DocumentCode :
3048098
Title :
Effect of Texture Features in Computer Aided Diagnosis of Pulmonary Nodules in Low-Dose Computed Tomography
Author :
Krewer, Henry ; Geiger, B. ; Hall, Lawrence O. ; Goldgof, Dmitry B. ; Yuhua Gu ; Tockman, Melvyn ; Gillies, Robert J.
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of South Florida, Tampa, FL, USA
fYear :
2013
fDate :
13-16 Oct. 2013
Firstpage :
3887
Lastpage :
3891
Abstract :
Low-dose helical computed tomography (LDCT) has facilitated the early detection of lung cancer through pulmonary screening of patients. There have been a few attempts to develop a computer-aided diagnosis system for classifying pulmonary nodules using size and shape, with little attention to texture features. In this work, texture and shape features were extracted from pulmonary nodules selected from the LIDC data set. Several classifiers including Decision Trees, Nearest Neighbor, and Support Vector Machines (SVM) were used for classifying malignant and benign pulmonary nodules. An accuracy of 90.91% was achieved using a 5-nearest-neighbors algorithm and a data set containing texture features only. Laws and Wavelet features received the highest rank when using feature selection implying a larger contribution in the classification process. Considering the improvement in classification accuracy, the use of texture features appears to be a promising direction in computer-aided diagnosis of pulmonary nodules in LDCT.
Keywords :
cancer; computerised tomography; decision trees; feature extraction; feature selection; image classification; image texture; medical image processing; shape recognition; support vector machines; wavelet transforms; 5-nearest-neighbors algorithm; LDCT; SVM classification; benign pulmonary nodule classification; computer aided diagnosis; decision trees; early lung cancer detection; feature selection; laws features; low-dose helical computed tomography; malignant pulmonary nodule classification; nearest neighbor classification; pulmonary screening; shape feature extraction; support vector machines; texture feature extraction; wavelet features; Accuracy; Cancer; Feature extraction; Lungs; Shape; Support vector machines; Three-dimensional displays; Computed Tomography; Computer Aided Diagnosis; Pulmonary Nodule Classification; Texture Features;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2013 IEEE International Conference on
Conference_Location :
Manchester
Type :
conf
DOI :
10.1109/SMC.2013.663
Filename :
6722416
Link To Document :
بازگشت