Share Email Print

Proceedings Paper

Localized Fisher vector representation for pathology detection in chest radiographs
Author(s): Ofer Geva; Sivan Lieberman; Eli Konen; Hayit Greenspan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this work, we present a novel framework for automatic detection of abnormalities in chest radiographs. The representation model is based on the Fisher Vector encoding method. In the representation process, we encode each chest radiograph using a set of extracted local descriptors. These include localized texture features that address typical local texture abnormalities as well as spatial features. Using a Gaussian Mixture Model, a rich image descriptor is generated for each chest radiograph. An improved representation is obtained by selection of features that correspond to the relevant region of interest for each pathology. Categorization of the X-ray images is conducted using supervised learning and the SVM classifier. The proposed system was tested on a dataset of 636 chest radiographs taken from a real clinical environment. We measured the performance in terms of area (AUC) under the receiver operating characteristic (ROC) curve. Results show an AUC value of 0.878 for abnormal mediastinum detection, and AUC values of 0.827 and 0.817 for detection of right and left lung opacities, respectively. These results improve upon the state-of-the-art as compared with two alternative representation models.

Paper Details

Date Published: 24 March 2016
PDF: 7 pages
Proc. SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 97850D (24 March 2016); doi: 10.1117/12.2217536
Show Author Affiliations
Ofer Geva, Tel Aviv Univ. (Israel)
Sivan Lieberman, The Chaim Sheba Medical Ctr., Tel Hashomer (Israel)
Eli Konen, The Chaim Sheba Medical Ctr., Tel Hashomer (Israel)
Hayit Greenspan, Tel Aviv Univ. (Israel)

Published in SPIE Proceedings Vol. 9785:
Medical Imaging 2016: Computer-Aided Diagnosis
Georgia D. Tourassi; Samuel G. Armato III, Editor(s)

© SPIE. Terms of Use
Back to Top