Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/60311
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Random forest based lung nodule classification aided by clustering
Author: Lee, S.
Kouzani, A.
Hu, E.
Citation: Computerized Medical Imaging and Graphics, 2010; 34(7):535-542
Publisher: Pergamon-Elsevier Science Ltd
Issue Date: 2010
ISSN: 0895-6111
1879-0771
Statement of
Responsibility: 
S.L.A. Lee, A.Z. Kouzani, E.J. Hu
Abstract: An automated lung nodule detection system can help spot lung abnormalities in CT lung images. Lung nodule detection can be achieved using template-based, segmentation-based, and classification-based methods. The existing systems that include a classification component in their structures have demonstrated better performances than their counterparts. Ensemble learners combine decisions of multiple classifiers to form an integrated output. To improve the performance of automated lung nodule detection, an ensemble classification aided by clustering (CAC) method is proposed. The method takes advantage of the random forest algorithm and offers a structure for a hybrid random forest based lung nodule classification aided by clustering. Several experiments are carried out involving the proposed method as well as two other existing methods. The parameters of the classifiers are varied to identify the best performing classifiers. The experiments are conducted using lung scans of 32 patients including 5721 images within which nodule locations are marked by expert radiologists. Overall, the best sensitivity of 98.33% and specificity of 97.11% have been recorded for proposed system. Also, a high receiver operating characteristic (ROC) Az of 0.9786 has been achieved.
Keywords: Lung images; Pulmonary nodules; Ensemble classification; Classification aided by clustering
Rights: © 2010 Elsevier Ltd. All rights reserved.
RMID: 0020097060
DOI: 10.1016/j.compmedimag.2010.03.006
Appears in Collections:Mechanical Engineering publications
Environment Institute publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.