Title :
Wavelet based texture analysis of Liver tumor from Computed Tomography images for characterization using Linear Vector Quantization Neural Network
Author :
Mala, K. ; Sadasivam, V.
Author_Institution :
Mepco Schlenk Eng. Coll., Tamilnadu
Abstract :
The use of medical imaging and tissue characterization techniques is popular in diagnosis, treatment and research. The objective of this work is to automatically extract the liver tumor from the liver region of the CT abdominal image and to characterize the liver tumor as benign or malignant using wavelet based texture analysis and Linear Vector Quantization (LVQ) neural network. The system is tested with 100 images. The accuracy obtained is 92%. Performance of the system for the different parameters of LVQ like learning rate, number of hidden neurons and the number of epochs are analyzed. To evaluate the performance of the system, parameters like sensitivity, specificity, positive predicting value and negative predicting value are calculated. The results are evaluated with radiologists.
Keywords :
computerised tomography; feature extraction; image texture; liver; medical image processing; neural nets; tumours; vector quantisation; wavelet transforms; CT abdominal image; LVQ neural network; automatic liver tumor extraction; computed tomography images; linear vector quantization neural network; medical imaging; tissue characterization techniques; wavelet based texture analysis; Abdomen; Biomedical imaging; Computed tomography; Image analysis; Image texture analysis; Liver neoplasms; Medical treatment; Neural networks; Vector quantization; Wavelet analysis; Biorthogonal wavelet; Computer Aided Diagnosis; LVQ neural network; Texture analysis;
Conference_Titel :
Advanced Computing and Communications, 2006. ADCOM 2006. International Conference on
Conference_Location :
Surathkal
Print_ISBN :
1-4244-0716-8
Electronic_ISBN :
1-4244-0716-8
DOI :
10.1109/ADCOM.2006.4289897