DocumentCode :
3183508
Title :
Classification of brain tumors using PCA-ANN
Author :
Kumar, Vinod ; Sachdeva, Jainy ; Gupta, Indra ; Khandelwal, Niranjan ; Ahuja, Chirag Kamal
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol. Roorkee, Roorkee, India
fYear :
2011
fDate :
11-14 Dec. 2011
Firstpage :
1079
Lastpage :
1083
Abstract :
The present study is conducted to assist radiologists in marking tumor boundaries and in decision making process for multiclass classification of brain tumors. Primary brain tumors and secondary brain tumors along with normal regions are segmented by Gradient Vector Flow (GVF)-a boundary based technique. GVF is a user interactive model for extracting tumor boundaries. These segmented regions of interest (ROIs) are than classified by using Principal Component Analysis-Artificial Neural Network (PCA-ANN) approach. The study is performed on diversified dataset of 856 ROIs from 428 post contrast T1- weighted MR images of 55 patients. 218 texture and intensity features are extracted from ROIs. PCA is used for reduction of dimensionality of the feature space. Six classes which include primary tumors such as Astrocytoma (AS), Glioblastoma Multiforme (GBM), child tumor-Medulloblastoma (MED) and Meningioma (MEN), secondary tumor-Metastatic (MET) along with normal regions (NR) are discriminated using ANN. Test results show that the PCA-ANN approach has enhanced the overall accuracy of ANN from 72.97 % to 95.37%. The proposed method has delivered a high accuracy for each class: AS-90.74%, GBM-88.46%, MED-85.00%, MEN-90.70%, MET-96.67%and NR-93.78%. It is observed that PCA-ANN provides better results than the existing methods.
Keywords :
biomedical MRI; feature extraction; gradient methods; image classification; image segmentation; medical image processing; neural nets; principal component analysis; radiology; tumours; GVF boundary based technique; PCA-ANN approach; artificial neural network; astrocytoma; brain tumor; child tumor-medulloblastoma; decision making process; dimensionality reduction; feature extraction; glioblastoma multiforme; gradient vector flow; intensity feature; meningioma; multiclass classification; principal component analysis; radiologist; secondary tumor-metastatic; segmented regions of interest; texture feature; tumor boundaries; user interactive model; weighted MR image; Accuracy; Artificial neural networks; Feature extraction; Gabor filters; Image segmentation; Principal component analysis; Tumors; Gradient Vector Flow (GVF); Principal component analysis (PCA); brain tumor classification; feature extraction; regions of interest (ROIs);
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information and Communication Technologies (WICT), 2011 World Congress on
Conference_Location :
Mumbai
Print_ISBN :
978-1-4673-0127-5
Type :
conf
DOI :
10.1109/WICT.2011.6141398
Filename :
6141398
Link To Document :
بازگشت