Full text
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview |
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.
Title: | Deep-learning strategy for pulmonary artery-vein classification of non-contrast CT images |
---|---|
Author/s: |
|
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 |
|
PDF
- Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB) | Preview |
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.
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 |