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

Nardelli, Pietro and Jimenez Carretero, Daniel and Bermejo Peláez, David and Ledesma Carbayo, Maria Jesus and Rahaghi, Farbod N. and San José Estépar, Raúl (2017). Deep-learning strategy for pulmonary artery-vein classification of non-contrast CT images. In: "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.

Description

Title: Deep-learning strategy for pulmonary artery-vein classification of non-contrast CT images
Author/s:
  • Nardelli, Pietro
  • Jimenez Carretero, Daniel
  • Bermejo Peláez, David
  • Ledesma Carbayo, Maria Jesus
  • Rahaghi, Farbod N.
  • San José Estépar, Raúl
Item Type: Presentation at Congress or Conference (Unspecified)
Event Title: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
Event Dates: 18/04/2017 - 21/042017
Event Location: Melbourne, VIC, Australia
Title of Book: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
Título de Revista/Publicación: IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
Date: 2017
Subjects:
Freetext Keywords: Artery-vein segmentation, convolutional neural networks, Frangi filter, lung
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería Electrónica
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview

Abstract

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.

More information

Item ID: 50703
DC Identifier: http://oa.upm.es/50703/
OAI Identifier: oai:oa.upm.es:50703
DOI: 10.1109/ISBI.2017.7950543
Official URL: https://ieeexplore.ieee.org/document/7950543/
Deposited by: Memoria Investigacion
Deposited on: 28 May 2018 17:49
Last Modified: 28 May 2018 17:49
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM