V. Barrios

Universidad de Carabobo, UC, Valencia, Estado Carabobo, Venezuela

Are you V. Barrios?

Claim your profile

Publications (14)1.83 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: A contour-based automatic recognition system was applied to classify intraductal breast carcinoma into high nuclear grade and low nuclear grade in a digitized histologic image. The image discriminating characteristics were selected by their invariability condition to rotation and translation. They were acquired from cellular contours information. The totally interconnected multilayer perceptron network architecture was selected, and it was trained with the error back propagation algorithm. Forty cases were analyzed by the system and the diagnoses were compared with that of pathologist consensus, obtaining agreement in 97.5% (p < .00001 of cases). The system may become a very useful tool for the pathologist in the definitive classification of intraductal carcinoma.
    The Breast Journal 07/1998; 4(4):238-44. · 1.83 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This work presents 3D cardiac images rendering based on volumetrics of plane sections obtained from the cardiac wall segmentation. This work introduces a non-rigid model based on physics as a segmentation method. An object is constructed in the shape of a polygon of n vertices, with masses on each of them, interconnected with springs to each other. The model is deformed when exposed to a force field that moves it toward the desired contour. In order to obtain the volumetric reconstructed rendering of the ventricular cavity, the method was used on a series of apical views of the heart of a healthy person. The views belong to radial sections (equally spaced in angle) which, alter segmentation, and by means of a bilinear interpolation process, permitted the reconstruction of a 3D image of the ventricular cavity.
    Computers in Cardiology, 1996; 10/1996
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The formation of the echocardiographic signal, that goes from the transducer to the 2D echo image, was simulated upon a 3D cardiac tissue image. Images of tissue are obtained by mathematical simulation, and a serie of histological slices of cardiac tissue. These slices were observed using an optical microscope at a calibration of 10 microns per pixel. Slices are corrected for translation and rotation errors in order to obtain the 3D reconstruction. Cardiac contraction dynamics are simulated with a simple three-transformation model Transducers are simulated with a cosine-moduled Gaussian three-dimensional spread function. The system outputs two signals: a radio-frecuency image and an echocardiographic image. Texture features are analyzed as a function of cardiac dynamics. Results' analysis shows the influence of the cellular and connective components of cardiac tissue in the echocardiographic response.
    Computers in Cardiology; 09/1996
  • [Show abstract] [Hide abstract]
    ABSTRACT: Presents a study of intensity variations in the echocardiographic image during myocardial contraction. Both simulated and actual tissue were used to study this phenomenon. One of the approaches was to simulate echocardiographic response to cardiac tissue variations. In order to perform this task, we developed four modules which we have designated as: Tissue, Dynamics, Equipment and Texture. In the first module, we research two alternatives: mathematically simulated tissue and actual tissue obtained from histological samples of diseased hearts. The second module simulates contraction's dynamics, using a three-transformations model (displacement, rotation and contraction) on an acoustic-impedance image. The third module simulates the transducers by varying the ultrasonic beam's frequency and dispersion. The equipment outputs two signals: a radio-frequency image and an echocardiographic image. Both signals are then analyzed by the Texture module. This also includes an analysis of the mean values. The final goal of the project is to analyze tissue's characterization, in order to infer about the cardiac fiber's condition based on the space-time analysis of the two output signals.
    Computers in Cardiology 1995; 10/1995
  • [Show abstract] [Hide abstract]
    ABSTRACT: During the analysis of histological images of cancer tissue, the specialist must carefully look for cellular shapes and sizes, as well as orientation, in order to make a diagnosis. This work develops an interactive auxiliary method to help the physician to quickly trace the edge for each cell, as selected by him (her) in a microscopic image. The method is based in a gradient and gray-level study of the image, along a series of radials centered in a selected cell. The analysis outputs a set of points from which the edge points are selected. The edge tracing is then performed using the B-spline method
    01/1995;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Two tracking methods based on matching techniques were used to detect the motion of ventricular walls in cardiac echocardiographic images. Two types of Regions of Interest (ROI) were selected. The first based on tracking blocks of pixels using Sum of Absolute Differences (SAD) and the Correlation Coefficient (CORR), as matching criteria. The second based on gray profile cross-sections along an axis, that passes through the point of interest. In this other case, Covariance (COV) and Correlation Coefficients (CORR) were used as the matching criteria. All four methods were tested with echocardiographic images with different quality levels. The interest points were chosen along the ventricle borders and the myocardial middle zone
