Computer-aided diagnostic network for brain tumor classification employing modulated Gabor filter banks
- PDF / 1,356,908 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 28 Downloads / 290 Views
ORIGINAL ARTICLE
Computer-aided diagnostic network for brain tumor classification employing modulated Gabor filter banks Rahul Singh1
· Aditya Goel1
· D. K. Raghuvanshi1
Accepted: 5 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract MR brain tumor classification is one of the extensively utilized approaches in medical prognosis. However, analyzing and processing MR brain images is still quite a task for radiologists. To encounter this problem, the evaluation of existing canonical techniques has already been done. There are numeral MR brain tumor classification approaches that are being used for medical diagnosis. In this paper, we have developed an automated computer-aided network for diagnosis of MR brain tumor class, i.e., HGG and LGG. We have proffered a Gabor-modulated convolutional filter-based classifier for brain tumor classification. The inclusion of Gabor filter dynamics endows the competency to deal with spatial and orientational transformations. This mere modification (modulation) of conventional convolutional filters by Gabor filters empowers the proposed architecture to learn relatively smaller feature maps and thereby, decreasing network parameter requirement. We have introduced some skip connections to our modulated CNN architecture without introducing an extra network parameter. Pre-trained networks, i.e., Alex-Net, Google-Net (Inception V1), Res-Net and VGG 19 have been considered for performance evaluation of our proposed Gabor-modulated CNN. Additionally, some popular machine learning classification techniques have also been considered for comparative analysis. Experimental findings demonstrate that our proposed network has limited network parameters to learn; therefore, it is quite easy to train such networks. Keywords Gabor orientation filters · Convolutional neural networks (CNNs) · Leave-one-patient-out (LOPO) · Deep learning · Transfer learning
1 Introduction MRI is the most popular tool to analyze the brain sections. It offers cross sectional as well as longitudinal high-resolution images with clear visibility of soft tissues. Tumor classification has to be accurate and precise for its evaluation and planning treatment accordingly. Manual identification and classification of brain tumor is cumbersome, thereby, this has encouraged researchers to develop automated diagnostic systems for tumor detection [34]. Most of the researchers have primarily focused on gliomas since it is most com-
B
Rahul Singh [email protected] Aditya Goel [email protected] D. K. Raghuvanshi [email protected]
1
Department of Electronics and Communication, National Institute of Technology, Bhopal, M.P., India
mon type of tumor. There are various MRI sequences that can capture these anomalies, i.e., T1-weighted (T1), T1weighted contrast-enhanced (T1c), T2-weighted (T2) and fluid attenuated inversion recovery (Flair). Detection and classification of gliomas is quite onerous because of many reasons, i.e., nonhomogenous intensity spectrum, wide variations in s
Data Loading...
