Deep-learning strategy for pulmonary artery-vein classification of non-contrast CT images

Nardelli, Pietro; Jimenez Carretero, Daniel; Bermejo Peláez, David; Ledesma Carbayo, Maria Jesus; Rahaghi, Farbod N. y San José Estépar, Raúl (2017). Deep-learning strategy for pulmonary artery-vein classification of non-contrast CT images. En: "IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)", 18/04/2017 - 21/042017, Melbourne, VIC, Australia. pp. 1-4. https://doi.org/10.1109/ISBI.2017.7950543.

Descripción

Título: Deep-learning strategy for pulmonary artery-vein classification of non-contrast CT images
Autor/es:
  • Nardelli, Pietro
  • Jimenez Carretero, Daniel
  • Bermejo Peláez, David
  • Ledesma Carbayo, Maria Jesus
  • Rahaghi, Farbod N.
  • San José Estépar, Raúl
Tipo de Documento: Ponencia en Congreso o Jornada (Sin especificar)
Título del Evento: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
Fechas del Evento: 18/04/2017 - 21/042017
Lugar del Evento: Melbourne, VIC, Australia
Título del Libro: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
Título de Revista/Publicación: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
Fecha: 2017
Materias:
Palabras Clave Informales: Artery-vein segmentation, convolutional neural networks, Frangi filter, lung
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Ingeniería Electrónica
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (1MB) | Vista Previa

Resumen

Artery-vein classification on pulmonary computed tomography (CT) images is becoming of high interest in the scientific community due to the prevalence of pulmonary vascular disease that affects arteries and veins through different mechanisms. In this work, we present a novel approach to automatically segment and classify vessels from chest CT images. We use a scale-space particle segmentation to isolate vessels, and combine a convolutional neural network (CNN) to graph-cut (GC) to classify the single particles. Information about proximity of arteries to airways is learned by the network by means of a bronchus enhanced image. The methodology is evaluated on the superior and inferior lobes of the right lung of twenty clinical cases. Comparison with manual classification and a Random Forests (RF) classifier is performed. The algorithm achieves an overall accuracy of 87% when compared to manual reference, which is higher than the 73% accuracy achieved by RF.

Más información

ID de Registro: 50703
Identificador DC: http://oa.upm.es/50703/
Identificador OAI: oai:oa.upm.es:50703
Identificador DOI: 10.1109/ISBI.2017.7950543
URL Oficial: https://ieeexplore.ieee.org/document/7950543/
Depositado por: Memoria Investigacion
Depositado el: 28 May 2018 17:49
Ultima Modificación: 28 May 2018 17:49
  • InvestigaM
  • GEO_UP4
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM