Deep learning approaches for the detection of scar presence from cine cardiac magnetic resonance adding derived parametric images

This work proposes a convolutional neural network (CNN) that utilizes different combinations of parametric images computed from cine cardiac magnetic resonance (CMR) images, to classify each slice for possible myocardial scar tissue presence. The CNN performance comparison in respect to expert interpretation of CMR with late gadolinium enhancement (LGE) images, used as ground truth (GT), was conducted on 206 patients (158 scar, 48 control) from Centro Cardiologico Monzino (Milan, Italy) at both slice- and patient-levels. Left ventricle dynamic features were extracted in non-enhanced cine images using parametric images based on both Fourier and monogenic signal analyses. The CNN, fed with cine images and Fourier-based parametric images, achieved an area under the ROC curve of 0.86 (accuracy 0.79, F1 0.81, sensitivity 0.9, specificity 0.65, and negative (NPV) and positive (PPV) predictive values 0.83 and 0.77, respectively), for individual slice classification. Remarkably, it exhibited 1.0 prediction accuracy (F1 0.98, sensitivity 1.0, specificity 0.9, NPV 1.0, and PPV 0.97) in patient classification as a control or pathologic. The proposed approach represents a first step towards scar detection in contrast-free CMR images. Patient-level results suggest its preliminary potential as a screening tool to guide decisions regarding LGE-CMR prescription, particularly in cases where indication is uncertain.

Hemodynamic impacts of hematocrit level by two-way coupled FSI in the left coronary bifurcation

Cardiovascular disease is now under the influence of several factors that encourage researchers to investigate the flow of these vessels. Oscillation influences the blood circulation in the volume of red blood cells (RBC) strongly. Therefore, in this study, its effects have been considered on hemodynamic parameters in the elastic wall and coronary bifurcation. In this study, a 3D geometry of non-Newtonian and pulsatile blood circulation is considered in the left coronary artery bifurcation. The Casson model with various hematocrits is analyzed in elastic and rigid walls. The wall shear stress (WSS) cannot show the stenosis artery alone, therefore, the oscillatory shear index (OSI) is represented as a hemodynamic parameter of WSS individually of time. The results are determined using two-way fluid-structure interaction (FSI) coupling method using an arbitrary Lagrangian-Eulerian method. The most prominent difference in velocity happened in the bifurcation and at hematocrit 30 with yield stress 6.59E-04 Pa. The backflow and vortex flow in the LCx branch grown with increasing shear rates. The likelihood of plaque generation at the ending of the LM branch is observed in hematocrits 10 and 20, while the WSS magnitude is normal in the hematocrit 60 with the greatest yield stress in the bifurcation. The shear stress among the rigid and elastic models is the highest at the ending of the LM branch. The wall shear stress magnitude among the models decreased at most of 24.49% by dividing the flow. Time-independent results for models showed that there is the highest value of OSI at the bifurcation, which then quickly dropped.

The Role of Phase Image in the Detection of Myocardial Dyskinesia by Magnetic Resonance Imaging (MRI)

Background:

The assessment of cardiac wall motion abnormalities plays an important role in the evaluation of many cardiovascular diseases and the prediction of functional recovery. Most of the methods dedicated to identifying the location of wall motion abnormalities have been restricted to study hypokinesia while an accurate way to assess dyskinesia is still needed in Cardiac Magnetic Resonance Imaging (CMRI). </P><P> Objective: The aim of this study is to propose a phase image based on the analytic signal able to assess the extent of the myocardial dyskinetic segments in Cardiac Magnetic Resonance Imaging (CMRI). </P><P> Materials: 22 subjects were retrospectively enrolled in this study (age 46 ± 11): 15 presenting an aneurysm and 7 control subjects with normal wall motion. For each patient, three standard views (short axis view, 2 chamber and 4 chamber views) were acquired using 3 Tesla Siemens Avanto MRI scanner and a segmented True FISP sequence. All the cine MRI images were analyzed by two experimented observers who were blinded to the diagnostic results.

Results:

The outcomes of this study show that using the proposed phase image in MRI clinical routine can increase the accuracy of the detection of myocardial dyskinetic segments from 77.23 % to 86.38 %, the sensitivity from 67.48 % to 78.86 % as well the specificity from 80.92 % to 89.23 % compared to the standard method based on cine MRI interpretation.

Conclusion:

The phase image is a promising tool in CMRI for the assessment of dyskinetic segments and the degree of myocardial asynchronism.

Left ventricular MRI wall motion assessment by monogenic signal amplitude image computation

BACKGROUND

Cardiac Magnetic Resonance Imaging (MRI) is the commonly used technique for the assessment of left ventricular (LV) function. Apart manually or semi-automatically contouring LV boundaries for quantification of By visual interpretation of cine images, assessment of regional wall motion is performed by visual interpretation of cine images, thus relying on an experience-dependent and subjective modality.

