A SR-Net 3D-to-2D architecture for paraseptal emphysema segmentation

Bermejo Peláez, David and Okajima, Y. and Washko, George R. and Ledesma Carbayo, Maria Jesus and San José Estepar, Raúl (2019). A SR-Net 3D-to-2D architecture for paraseptal emphysema segmentation. In: "2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)", 08/04/2019 - 11/04/2019, Venecia, Italia. ISBN 978-1-5386-3641-1. pp. 303-306. https://doi.org/10.1109/ISBI.2019.8759184.

Description

Title: A SR-Net 3D-to-2D architecture for paraseptal emphysema segmentation
Author/s:
  • Bermejo Peláez, David
  • Okajima, Y.
  • Washko, George R.
  • Ledesma Carbayo, Maria Jesus
  • San José Estepar, Raúl
Item Type: Presentation at Congress or Conference (Unspecified)
Event Title: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
Event Dates: 08/04/2019 - 11/04/2019
Event Location: Venecia, Italia
Title of Book: Proceedings of 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
Título de Revista/Publicación: 2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019)
Date: 2019
ISBN: 978-1-5386-3641-1
ISSN: 1945-7928
Subjects:
Freetext Keywords: Parasetal emphysema; Deep learning; Convolutional neural networks; Segmentation
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

Paraseptal emphysema (PSE) is a relatively unexplored emphysema subtype that is usually asymptomatic, but recently associated with interstitial lung abnormalities which are related with clinical outcomes, including mortality. Previous local-based methods for emphysema subtype quantification do not properly characterize PSE. This is in part for their inability to properly capture the global aspect of the disease, as some the PSE lesions can involved large regions along the chest wall. It is our assumption, that path-based approaches are not well-suited to identify this subtype and segmentation is a better paradigm. In this work we propose and introduce the Slice-Recovery network (SR-Net) that leverages 3D contextual information for 2D segmentation of PSE lesions in CT images. For that purpose, a novel convolutional network architecture is presented, which follows an encoding-decoding path that processes a 3D volume to generate a 2D segmentation map. The dataset used for training and testing the method comprised 664 images, coming from 111 CT scans. The results demonstrate the benefit of the proposed approach which incorporate 3D context information to the network and the ability of the proposed method to identify and segment PSE lesions with different sizes even in the presence of other emphysema subtypes in an advanced stage.

Funding Projects

TypeCodeAcronymLeaderTitle
Government of SpainRTI2018-098682-B-I00ST-IMMUNOUnspecifiedAprendizaje profundo espacio-temporal para la predicción de respuesta de tratamiento por inmunoterapia

More information

Item ID: 64110
DC Identifier: http://oa.upm.es/64110/
OAI Identifier: oai:oa.upm.es:64110
DOI: 10.1109/ISBI.2019.8759184
Official URL: https://ieeexplore.ieee.org/abstract/document/8759184
Deposited by: Memoria Investigacion
Deposited on: 10 Nov 2020 18:38
Last Modified: 10 Nov 2020 18:38
  • 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