|Communications on Applied Electronics|
|Foundation of Computer Science (FCS), NY, USA|
|Volume 4 - Number 5|
|Year of Publication: 2016|
|Authors: Tapas Si, Arunava De, Anup Kumar Bhattacharjee|
Tapas Si, Arunava De, Anup Kumar Bhattacharjee . Artificial Neural Network based Lesion Segmentation of Brain MRI. Communications on Applied Electronics. 4, 5 ( February 2016), 1-5. DOI=10.5120/cae2016652096
An Artificial Neural Network based segmentation method for lesion in brain is proposed. First, Magnetic Resonance Images (MRI) are denoised and intensity inhomogeneities are corrected in the preprocessing steps. Artificial neural network is used for training using gray levels and extracted statistical features from the training data with the labelled ground truth. The test images are segmented into lesion and healthy tissues using trained neural network. The connected component labelling algorithm is used to extract only lesion from the segmented images. The proposed method is applied on two MRI data set. The performance of the proposed method is compared with K-means algorithm. The proposed method performs better than K-means algorithm both qualitatively and quantitatively.