OBJECTIVE

The aim of this work is to describe a novel algorithm based on the computation of the monogenic amplitude image to be utilized in conjunction with conventional cine-MRI visualization to assess LV motion abnormalities and to validate it against gold standard expert visual interpretation.

METHODS

The proposed method uses a recent image processing tool called "monogenic signal" to decompose the MR images into features, which are relevant for motion estimation. Wall motion abnormalities are quantified locally by measuring the temporal variations of the monogenic signal amplitude. The new method was validated by two non-expert radiologists using a wall motion scoring without and with the computed image, and compared against the expert interpretation. The proposed approach was tested on a population of 40 patients, including 8 subjects with normal ventricular function and 32 pathological cases (20 with myocardial infarction, 9 with myocarditis, and 3 with dilated cardiomyopathy).

RESULTS

The results show that, for both radiologists, sensitivity, specificity and accuracy of cine-MRI alone were similar and around 59%, 77%, and 71%, respectively. Adding the proposed amplitude image while visualizing the cine MRI images significantly increased both sensitivity, specificity and accuracy up to 75%, 89%, and 84%, respectively.

CONCLUSION

Accuracy of wall motion interpretation adding amplitude image to conventional visualization was proven feasible and superior to standard image interpretation on the considered population, in inexperienced observers. Adding the amplitude images as a diagnostic tool in clinical routine is likely to improve the detection of myocardial segments presenting a cardiac dysfunction.

Parametric Imaging for the Assessment of Cardiac Motion: A Review

The assessment of wall motion abnormalities such as hypokinesia or dyskinesia and the identification of their extent as well as their degree of severity allow an accurate evaluation of several ischemic heart diseases and an early diagnosis of heart failure. These dysfunctions are usually revealed by a drop of contraction indicating a regional hypokinesia or a total absence of the wall motion in case of akinesia. The discrimination between these contraction abnormalities plays also a significant role in the therapeutic decision through the differentiation between the infarcted zones, which have lost their contractile function, and the stunned areas that still retain viable myocardial tissues. The lack of a reliable method for the evaluation of wall motion abnormalities in cardiac imaging presents a major limitation for a regional assessment of the left ventricular function. In the past years, several techniques were proposed as additional tools for the local detection of wall motion deformation. Among these approaches, the parametric imaging is likely to represent a promising technique for the analysis of a local contractile function. The aim of this paper is to review the most recent techniques of parametric imaging computation developed in cardiac imaging and their potential contributions in clinical practice.

A Compact VLSI System for Bio-Inspired Visual Motion Estimation

This paper proposes a bio-inspired visual motion estimation algorithm based on motion energy, along with its compact very-large-scale integration (VLSI) architecture using low-cost embedded systems. The algorithm mimics motion perception functions of retina, V1, and MT neurons in a primate visual system. It involves operations of ternary edge extraction, spatiotemporal filtering, motion energy extraction, and velocity integration. Moreover, we propose the concept of confidence map to indicate the reliability of estimation results on each probing location. Our algorithm involves only additions and multiplications during runtime, which is suitable for low-cost hardware implementation. The proposed VLSI architecture employs multiple (frame, pixel, and operation) levels of pipeline and massively parallel processing arrays to boost the system performance. The array unit circuits are optimized to minimize hardware resource consumption. We have prototyped the proposed architecture on a low-cost field-programmable gate array platform (Zynq 7020) running at 53-MHz clock frequency. It achieved 30-frame/s real-time performance for velocity estimation on 160 × 120 probing locations. A comprehensive evaluation experiment showed that the estimated velocity by our prototype has relatively small errors (average endpoint error < 0.5 pixel and angular error < 10°) for most motion cases.

Fast left ventricle tracking using localized anatomical affine optical flow

In daily clinical cardiology practice, left ventricle (LV) global and regional function assessment is crucial for disease diagnosis, therapy selection, and patient follow-up. Currently, this is still a time-consuming task, spending valuable human resources. In this work, a novel fast methodology for automatic LV tracking is proposed based on localized anatomically constrained affine optical flow. This novel method can be combined to previously proposed segmentation frameworks or manually delineated surfaces at an initial frame to obtain fully delineated datasets and, thus, assess both global and regional myocardial function. Its feasibility and accuracy were investigated in 3 distinct public databases, namely in realistically simulated 3D ultrasound, clinical 3D echocardiography, and clinical cine cardiac magnetic resonance images. The method showed accurate tracking results in all databases, proving its applicability and accuracy for myocardial function assessment. Moreover, when combined to previous state-of-the-art segmentation frameworks, it outperformed previous tracking strategies in both 3D ultrasound and cardiac magnetic resonance data, automatically computing relevant cardiac indices with smaller biases and narrower limits of agreement compared to reference indices. Simultaneously, the proposed localized tracking method showed to be suitable for online processing, even for 3D motion assessment. Importantly, although here evaluated for LV tracking only, this novel methodology is applicable for tracking of other target structures with minimal adaptations.