    Engineering in Medicine and Biology Society, 1994. Engineering Advances: New Opportunities for Biomedical Engineers. Proceedings of the 16th Annual International Conference of the IEEE; 12/1994
  • [Show abstract] [Hide abstract]
    ABSTRACT: A multi-layer perceptron neural network, with a backpropagation training algorithm, was employed for edge detection and tracing in cancer cellular tissue images, obtained with an optical microscope. This network predicts the cellular edges' location, based on information regarding a small known section of it, at every point. We use a metaphorical “worm”, based in the neural network, who crawls along the edge and “feeds” from the points it finds along the same. The method was used with a set of 256 gray-level test images, in order to detect edges of known geometric shapes, under controlled noise conditions. It was later applied to mammary tissue images. Additionally, this method provides some learning capabilities, which yield it's application to several image types
    01/1994;
  • [Show abstract] [Hide abstract]
    ABSTRACT: A method was developed to detect the ventricle wall for the parasternal short axis view in two-dimensional echocardiography. The ventricular shape is modeled with a very simple parametric closed curve: an ellipse defined by four parameters. A genetic algorithm (GA) guides the elliptical shape and its position to find an optimum result. It minimizes one border dependent function, obtained after sampling 56 points in the ellipse. These points are located at the septum region (19) and at the ventricular posterior wall (37). The obtained solution is considered excellent as a first approximation to the real border. Then a second search complements the final solution. The ventricular shape is followed along one image sequence, basing the search space on the solutions given by the previous image. Medical knowledge about the cardiac structure and the image acquisition process is added to evaluate the function
    Computers in Cardiology 1993, Proceedings.; 10/1993
  • [Show abstract] [Hide abstract]
    ABSTRACT: Not Available
    Engineering in Medicine and Biology Society, 1993. Proceedings of the 15th Annual International Conference of the IEEE; 02/1993
  • [Show abstract] [Hide abstract]
    ABSTRACT: Not Available
    Engineering in Medicine and Biology Society, 1993. Proceedings of the 15th Annual International Conference of the IEEE; 02/1993
  • [Show abstract] [Hide abstract]
    ABSTRACT: A PC compatible board, based on the special purpose 32-bit microprocessor TMS34010 G S P T M (Graphic System Processor), for cardiac image sequence acquisition has been designed. The board is one of the components of an i mage processing workstation aimed at the study of echocardiographic and angiographic image sequences over the extension of the entire cardiac cycle. In a first approach the system has been focused to texture variability analysis of echocardiographic images and to the analysis of cardiac muscle mobility by means of optical flow computation in sequences of echocardiographic images.
    Engineering in Medicine and Biology Society, 1992 14th Annual International Conference of the IEEE; 12/1992
  • [Show abstract] [Hide abstract]
    ABSTRACT: An algorithm based on texture analysis for the extraction of endocardial borders in bi-dimensional echocardiographic images is presented. Using the Inverse Difference Moment (IDM) of the original image, an image that contains texture information is constructed and is used as a texture channel. Application of appropriate thresholding on projections of the cooccurrence matrix of the texture channel allows separation of regions and borders. The method has been applied to apical four chamber views and paraesternal short axis views, showing excellent results in determining reliable borders. Aditionally, by adding some detection criteria and medical knowledge of the heart, the algorithm can detect borders in incomplete and noisy images.
    Engineering in Medicine and Biology Society, 1992 14th Annual International Conference of the IEEE; 12/1992
  • [Show abstract] [Hide abstract]
    ABSTRACT: A tool for image texture analysis (TITA) has been developed for application to two-dimensional echocardiographic images. Through a user-friendly environment, spatio-temporal changes in texture can be analyzed to characterize the tissue or to provide segmentation and border detection. As an example of the application of TITA, the implementation of an inverse difference moment based algorithm for the extraction of endocardial boundaries from echocardiographic images is presented. The proposed method has been applied to apical four chamber and paraesternal short axis views, showing excellent results even in difficult images. It is possible to conclude that the difference image of echocardiographic frames contains sufficient information for accurate detection of borders and regions
    Computers in Cardiology 1992. Proceedings.; 11/1992
  • V. Barrios, G. Montilla, M. Cerrolaza

Publication Stats

14 Citations
1.83 Total Impact Points

Top Journals

Institutions

  • 1996
    • Universidad de Carabobo, UC
      • Centro de Procesamiento de Imágenes (CPI)
      Valencia, Estado Carabobo, Venezuela