scholarly journals Active Contour driven by geometric mean and standard deviation-based energy fitting model for the left ventricle segmentation from cardiac magnetic resonance images

2021 ◽  
Vol 23 (06) ◽  
pp. 1407-1416
Author(s):  
K. Sivakumar ◽  
◽  
Jayashree. S ◽  
Kaavya. K ◽  
Pooja. S ◽  
...  
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Standard Deviation ◽  
Magnetic Resonance ◽  
Left Ventricle ◽  
Cardiac Mri ◽  
Active Contour ◽  
Geometric Mean ◽  
Initial Contour ◽  
Proposed Model ◽  
Fitting Model

This paper proposes a geometric mean and standard deviation-based energy fitting model to improve the accuracy of segmentation of the left ventricle from cardiac Magnetic Resonance Imaging (MRI). Energy-fitting-based active contour models emerged so far suffer either from intensity inhomogeneity or gives wrong segmentation result due to an inappropriate initial contour. Thus, accurate and robust segmentation of the left ventricle from cardiac MRI still a challenging problem. Therefore, to tackle both the problems, a geometric mean-based energy-fitting model is proposed. Unlike the recent energy-fitting-based models which use the arithmetic mean to calculate the local energy, the proposed method uses geometric mean and scaled standard deviation to compute the energy functional which drives the active contour to the region of interest. In addition to that completely removes the initial contour problem by automating it according to the input. The initial contour in the proposed model is a circle its radius and the center are calculated from the input sample itself. This initial contour is an appropriate and automated one that helps to reduce the computation time for segmentation. Experiments are conducted on cardiac MRI images the result obtained is compared with ground truth and evaluated by Average perpendicular distance (APD) and DICE similarity coefficient. Further the visual, as well as evaluated parameters, evidences that the proposed model performs better than the existing methods.

scholarly journals Sensitivity analysis for interpretation of machine learning based segmentation models in cardiac MRI

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Markus J. Ankenbrand ◽  
Liliia Shainberg ◽  
Michael Hock ◽  
David Lohr ◽  
Laura M. Schreiber
Keyword(s):  
Neural Networks ◽  
Sensitivity Analysis ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Cardiac Mri ◽  
Magnetic Resonance Images ◽  
Model Interpretation ◽  
First Case ◽  
Segmentation Models

Abstract Background Image segmentation is a common task in medical imaging e.g., for volumetry analysis in cardiac MRI. Artificial neural networks are used to automate this task with performance similar to manual operators. However, this performance is only achieved in the narrow tasks networks are trained on. Performance drops dramatically when data characteristics differ from the training set properties. Moreover, neural networks are commonly considered black boxes, because it is hard to understand how they make decisions and why they fail. Therefore, it is also hard to predict whether they will generalize and work well with new data. Here we present a generic method for segmentation model interpretation. Sensitivity analysis is an approach where model input is modified in a controlled manner and the effect of these modifications on the model output is evaluated. This method yields insights into the sensitivity of the model to these alterations and therefore to the importance of certain features on segmentation performance. Results We present an open-source Python library (misas), that facilitates the use of sensitivity analysis with arbitrary data and models. We show that this method is a suitable approach to answer practical questions regarding use and functionality of segmentation models. We demonstrate this in two case studies on cardiac magnetic resonance imaging. The first case study explores the suitability of a published network for use on a public dataset the network has not been trained on. The second case study demonstrates how sensitivity analysis can be used to evaluate the robustness of a newly trained model. Conclusions Sensitivity analysis is a useful tool for deep learning developers as well as users such as clinicians. It extends their toolbox, enabling and improving interpretability of segmentation models. Enhancing our understanding of neural networks through sensitivity analysis also assists in decision making. Although demonstrated only on cardiac magnetic resonance images this approach and software are much more broadly applicable.

