Brain tumor detection based on hybrid deep neural network in MRI by adaptive squirrel search optimization
- PDF / 3,131,317 Bytes
- 25 Pages / 439.37 x 666.142 pts Page_size
- 96 Downloads / 211 Views
Brain tumor detection based on hybrid deep neural network in MRI by adaptive squirrel search optimization Daizy Deb 1 & Sudipta Roy 2 Received: 1 May 2020 / Revised: 5 August 2020 / Accepted: 2 September 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
In the medical field, image segmentation is a paramount and challenging task. The head and vertebral column make up the central nervous system (CNS), which control all the paramount functions. These include thinking, speaking, and gestures. The uncontrolled growth in the CNS can affect a person’s thinking of communication or movement. The tumor is known as the uncontrolled growth of cells in brain. The tumor can be recognized by MRI image. Brain tumor detection is mostly affected with inaccurate classification. This proposed work designed a novel classification and segmentation algorithm for the brain tumor detection. The proposed system uses the Adaptive fuzzy deep neural network with frog leap optimization to detect normality and abnormality of the image. Accurate classification is achieved with error minimization strategy through our proposed method. Then, the abnormal image is segmented using adaptive flying squirrel algorithm and the size of the tumor is detected, which is used to find out the severity of the tumor. The proposed work is implemented in the MATLAB simulation platform. The proposed work Accuracy, sensitivity, specificity, false positive rate and false negative rate are 99.6%, 99.9%, 99.8%, 0.0043 and 0.543, respectively. The detection accuracy is better in our proposed system than the existing teaching and learning based algorithm, social group algorithm and deep neural network. Keywords Flying squirrel . Frog leap . Optimization . Segmentation . Classification . Brain tumor detection
* Daizy Deb [email protected]
1
Department of Computer Science and Engineering, Triguna Sen School of Technology, Assam University, Silchar 788011, India
2
Department of Computer Science & Engineering, Triguna Sen School of Technology, Assam University (A Central University), Silchar 788011, India
Multimedia Tools and Applications
1 Introduction An accurate and automatic segmentation of brain tumor imparts great assistance to the doctors in the medical field, speedy diagnosis during the treatment, computer-aided surgery, radiation therapy etc. [37]. The most important task of detection or segmentation of MR image is to segment the tumor image in terms of white matter (WM), cerebrospinal fluid (CSF) and grey matter (GM). In addition to that, tumor volume calculation provides the most useful information for the diagnostic purpose [31], because the severity of the tumor can be predicted only with this tumor size. The person with a large tumor volume can lead to major surgery. Hence, size prediction in MR and CT images can distinguish the intensity of an image for different tissues. For the analysis case in medical images, some segmentation or clustering task focus on the prediction of tumor size based on a region of interest
Data Loading...