Magnetic resonance imaging of myocardial strain: A review of current approaches

Contraction of the heart is central to its purpose of pumping blood around the body. While simple global function measures (such as the ejection fraction) are most commonly used in the clinical assessment of cardiac function, MRI also provides a range of approaches for quantitatively characterizing regional cardiac function, including the local deformation (or strain) within the heart wall. While they have been around for some years, these methods are still undergoing further technical development, and they have had relatively little clinical evaluation. However, they can provide potentially useful new ways to assess cardiac function, which may be able to contribute to better classification and treatment of heart disease. This article provides some basic background on the physical and physiological factors that determine the motion of the heart, in health and disease and then reviews some of the ways that MRI methods are being developed to image and quantify strain within the myocardium.

LEVEL OF EVIDENCE

4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;46:1263-1280.

Assessment of left atrial function by MRI myocardial feature tracking

BACKGROUND

Left atrium (LA) volumes and function are predictors of cardiovascular events. Because LA function cannot be assessed from cardiovascular magnetic resonance imaging (MRI) using the well-established left ventricular tagging techniques, we hypothesized that adequate feature tracking (FT) applied to conventional cine MRI data could characterize LA function accurately.

METHODS

We studied 10 young (28 ± 7 years) and 10 elderly (64 ± 6 years) healthy subjects, as well as 20 patients with moderate to severe aortic valve stenosis (AVS; 73 ± 15 years, effective aortic valve area: 0.67 ± 0.36 cm(2) ). MRI cine two-, three-, and four-chamber views were analyzed using a newly proposed FT method based on spatial correlation and endocardial detection resulting in: regional and global longitudinal strain and strain rate, radial motion fraction and relative velocity for the three LA motion phases including reservoir, conduit, and LA contraction.

RESULTS

FT reliability was indicated by a good overlap between tracking results and manual LA endocardial borders, the low error for comparison against theoretical strains introduced in a synthetic phantom and the good inter-observer reproducibility (coefficient of variation < 15%). While all LA functional parameters were significantly impaired in AVS patients (p < 0.04), subclinical age-related variations induced a decreasing trend on all LA parameters but were significant only for radial conduit function parameters (p < 0.03). Finally, LA functional parameters characterized LA alteration in AVS with higher sensitivity than conventional LA volumetric parameters.

CONCLUSIONS

Left atrial FT is feasible on MRI cine images and its addition to conventional analysis tools might enhance the diagnosis value of MRI in many heart diseases.

Motility mapping as evaluation tool for bowel motility: initial results on the development of an automated color-coding algorithm in cine MRI

PURPOSE

To develop and implement an automated algorithm for visualizing and quantifying bowel motility using cine magnetic resonance imaging (MRI).

MATERIALS AND METHODS

Four healthy volunteers as well as eight patients with suspected or diagnosed inflammatory bowel disease (IBD) underwent MR examinations on a 1.5T scanner. Coronal T2-weighted cine MR images were acquired in healthy volunteers without and with intravenous (i.v.) administration of butylscopolamine. In patients with IBD, cine MRI sequences were collected prior to standard bowel MRI. Bowel motility was assessed using an optical flow algorithm. The resulting motion vector magnitudes were presented as bowel motility maps. Motility changes after i.v. administration of butylscopolamine were measured in healthy volunteers. Inflamed bowel segments in patients were correlated with motility map findings.

RESULTS

The acquisition of bowel motility maps was feasible in all subjects examined. In healthy volunteers butylscopolamine led to quantitatively measurable decrease in bowel motility (mean decrease of 59%; P = 0.171). In patients with IBD, visualization of bowel movement by color-coded motility mapping allowed for the detection of segments with abnormal bowel motility. Inflamed bowel segments could be identified by exhibiting a decreased motility.

CONCLUSION

Our method is a feasible and promising approach for the assessment of bowel motility disorders.

Cardiovascular health informatics: risk screening and intervention

Despite enormous efforts to prevent cardiovascular disease (CVD) in the past, it remains the leading cause of death in most countries worldwide. Around two-thirds of these deaths are due to acute events, which frequently occur suddenly and are often fatal before medical care can be given. New strategies for screening and early intervening CVD, in addition to the conventional methods, are therefore needed in order to provide personalized and pervasive healthcare. In this special issue, selected emerging technologies in health informatics for screening and intervening CVDs are reported. These papers include reviews or original contributions on 1) new potential genetic biomarkers for screening CVD outcomes and high-throughput techniques for mining genomic data; 2) new imaging techniques for obtaining faster and higher resolution images of cardiovascular imaging biomarkers such as the cardiac chambers and atherosclerotic plaques in coronary arteries, as well as possible automatic segmentation, identification, or fusion algorithms; 3) new physiological biomarkers and novel wearable and home healthcare technologies for monitoring them in daily lives; 4) new personalized prediction models of plaque formation and progression or CVD outcomes; and 5) quantifiable indices and wearable systems to measure them for early intervention of CVD through lifestyle changes. It is hoped that the proposed technologies and systems covered in this special issue can result in improved CVD management and treatment at the point of need, offering a better quality of life to the patient.