 3 algorithms in each modality. Segmentation of the wall with algorithms was found to be feasible in both modalities. There was generally a lack of accuracy in the algorithms and inter-rater differences showed that algorithms could do better. Benchmarks were determined and algorithms were ranked to allow future algorithms to be ranked alongside the state-of-the-art techniques presented in this work. A mean atlas was also constructed from both modalities to illustrate the variation in thickness within this small cohort.

MITT: Medical Image Tracking Toolbox

Over the years, medical image tracking has gained considerable attention from both medical and research communities due to its widespread utility in a multitude of clinical applications, from functional assessment during diagnosis and therapy planning to structure tracking or image fusion during image-guided interventions. Despite the ever-increasing number of image tracking methods available, most still consist of independent implementations with specific target applications, lacking the versatility to deal with distinct end-goals without the need for methodological tailoring and/or exhaustive tuning of numerous parameters. With this in mind, we have developed the medical image tracking toolbox (MITT)-a software package designed to ease customization of image tracking solutions in the medical field. While its workflow principles make it suitable to work with 2-D or 3-D image sequences, its modules offer versatility to set up computationally efficient tracking solutions, even for users with limited programming skills. MITT is implemented in both C/C++ and MATLAB, including several variants of an object-based image tracking algorithm and allowing to track multiple types of objects (i.e., contours, multi-contours, surfaces, and multi-surfaces) with several customization features. In this paper, the toolbox is presented, its features discussed, and illustrative examples of its usage in the cardiology field provided, demonstrating its versatility, simplicity, and time efficiency.

3-D Measurements of Acceleration-Induced Brain Deformation via Harmonic Phase Analysis and Finite-Element Models

OBJECTIVE

To obtain dense spatiotemporal measurements of brain deformation from two distinct but complementary head motion experiments: linear and rotational accelerations.

METHODS

This study introduces a strategy for integrating harmonic phase analysis of tagged magnetic resonance imaging (MRI) and finite-element models to extract mechanically representative deformation measurements. The method was calibrated using simulated as well as experimental data, demonstrated in a phantom including data with image artifacts, and used to measure brain deformation in human volunteers undergoing rotational and linear acceleration.

RESULTS

Evaluation methods yielded a displacement error of 1.1 mm compared to human observers and strain errors between [Formula: see text] for linear acceleration and [Formula: see text] for rotational acceleration. This study also demonstrates an approach that can reduce error by 86% in the presence of corrupted data. Analysis of results shows consistency with 2-D motion estimation, agreement with external sensors, and the expected physical behavior of the brain.

CONCLUSION

Mechanical regularization is useful for obtaining dense spatiotemporal measurements of in vivo brain deformation under different loading regimes.

SIGNIFICANCE

The measurements suggest that the brain's 3-D response to mild accelerations includes distinct patterns observable using practical MRI resolutions. This type of measurement can provide validation data for computer models for the study of traumatic brain injury.

Equilibrated warping: Finite element image registration with finite strain equilibrium gap regularization

In this paper, we propose a novel continuum finite strain formulation of the equilibrium gap regularization for image registration. The equilibrium gap regularization essentially penalizes any deviation from the solution of a hyperelastic body in equilibrium with arbitrary loads prescribed at the boundary. It thus represents a regularization with strong mechanical basis, especially suited for cardiac image analysis. We describe the consistent linearization and discretization of the regularized image registration problem, in the framework of the finite elements method. The method is implemented using FEniCS & VTK, and distributed as a freely available python library. We show that the equilibrated warping method is effective and robust: regularization strength and image noise have minimal impact on motion tracking, especially when compared to strain-based regularization methods such as hyperelastic warping. We also show that equilibrated warping is able to extract main deformation features on both tagged and untagged cardiac magnetic resonance images.

Regional Multi-View Learning for Cardiac Motion Analysis: Application to Identification of Dilated Cardiomyopathy Patients

OBJECTIVE

The aim of this paper is to describe an automated diagnostic pipeline that uses as input only ultrasound (US) data, but is at the same time informed by a training database of multimodal magnetic resonance (MR) and US image data.

METHODS

We create a multimodal cardiac motion atlas from three-dimensional (3-D) MR and 3-D US data followed by multi-view machine learning algorithms to combine and extract the most meaningful cardiac descriptors for classification of dilated cardiomyopathy (DCM) patients using US data only. More specifically, we propose two algorithms based on multi-view linear discriminant analysis and multi-view Laplacian support vector machines (MvLapSVMs). Furthermore, a novel regional multi-view approach is proposed to exploit the regional relationships between the two modalities.

RESULTS

We evaluate our pipeline on the classification task of discriminating between normals and DCM patients. Results show that the use of multi-view classifiers together with a cardiac motion atlas results in a statistically significant improvement in accuracy compared to classification without the multimodal atlas. MvLapSVM was able to achieve the highest accuracy for both the global approach (92.71%) and the regional approach (94.32%).

CONCLUSION

Our work represents an important contribution to the understanding of cardiac motion, which is an important aid in the quantification of the contractility and function of the left ventricular myocardium.

SIGNIFICANCE

The intended workflow of the developed pipeline is to make use of the prior knowledge from the multimodal atlas to enable robust extraction of indicators from 3-D US images for detecting DCM patients.

A Novel Hierarchical Template Matching Model for Cardiac Motion Estimation

Cardiovascular disease diagnosis and prognosis can be improved by measuring patient-specific in-vivo local myocardial strain using Magnetic Resonance Imaging. Local myocardial strain can be determined by tracking the movement of sample muscles points during cardiac cycle using cardiac motion estimation model. The tracking accuracy of the benchmark Free Form Deformation (FFD) model is greatly affected due to its dependency on tunable parameters and regularisation function. Therefore, Hierarchical Template Matching (HTM) model, which is independent of tunable parameters, regularisation function, and image-specific features, is proposed in this article. HTM has dense and uniform points correspondence that provides HTM with the ability to estimate local muscular deformation with a promising accuracy of less than half a millimetre of cardiac wall muscle. As a result, the muscles tracking accuracy has been significantly (p < 0.001) improved (30%) compared to the benchmark model. Such merits of HTM provide reliably calculated clinical measures which can be incorporated into the decision-making process of cardiac disease diagnosis and prognosis.

A Novel Filtering Approach for 3D Harmonic Phase Analysis of Tagged MRI

Harmonic phase analysis has been used to perform noninvasive organ motion and strain estimation using tagged magnetic resonance imaging (MRI). The filtering process, which is used to produce harmonic phase images used for tissue tracking, influences the estimation accuracy. In this work, we evaluated different filtering approaches, and propose a novel high-pass filter for volumes tagged in individual directions. Testing was done using an open benchmarking dataset and synthetic images obtained using a mechanical model. We compared estimation results from our filtering approach with results from the traditional filtering approach. Our results indicate that 1) the proposed high-pass filter outperforms the traditional filtering approach reducing error by as much as 50% and 2) the accuracy improvements are especially marked in complex deformations.