Articles producció científica> Enginyeria Informàtica i Matemàtiques

Fully Automated Breast Density Segmentation and Classification Using Deep Learning

  • Datos identificativos

    Identificador: imarina:9093105
    Handle: http://hdl.handle.net/20.500.11797/imarina9093105
  • Autores:

    Saffari, Nasibeh
    Rashwan, Hatem A.
    Abdel-Nasser, Mohamed
    Kumar Singh, Vivek
    Arenas, Meritxell
    Mangina, Eleni
    Herrera, Blas
    Puig, Domenec
  • Otros:

    Autor según el artículo: Saffari, Nasibeh; Rashwan, Hatem A.; Abdel-Nasser, Mohamed; Kumar Singh, Vivek; Arenas, Meritxell; Mangina, Eleni; Herrera, Blas; Puig, Domenec;
    Departamento: Enginyeria Informàtica i Matemàtiques Enginyeria Electrònica, Elèctrica i Automàtica
    e-ISSN: 2075-4418
    Autor/es de la URV: Abdellatif Fatahallah Ibrahim Mahmoud, Hatem / Abdelnasser Mohamed Mahmoud, Mohamed / Arenas Prat, Meritxell / Herrera Gómez, Blas / Puig Valls, Domènec Savi
    Palabras clave: Women Tissue Risk Patterns Mammograms Images Generative adversarial networks Deep learning Convolutional neural network Cancer Breast density Breast cancer
    Resumen: Breast density estimation with visual evaluation is still challenging due to low contrast and significant fluctuations in the mammograms' fatty tissue background. The primary key to breast density classification is to detect the dense tissues in the mammographic images correctly. Many methods have been proposed for breast density estimation; nevertheless, most of them are not fully automated. Besides, they have been badly affected by low signal-to-noise ratio and variability of density in appearance and texture. This study intends to develop a fully automated and digitalized breast tissue segmentation and classification using advanced deep learning techniques. The conditional Generative Adversarial Networks (cGAN) network is applied to segment the dense tissues in mammograms. To have a complete system for breast density classification, we propose a Convolutional Neural Network (CNN) to classify mammograms based on the standardization of Breast Imaging-Reporting and Data System (BI-RADS). The classification network is fed by the segmented masks of dense tissues generated by the cGAN network. For screening mammography, 410 images of 115 patients from the INbreast dataset were used. The proposed framework can segment the dense regions with an accuracy, Dice coefficient, Jaccard index of 98%, 88%, and 78%, respectively. Furthermore, we obtained precision, sensitivity, and specificity of 97.85%, 97.85%, and 99.28%, respectively, for breast density classification. This study's findings are promising and show that the proposed deep learning-based techniques can produce a clinically useful computer-aided tool for breast density analysis by digital mammography.
    Áreas temáticas: Medicine, general & internal Clinical biochemistry
    Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
    Direcció de correo del autor: hatem.abdellatif@urv.cat mohamed.abdelnasser@urv.cat blas.herrera@urv.cat domenec.puig@urv.cat meritxell.arenas@urv.cat
    Identificador del autor: 0000-0002-1074-2441 0000-0003-2924-9195 0000-0002-0562-4205 0000-0003-0815-2570
    Fecha de alta del registro: 2023-05-14
    Versión del articulo depositado: info:eu-repo/semantics/publishedVersion
    Enlace a la fuente original: https://www.mdpi.com/2075-4418/10/11/988
    URL Documento de licencia: http://repositori.urv.cat/ca/proteccio-de-dades/
    Referencia al articulo segun fuente origial: Diagnostics. 10 (11):
    Referencia de l'ítem segons les normes APA: Saffari, Nasibeh; Rashwan, Hatem A.; Abdel-Nasser, Mohamed; Kumar Singh, Vivek; Arenas, Meritxell; Mangina, Eleni; Herrera, Blas; Puig, Domenec; (2020). Fully Automated Breast Density Segmentation and Classification Using Deep Learning. Diagnostics, 10(11), -. DOI: 10.3390/diagnostics10110988
    DOI del artículo: 10.3390/diagnostics10110988
    Entidad: Universitat Rovira i Virgili
    Año de publicación de la revista: 2020
    Tipo de publicación: Journal Publications
  • Palabras clave:

    Clinical Biochemistry,Medicine, General & Internal
    Women
    Tissue
    Risk
    Patterns
    Mammograms
    Images
    Generative adversarial networks
    Deep learning
    Convolutional neural network
    Cancer
    Breast density
    Breast cancer
    Medicine, general & internal
    Clinical biochemistry
  • Documentos:

  • Cerca a google

    Search to google scholar