Textured graph-model of the lungs for tuberculosis type classification and drug resistance prediction : participation in ImageCLEF 2017

Dicente Cid, Yashin (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; University of Geneva, Switzerland) ; Batmanghelich, Kayhan (University of Pittsburgh, USA) ; Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) ; University of Geneva, Switzerland)

In 2017, the ImageCLEF benchmark proposed a task based on CT (Computed Tomography) images of patients with tuberculosis (TB). This task was divided into two subtasks: multi-drug resistance prediction, and TB type detection. In this work we present a graph-model of the lungs capable of characterizing TB patients with different lung problems. This graph contains a fixed number of nodes with weighted edges based on distance measures between texture descriptors computed on the nodes. This model attempts to encode the texture distribution along the lungs, making it suitable for describing patients with different tuberculosis types. The results show the strength of the technique, leading to best results in the competition for multi-drug resistance (AUC = 0.5825) and good results in the tuberculosis type detection (Cohen’s Kappa coef. = 0.1623), with many of the good runs being fairly close.


Keywords:
Conference Type:
full paper
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Informatique
Publisher:
Dublin, Ireland, 11-14 September 2017
Date:
2017-09
Dublin, Ireland
11-14 September 2017
Pagination:
10 p.
Published in:
Proceedings of the CLEF 2017 Working Notes
ISSN:
1613-0073
External resources:
Appears in Collection:



 Record created 2017-12-23, last modified 2019-06-11

Fulltext:
Download fulltext
PDF

Rate this document:

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