Examinando por Autor "Bermejo, Javier"

Mostrando 1 - 15 de 15

A New Method for Single-Step Robust Post-Processing of Flow Color Doppler M-Mode Images Using Support Vector Machines
(2009-06-15T10:08:10Z) Conde Pardo, P; Guerrero Curieses, A; Rojo-Álvarez, José Luis; Yotti, R; Requena Carrión, J; Antoranz, José Carlos; Bermejo, Javier
Intra-cardiac pressure gradients (ICPG) are usually es timated by post-processing of flow Color Doppler M-mode images (CDMMI) by using a sequence of processing steps. We propose a novel image processing method which gives a single-step approximation of the ICPG image, based on a simple, yet specifically developed, Support Vector Machine (SVM) algorithm. Our method only requires the SVM estimation of the blood velocity from the CDMMI. Given that ICPG images are obtained by deterministic operators (Euler's momentum equation) on the blood velocity, the ICPG estimation is a simple model that consists of the same coefficients and the operator applied to the Mercer's kernel. A diverse-width Mercer's kernel is proposed, as an alternative to conventional Radial Basis Function kernel. Simulations on a synthetic model and approximations of a real example image, trained with up to 10% of the pixels, show the possibilities of this new single-step postprocessing method.
A Noninvasive Method for Assessing Impaired Diastolic Suction in Patients With Dilated Cardiomyopathy
(2009-07-14T11:31:16Z) Yotti, R; Bermejo, Javier; Antoranz, José Carlos; Desco, Mar; Cortina, Cristina; Rojo-Álvarez, José Luis; Allué, Carmen; Martín, Laura; Moreno, Mar; Serrano, JA; Muñoz, Roberto; García Fernández, MA
Caracterización no invasiva de la contractilidad miocárdica mediante el análisis de los gradientes de presión intraventricular derivados de imágenes de Doppler-color
(2009-07-28T10:11:23Z) Yotti, R; Bermejo, Javier; Desco, Mar; Cortina, Cristina; Antoranz, José Carlos; Rojo-Álvarez, José Luis; Moreno, Mar; García Fernández, MA
Dependencia de la precarga y postcarga de los gradientes de presión intraventricular sistólicos medidos mediante ecocardiografía Doppler
(2009-07-28T10:20:30Z) Yotti, R; Bermejo, Javier; Desco, Mar; Antoranz, José Carlos; Rojo-Álvarez, José Luis; Cortina, Cristina; Rodríguez Abella, Hugo; García Fernández, MA
Doppler-Derived Ejection Intraventricular Pressure Gradients Provide a Reliable Assessment of Left Ventricular Systolic Chamber Function
(2009-07-23T10:19:06Z) Yotti, R; Bermejo, Javier; Desco, Mar; Antoranz, José Carlos; Rojo-Álvarez, José Luis; Cortina, Cristina; Allué, Carmen; Rodríguez Abella, Hugo; Moreno, Mar; García Fernández, Miguel Ángel
Effect of Spatial, Temporal, and Velocity Resolution on Doppler Tissue Image Derived Indices
(2009-06-15T09:59:02Z) Rojo-Álvarez, José Luis; Bermejo, Javier; Rodríguez González, AB; Yotti, R; Martínez Fernández, A; García Fernández, MA; Antoranz, José Carlos
Many indices derived from color Roppler Tissue Imaging (UTI) are computed mathematically from the velociy fields provided by the ultrasound scanner We developed a procedure for assessing the uncertainty that temporal, spatial, and velociry resolution causes on cardiovascular parameter5 derived from myocardial velociry. A first-order Taylor's series for the functional relationship between velocity and the cardiac index under study is proposed, and analytically solved by using the chain rule. Pedormance on myocardial acceleration, strain, and strain rate, was tested both on a simulation model (symbolic calculations) and on a clinical image example. Velociry and temporal resolutions were the most determinant on DTI-derived parameters, and increasing color-Doppler bit-depth from 5 to 7 bils reduced to less than 10% the uncertainty of all the analyzed indices. Taylor-based error bounds are a useful tool tu assess the effect of resolution on quantitative cardiovascular indices derived from tissue velocity measurements.
