Articles producció científica> Enginyeria Informàtica i Matemàtiques

The impact of pixel resolution, integration scale, preprocessing, and feature normalization on texture analysis for mass classification in mammograms

  • Datos identificativos

    Identificador: imarina:9282609
    Autores:
    Abdel-Nasser, MohamedMelendez, JaimeMoreno, AntonioPuig, Domenec
    Resumen:
    Texture analysis methods are widely used to characterize breast masses in mammograms. Texture gives information about the spatial arrangement of the intensities in the region of interest. This information has been used in mammogram analysis applications such as mass detection, mass classification, and breast density estimation. In this paper, we study the effect of factors such as pixel resolution, integration scale, preprocessing, and feature normalization on the performance of those texture methods for mass classification. The classification performance was assessed considering linear and nonlinear support vector machine classifiers. To find the best combination among the studied factors, we used three approaches: greedy, sequential forward selection (SFS), and exhaustive search. On the basis of our study, we conclude that the factors studied affect the performance of texture methods, so the best combination of these factors should be determined to achieve the best performance with each texture method. SFS can be an appropriate way to approach the factor combination problem because it is less computationally intensive than the other methods. © 2016 Mohamed Abdel-Nasser et al.
  • Otros:

    Autor según el artículo: Abdel-Nasser, Mohamed; Melendez, Jaime; Moreno, Antonio; Puig, Domenec
    Departamento: Enginyeria Informàtica i Matemàtiques
    Autor/es de la URV: Abdelnasser Mohamed Mahmoud, Mohamed / Moreno Ribas, Antonio / Puig Valls, Domènec Savi
    Palabras clave: X ray screens Texture analysis method Support vector machines Spatial arrangements Sequential forward selection Pixels Nonlinear support vector machines Mass classifications Mammography Image segmentation Image processing Feature normalization Classification performance Classification (of information) Breast density estimation
    Resumen: Texture analysis methods are widely used to characterize breast masses in mammograms. Texture gives information about the spatial arrangement of the intensities in the region of interest. This information has been used in mammogram analysis applications such as mass detection, mass classification, and breast density estimation. In this paper, we study the effect of factors such as pixel resolution, integration scale, preprocessing, and feature normalization on the performance of those texture methods for mass classification. The classification performance was assessed considering linear and nonlinear support vector machine classifiers. To find the best combination among the studied factors, we used three approaches: greedy, sequential forward selection (SFS), and exhaustive search. On the basis of our study, we conclude that the factors studied affect the performance of texture methods, so the best combination of these factors should be determined to achieve the best performance with each texture method. SFS can be an appropriate way to approach the factor combination problem because it is less computationally intensive than the other methods. © 2016 Mohamed Abdel-Nasser et al.
    Áreas temáticas: Optics Electronic, optical and magnetic materials Atomic and molecular physics, and optics
    Direcció de correo del autor: mohamed.abdelnasser@urv.cat antonio.moreno@urv.cat domenec.puig@urv.cat
    Identificador del autor: 0000-0002-1074-2441 0000-0003-3945-2314 0000-0002-0562-4205
    Fecha de alta del registro: 2024-10-12
    Versión del articulo depositado: info:eu-repo/semantics/publishedVersion
    Enlace a la fuente original: https://www.hindawi.com/journals/ijo/2016/1370259/
    URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
    Referencia al articulo segun fuente origial: International Journal Of Optics. 2016 1370259-
    Referencia de l'ítem segons les normes APA: Abdel-Nasser, Mohamed; Melendez, Jaime; Moreno, Antonio; Puig, Domenec (2016). The impact of pixel resolution, integration scale, preprocessing, and feature normalization on texture analysis for mass classification in mammograms. International Journal Of Optics, 2016(), 1370259-. DOI: 10.1155/2016/1370259
    DOI del artículo: 10.1155/2016/1370259
    Entidad: Universitat Rovira i Virgili
    Año de publicación de la revista: 2016
    Tipo de publicación: Journal Publications
  • Palabras clave:

    Atomic and Molecular Physics, and Optics,Electronic, Optical and Magnetic Materials,Optics
    X ray screens
    Texture analysis method
    Support vector machines
    Spatial arrangements
    Sequential forward selection
    Pixels
    Nonlinear support vector machines
    Mass classifications
    Mammography
    Image segmentation
    Image processing
    Feature normalization
    Classification performance
    Classification (of information)
    Breast density estimation
    Optics
    Electronic, optical and magnetic materials
    Atomic and molecular physics, and optics
  • Documentos:

  • Cerca a google

    Search to google scholar