Descripción
|
|
---|---|
Chronic Obstructive Pulmonary Disease (COPD) is the fourth leading cause of death worldwide and leads to two main phenotypes: chronic bronchitis and emphysema. Densitometric analysis in CT is widely accepted measurement of emphysema, however it may not be able to classify it into subtypes. Others methods based on texture information have been proposed to carry out an emphysema classification. Texture patterns lead to six distinct types of emphysematous tissue: normal tissue (NT), paraseptal (PS), panlobular (PL) and mild, moderate and severe centrilobular (CL1, CL2, CL3) emphysema. In this article we propose and validate an emphysema pattern classification tool in CT images based on a Multi-scale Convolutional Neural Network (MCNN). | |
Internacional
|
Si |
Nombre congreso
|
31st Computer Assisted Radiology and Surgery (CARS 2017) |
Tipo de participación
|
960 |
Lugar del congreso
|
Barcelona- España |
Revisores
|
Si |
ISBN o ISSN
|
1861-6410 |
DOI
|
10.1007/s11548-017-1588-3 |
Fecha inicio congreso
|
20/06/2017 |
Fecha fin congreso
|
24/06/2017 |
Desde la página
|
141 |
Hasta la página
|
143 |
Título de las actas
|
Int. J. Comput. Assist. Radiol. Surg., vol. 12, no. suppl. 1, |