Estimación Paramétrica de la Impedancia de Entrada Arterial: Alcance y Limitaciones
(2009-07-28T09:47:27Z) Arenas García, J.; Rojo-Álvarez, José Luis; Yotti, R; Antoranz, José Carlos; García Fernández, MA; Bermejo, Javier
El estudio de la función ventricular a través de la impedancia de entrada arterial se ha realizado habitualmente mediante el desarrollo en Series de Fourier de la presión aórtica y del flujo de salida valvular. Aunque el modelado paramétrico ha sido propuesto como un método alternativo de estimación de la impedancia, no ha sido utilizado en la práctica. En este trabajo se estudia el valor y las limitaciones de los métodos de modelado paramétrico utilizando señales de presión y flujo obtenidas in vivo. Se concluye que la estimación de la admitancia, el inverso de la impedancia, es un problema clínicamente equivalente pero numéricamente mejor condicionado para la estimación paramétrica.
Estimation of Reference Indices of Left Ventricular Chamber Function from Echocardiographic Images with Multidimensional Kernel Methods
(IEEE, 2012-09-09) Santiago-Mozos, Ricardo; Rojo-Álvarez, José Luis; Antoranz, J Carlos; Rodriguez, Daniel; Desco, Mar; Barrio, Alicia; Benito, Yolanda; Yotti, Raquel; Bermejo, Javier
Advanced nonlinear estimation methods can compete with their linear counterparts for the estimation of left ventricular (LV) function indices from color-Doppler M-mode images. We benchmarked three methods: Support Vector Regression, Partial Least Squares and Principal Component Regression using linear and non-linear (Gaussian) kernels. Two reference indices were directly estimated from the images, namely, the peak-systolic elastance (Emax) and the time-constant of LV relaxation (Tau). We found linear methods performing slightly better for predicting Emax, an easier task, but they were outperformed by non-linear procedures when predicting Tau, a harder estimation problem.
Estimation of the End of Ejection in aortic Stenosis. An Unreported Source of Error in the Invasive Assessment of Severity
(2009-07-23T10:11:51Z) Bermejo, Javier; Rojo-Álvarez, José Luis; Antoranz, José Carlos; Abel, Mónica; G. Burwash, Ian; Yotti, R; Moreno, Mar; García Fernández, Miguel Ángel; G. Lehmann, Kenneth; M. Otto, Catherine
Impact of Image Spatial, Temporal, and Velocity Resolutions on Cardiovascular Indices Derived from Color-Doppler Echocardiography
(2009-07-23T09:04:29Z) Rojo-Álvarez, José Luis; Bermejo, Javier; Rodríguez González, Ana Belén; Martínez Fernández, A; Yotti, R; García Fernández, Miguel Ángel; Antoranz, José Carlos
Quantitative processing of color-Doppler echocardiographic images has substantially improved noninvasive assessment of cardiac physiology. Many indices are computed from the velocity fields derived either from color-Doppler tissue imaging (DTI), such as acceleration, strain and strain-rate, or from blood-flow color-Doppler, such as intracardiac pressure gradients (ICPG). All of these indices are dependent on the finite resolution of the ultrasound scanner. Therefore, we developed an image-dependent method for assessing the influence of temporal, spatial, and velocity resolutions, on cardiovascular parameters derived from velocity images. In order to focus our study on the spatial, temporal, and velocity resolutions of the digital image, we did not consider the effect of other sources of noise such as the interaction between ultrasound and tissue. A simple first-order Taylor's expansion was used to establish the functional relationship between the acquired image velocity and the calculated cardiac index. Resolutions were studied on: (a) myocardial acceleration, strain, and strain-rate from DTI, and (b) ICPG from blood-flow color-Doppler. The performance of Taylor's-based error bounds (TBEB) was demonstrated on simulated models and illustrated on clinical images. Velocity and temporal resolution were highly relevant for the accuracy of DTI-derived parameters and ICPGs. TBEB allow to assess the effects of ideal digital image resolution on quantitative cardiovascular indices derived from velocity measurements obtained by cardiac imaging techniques.
