SMO-based System for identifying common lung conditions using histogram

Author

de la Cruz, R.R.G. ; Roque, Trizia Roby-Ann C. ; Rosas, J.D.G. ; Vera Cruz, Charles Vincent M. ; Cordel, M.O. ; Ilao, J.P. ; Rabe, A.P.J. ; Petronilo, J.P.

Author_Institution

Comput. Technol. Dept., De La Salle Univ. - Manila, Manila, Philippines

fYear

2013

fDate

6-8 March 2013

Firstpage

112

Lastpage

116

Abstract

A radiograph is a visualization aid that physicians use in identifying lung abnormalities. Although digitized X-ray images are available, diagnosis by a medical expert through pattern recognition is done manually. Thus, this paper presents a system that utilizes machine learning for pattern recognition and classification of three lung conditions, namely Normal, Pleural Effusion and Pneumothorax cases. Using two histogram equalization techniques, the designed system achieves an accuracy rate of 76.19% and 78.10% by using Sequential Minimal Optimization (SMO).

Keywords

diagnostic radiography; learning (artificial intelligence); lung; medical image processing; optimisation; pattern classification; support vector machines; SMO-based system; digitized X-ray images; histogram equalization techniques; lung abnormality identification; lung condition identification; machine learning; medical expert; normal lung conditions; pattern classification; pattern recognition; physicians; pleural effusion case; pneumothorax case; radiograph; sequential minimal optimization; Adaptive equalizers; Biomedical imaging; Histograms; Kernel; Lungs; Support vector machines; Training; Image Histogram; Pattern Recognition; Support Vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Medical Information and Communication Technology (ISMICT), 2013 7th International Symposium on

Conference_Location

Tokyo

ISSN

2326-828X

Print_ISBN

978-1-4673-5770-8

Electronic_ISBN

2326-828X

Type

conf

DOI

10.1109/ISMICT.2013.6521711

Filename

6521711