Machine Learning Approaches for Myocardial Motion and Deformation Analysis

Duchateau, Nicolás; King, Andrew P.; Craene, Mathieu De

doi:10.3389/fcvm.2019.00190

Cited by 21 publications

(16 citation statements)

References 93 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e usage of deep learning methods shown in Figure 1 supports reducing the computation time and enables normalising the data for better accuracy. Many researchers have noted that the usage of deep learning models supports greatly in analysing the data very effectively and the dataset can be increased through the usage of deep learning models these aspects can be effectively analysed [4]. Deep learning tools like multilayer neural networks enable performing the classification of data sets in heart-related diseases with more accuracy when compared with the traditional models.…”

Section: Introductionmentioning

confidence: 99%

Forecasting the Applied Deep Learning Tools in Enhancing Food Quality for Heart Related Diseases Effectively: A Study Using Structural Equation Model Analysis

Bangare

Virmani²,

Karetla

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

The term heart-related disease is stated as the range of condition that impacts an individual heart negatively. In the current scenario, cardiovascular diseases are causing more deaths when compared with other ailments, it has been estimated that there are nearly 18 million deaths annually as per the recent report released by World Health Organization (WHO). It has been stated that unhealthy habits and other related aspects adopted by individuals are considered as the primary reasons for an increase in the risk of heart diseases. High cholesterol, eating more junk foods, hypertension, etc., created the issue related to heart diseases. Hence, addressing food quality and suggesting better eating habits enable individuals to enhance their living and support better health. The application of new technologies like machine learning, deep learning, and other models support doctors, nurses, and radiologists to predict heart disease effectively. Studies have stated that the various models are used mainly for the classification and forecasting of the diagnosis of heart-related diseases. The researchers have identified that critical algorithms like CART support the predictability of the disease by 93.3% whereas the conventional models possess vert less specificity. Furthermore, deep neural networks can be applied for analyzing and detecting heart failures effectively and supporting medical practitioners in making better and more critical clinical decisions making. The researchers focus on using a descriptive research study for performing the study; moreover, the researcher collates the data using the questionnaire method, which enables sourcing the critical information from the medical practitioners and supports in making critical data analysis effectively. The researchers also use secondary data modes for sourcing the information related to past studies on the related topic. The researchers use the frequency analysis, correlation analysis, and structural equation model analysis for performing the study, and the results are stated in detail in the respective sections.

show abstract

Section: Introductionmentioning

confidence: 99%

Forecasting the Applied Deep Learning Tools in Enhancing Food Quality for Heart Related Diseases Effectively: A Study Using Structural Equation Model Analysis

Bangare

Virmani²,

Karetla

et al. 2022

Journal of Food Quality

View full text Add to dashboard Cite

show abstract

“…The low-dimensional embedding of myocardial shape or motion/deformation has been thoroughly explored in research, as reviewed in (Gilbert et al, 2020;Duchateau et al, 2020). Nonetheless, shape and deformation should not be considered independently from each other.…”

Section: Analyzing Myocardial Shape and Deformationmentioning

confidence: 99%

Characterizing interactions between cardiac shape and deformation by non-linear manifold learning

Maxime

Moceri

Clarysse

et al. 2022

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

“…The networks mentioned above have been applied to cardiac imaging, with a main focus on MRI [13]- [16]. In parallel, a pilot study has recently shown the adaptability of FlowNet-based networks to the characteristics of ultrasound images for motion estimation [2].…”

Section: Introductionmentioning

confidence: 99%

Motion Estimation by Deep Learning in 2D Echocardiography: Synthetic Dataset and Validation

Evain

Sun

Faraz

et al. 2022

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Motion estimation in echocardiography plays an important role in the characterization of cardiac function, allowing the computation of myocardial deformation indices. However, there exist limitations in clinical practice, particularly with regard to the accuracy and robustness of measurements extracted from images. We therefore propose a novel deep learning solution for motion estimation in echocardiography. Our network corresponds to a modified version of PWC-Net which achieves high performance on ultrasound sequences. In parallel, we designed a novel simulation pipeline allowing the generation of a large amount of realistic B-mode sequences. These synthetic data, together with strategies during training and inference, were used to improve the performance of our deep learning solution, which achieved an average endpoint error of 0.07± 0.06 mm per frame and 1.20±0.67 mm between ED and ES on our simulated dataset. The performance of our method was further investigated on 30 patients from a publicly available clinical dataset acquired from a GE system. The method showed promise by achieving a mean absolute error of the global longitudinal strain of 2.5 ± 2.1% and a correlation of 0.77 compared to GLS derived from manual segmentation, much better than one of the most efficient methods in the state-of-the-art (namely the FFT-Xcorr block-matching method). We finally evaluated our method on an auxiliary dataset including 30 patients from another center and acquired with a different system. Comparable results were achieved, illustrating the ability of our method to maintain high performance regardless of the echocardiographic data processed.

show abstract

Machine Learning Approaches for Myocardial Motion and Deformation Analysis

Cited by 21 publications

References 93 publications

Forecasting the Applied Deep Learning Tools in Enhancing Food Quality for Heart Related Diseases Effectively: A Study Using Structural Equation Model Analysis

Forecasting the Applied Deep Learning Tools in Enhancing Food Quality for Heart Related Diseases Effectively: A Study Using Structural Equation Model Analysis

Characterizing interactions between cardiac shape and deformation by non-linear manifold learning

Motion Estimation by Deep Learning in 2D Echocardiography: Synthetic Dataset and Validation

Contact Info

Product

Resources

About