Noninvasive Assessment of Ejection Intraventricular Pressure Gradients
(2009-07-23T10:26:02Z) Yotti, R; Bermejo, Javier; Antoranz, José Carlos; Rojo-Álvarez, José Luis; Allué, Carmen; Silva, Jacobo; Desco, Mar; Moreno, Mar; García Fernández, Miguel Ángel
Noninvasive Assessment of the Right Ventricular Filling Pressure Gradient
(2009-07-23T10:33:36Z) Cortina, Cristina; Bermejo, Javier; Yotti, R; Desco, Mar; Rodríguez Pérez, Daniel; Antoranz, José Carlos; Rojo-Álvarez, José Luis; García, Damien; García Fernández, Miguel Ángel; Fernández Avilés, F.
Noninvasive Estimation of Maximum Elastance from Color-Doppler M-Mode Echocardiograms Using Support Vector Machines
(2009-06-15T09:52:52Z) Rojo-Álvarez, José Luis; Bermejo, Javier; Juarez Caballero, VM; Yotti, R; García Fernández, MA; Antoranz, José Carlos
On feature extraction for noninvasive kernel estimation of left ventricular chamber function indices from echocardiographic images
(2015-01-30) Santiago-Mozos, Ricardo; Rojo-Álvarez, José Luis; Antoranz, J. Carlos; Rodríguez-Pérez, Daniel; Yotti, Raquel; Bermejo, Javier; Elsevier
Two reference indices used to characterize left ventricular (LV) global chamber function are end-systolic peak elastance (EmaxEmax) and the time-constant of relaxation rate (¿ ). However, these two indices are very difficult to obtain in the clinical setting as they require invasive high-fidelity catheterization procedures. We have previously demonstrated that it is possible to approximate these indices noninvasively by digital processing color-Doppler M-mode (CDMM) images. The aim of the present study was twofold: (1) to study which feature extraction from linearly reduced input spaces yields the most useful information for the prediction of the haemodynamic variables from CDMM images; (2) to verify whether the use of nonlinear versions of those linear methods actually improves the estimation. We studied the performance and interpretation of different linearly transformed input spaces (raw image, discrete cosine transform (DCT) coefficients, partial least squares, and principal components regression), and we compared whether nonlinear versions of the above methods provided significant improvement in the estimation quality. Our results showed that very few input features suffice for providing a good (medium) quality estimator for EmaxEmax (for ¿), which can be readily interpreted in terms of the measured flows. Additional covariates should be included to improve the prediction accuracy of both reference indices, but especially in ¿ models. The use of efficient nonlinear kernel algorithms does improve the estimation quality of LV indices from CDMM images when using DCT input spaces that capture almost all energy.
Support Vector Analysis of Color-Doppler Images: A New Approach for Estimating Indices on Left Ventricular Function
(2006-08-01) Rojo-Álvarez, José Luis; Bermejo, Javier; Juárez Caballero, Víctor Manuel; Yotti, Raquel; Cortina, Cristina; García Fernández, Miguel Ángel; Antoranz, José Carlos
Reliable noninvasive estimators of global left ventricular (LV) chamber function remain unavailable. We have previously demonstrated a potential relationship between color-Doppler M-mode (CDMM) images and two basic indices of LV function: peak-systolic elastance (Emax) and the time-constant of LV relaxation (tau). Thus, we hypothesized that these two indices could be estimated noninvasively by adequate postprocessing of CDMM recordings. A semiparametric regression (SR) version of support vector machine (SVM) is here proposed for building a blind model, capable of analyzing CDMM images automatically, as well as complementary clinical information. Simultaneous invasive and Doppler tracings were obtained in nine mini-pigs in a high-fidelity experimental setup. The model was developed using a test and validation leave-one-out design. Reasonably acceptable prediction accuracy was obtained for both Emax (intraclass correlation coefficient 0.81) and ( 0. 61). For the first time, a quantitative, noninvasive estimation of cardiovascular indices is addressed by processing Doppler-echocardiography recordings using a learning-from-samples method.