scholarly journals Cardiac Magnetic Resonance in Endomyocardial Fibrosis

2021 ◽  
pp. 263246362098563
Author(s):  
Shruthi Kalyan Athni ◽  
Johann Christopher
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Left Ventricle ◽  
Surgical Management ◽  
Symptomatic Relief ◽  
Endomyocardial Fibrosis ◽  
Management Options ◽  
High Level

Endomyocardial fibrosis is a rare cardiomyopathy. There has to be a high level of suspicion to make the diagnosis. The treatment is based on symptomatic relief and surgical management is based on the exact pathology found in the left ventricle apex. MRI is a robust investigation which can confirm diagnosis and provide management options and prognosis.

scholarly journals Left ventricular noncompaction—a rare cause of triad: heart failure, ventricular arrhythmias, and systemic embolic events: a case report 

2021 ◽  
Vol 15 (1) ◽  
Author(s):  
Despina Toader ◽  
Alina Paraschiv ◽  
Petrișor Tudorașcu ◽  
Diana Tudorașcu ◽  
Constantin Bataiosu ◽  
...  
Keyword(s):  
Heart Failure ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Left Ventricle ◽  
Ventricular Arrhythmias ◽  
Left Ventricular ◽  
Left Ventricular Ejection ◽  
Left Ventricular Noncompaction ◽  
Ventricular Noncompaction ◽  
The Right

Abstract Background Left ventricular noncompaction is a rare cardiomyopathy characterized by a thin, compacted epicardial layer and a noncompacted endocardial layer, with trabeculations and recesses that communicate with the left ventricular cavity. In the advanced stage of the disease, the classical triad of heart failure, ventricular arrhythmia, and systemic embolization is common. Segments involved are the apex and mid inferior and lateral walls. The right ventricular apex may be affected as well. Case presentation A 29-year-old Caucasian male was hospitalized with dyspnea and fatigue at minimal exertion during the last months before admission. He also described a history of edema of the legs and abdominal pain in the last weeks. Physical examination revealed dyspnea, pulmonary rales, cardiomegaly, hepatomegaly, and splenomegaly. Electrocardiography showed sinus rhythm with nonspecific repolarization changes. Twenty-four-hour Holter monitoring identified ventricular tachycardia episodes with right bundle branch block morphology. Transthoracic echocardiography at admission revealed dilated left ventricle with trabeculations located predominantly at the apex but also in the apical and mid portion of lateral and inferior wall; end-systolic ratio of noncompacted to compacted layers > 2; moderate mitral regurgitation; and reduced left ventricular ejection fraction. Between apical trabeculations, multiple thrombi were found. The right ventricle had normal morphology and function. Speckle-tracking echocardiography also revealed systolic left ventricle dysfunction and solid body rotation. Abdominal echocardiography showed hepatomegaly and splenomegaly. Abdominal computed tomography was suggestive for hepatic and renal infarctions. Laboratory tests revealed high levels of N-terminal pro-brain natriuretic peptide and liver enzymes. Cardiac magnetic resonance evaluation at 1 month after discharge confirmed the diagnosis. The patient received anticoagulants, antiarrhythmics, and heart failure treatment. After 2 months, before device implantation, he presented clinical improvement, and echocardiographic evaluation did not detect thrombi in the left ventricle. Coronary angiography was within normal range. A cardioverter defibrillator was implanted for prevention of sudden cardiac death. Conclusions Left ventricular noncompaction is rare cardiomyopathy, but it should always be considered as a possible diagnosis in a patient hospitalized with heart failure, ventricular arrhythmias, and systemic embolic events. Echocardiography and cardiac magnetic resonance are essential imaging tools for diagnosis and follow-up.

Loeffler Endocarditis of the Left Ventricle: Cardiac Magnetic Resonance Findings

2013 ◽  
Vol 22 (12) ◽  
pp. 1056-1057 ◽  
Author(s):  
Clara Bonanad ◽  
Jose Vicente Monmeneu ◽  
Maria Pilar López-Lereu
Keyword(s):  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Left Ventricle ◽  
Loeffler Endocarditis
Sign in / Sign up

Export Citation Format

Share Document