Volume 2
Brain Tumor Type Classification Using Deep Features of MRI Images and Optimized RBFNN
Authors
Abdoljalil Addeh, Moshtagh Iri
Abstract
The detection of Brain cancer is an essential process, which is based on the clinician’s knowledge and experience. An automatic tumor classification model is important to handle radiologists to detect the brain tumors. However, the precision of present model should be enhanced for appropriate treatments. Numerous computer-aided diagnosis (CAD) models are offered in the literary works of medical imaging to help radiologists concerning their patients. This paper proposes an intelligent diagnostic method for early detection of brain tumor based on radial basis function neural network (RBFNN) and efficient deep features of magnetic resonance imaging (MRI) scans. The developed method includes four main modules including the segmentation, feature extraction, classification and learning modules. In the segmentation module, Grab cut method is applied for segmenting tumor region. In the feature extraction module, a convolutional neural network (ConvNet) is utilized for extraction of new deep features from segmented images. The extracted deep features are fed into RBFNN in the classification module. In the RBFNN, learning algorithm has a high impact on the network performance. Therefore, a new learning algorithm based on the bees algorithm (BA) has been used in the learning module. The developed method applied on Brain Tumor Segmentation (BraTS) 2015 datasets and the obtained results showed that the developed method is effective and can be used in computer-aided systems to detect brain tumor.
Keyword: MRI scans, Brain tumor, Deep learning, Feature extraction, RBFNN Bees algorithm
PDF [ 291.4 Kb ] | Endnote File | XML
