A lung graph–model for pulmonary hypertension and pulmonary embolism detection on DECT images

Dicente Cid, Yashin (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; University of Geneva) ; Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; University of Geneva ; 3 Martinos Center for Biomedical Imaging, Charlestown, USA) ; Platon, Alexandra (University Hospitals of Geneva (HUG), Switzerland) ; Janssens, Jean-Paul (University Hospitals of Geneva (HUG), Switzerland) ; Lador, Frederic (University Hospitals of Geneva (HUG), Switzerland) ; Poletti, Pierre-Alexandre (University Hospitals of Geneva (HUG), Switzerland) ; Depeursinges, Adrien (Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland)

This article presents a novel graph–model approach encoding the relations between the perfusion in several regions of the lung extracted from a geometry–based atlas. Unlike previous approaches that individually analyze regions of the lungs, our method evaluates the entire pulmonary circulatory network for the classification of patients with pulmonary embolism and pulmonary hypertension. An undirected weighted graph with fixed structure is used to encode the network of intensity distributions in Dual Energy Computed Tomography (DECT) images. Results show that the graph–model presented is capable of characterizing a DECT dataset of 30 patients affected with disease and 26 healthy patients, achieving a discrimination accuracy from 0.77 to 0.87 and an AUC between 0.73 and 0.86. This fully automatic graph–model of the lungs constitutes a novel and effective approach for exploring the various patterns of pulmonary perfusion of healthy and diseased patients.


Keywords:
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Informatique
Publisher:
Cham, Springer
Date:
2017-01
Cham
Springer
Pagination:
Pp. 58-68
Published in:
Medical Computer Vision and Bayesian and Graphical Models for Biomedical Imaging MICCAI 2016 International Workshops, MCV and BAMBI, Athens, Greece, October 21, 2016, Revised Selected Papers
Author of the book:
Müller, Henning ; (ed.) ; University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)
DOI:
ISBN:
978-3-319-61187-7
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2019-01-30, last modified 2019-01-30

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)