A new method for pulmonary nodule detection using decision trees

Author

Tartar, A. ; Kilic, N. ; Akan, A.

Author_Institution

Dept. of Eng. Sci., Univ. of Istanbul, Istanbul, Turkey

fYear

2013

fDate

3-7 July 2013

Firstpage

7355

Lastpage

7359

Abstract

A computer-aided detection (CAD) can help radiologists in diagnosing of lung diseases at an early level. In this study, a new CAD system for pulmonary nodule detection from CT imagery is presented by using morphological features and patient information properties. Decision trees are utilized for classification and overall detection performance is evaluated. Results are compared to similar techniques in the literature by using standard measures. Proposed CAD system with random forest classifier result in 90.5 % sensitivity and 87.6 % specificity of detection performance.

Keywords

computerised tomography; decision trees; diseases; feature extraction; lung; medical image processing; CAD system; CT imagery; computer aided detection; decision trees; lung diseases; morphological features; overall detection performance; patient information properties; pulmonary nodule detection; radiologists; Biomedical imaging; Computed tomography; Design automation; Feature extraction; Radio frequency; Sensitivity; Vegetation;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE

Conference_Location

Osaka

ISSN

1557-170X

Type

conf

DOI

10.1109/EMBC.2013.6611257

Filename

6611257