DocumentCode :
2976993
Title :
Assessing lung volumetric variation to detect and stage COPD
Author :
Hosseini, M. Parsa ; Soltanian-Zadeh, Hamid ; Akhlaghpoor, Shahram
Author_Institution :
Sci. & Res. Branch, Dept. of Electr. Eng., Islamic Azad Univ., Tehran, Iran
fYear :
2011
fDate :
21-24 Feb. 2011
Firstpage :
312
Lastpage :
315
Abstract :
Chronic obstructive pulmonary disease (COPD) is a devastating disease. In this paper, we propose a novel method for scoring of air trapping in the lungs for detection and evaluation of COPD. The proposed method finds volumetric changes of the lungs from inspiration to expiration. To this end, trachea CT images at full inspiration and expiration are compared. For this comparison, the lungs parenchyma in the inspiration and expiration images are found and changes in the surface and volume of the lungs between inspiration and expiration are used to define quantitative measures (features). Using these features, the subjects are classified into two groups of normal class and COPD patients using a Bayesian classifier. In addition, t-tests are applied to evaluate discrimination powers of the features for this classification. The main advantage of the proposed method is its ability to estimate air trapping in the lungs from CT images without human intervention. The proposed method may assists radiologists in the detection of COPD as a computer aided diagnosis (CAD) system. It may also assist them with the scoring of the disease (severity of air trapping in the lungs).
Keywords :
Bayes methods; computerised tomography; diseases; image classification; lung; medical image processing; pneumodynamics; statistical analysis; Bayesian classifier; air trapping; chronic obstructive pulmonary disease; computer aided diagnosis; expiration; inspiration; lung volumetric variation; t-tests; trachea CT images; Active contours; Charge carrier processes; Computed tomography; Diseases; Image segmentation; Lungs;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Engineering (MECBME), 2011 1st Middle East Conference on
Conference_Location :
Sharjah
Print_ISBN :
978-1-4244-6998-7
Type :
conf
DOI :
10.1109/MECBME.2011.5752128
Filename :
5752128
Link To Document :
بازگشت