An Efficient Hybridization Approach for Tissue Segmentation and Classification in Brain MRI Images
jayanthi M G
, Preethi S , Yashaswini S
Brain tissues, fuzzy c-means clustering, optimal deep neural network, grasshopper optimization algorithm, White matter, gray matter, cerebral spinal fluid, background (BG) and tumor tissues.
The classification of brain tissues plays an important role in numerous neuro-anatomical analysis and applications. Manual detection of these brain tissues may results in misdiagnosis of volume and location of unwanted tissues due to human errors caused by visual fatigue. Also, it is very time consuming and may exhibit tremendous bias inter or intra the operators. In order to overcome the problem, in this paper, MRI brain tissue segmentation and classification using hybridization of fuzzy c-means clustering (FCM) and optimal deep neural network (ODNN) is presented. The proposed system consists of five modules such as preprocessing, segmentation, feature extraction, feature selection,and classification. Initially, we remove the noise present in the input image. Then, we segment the different tissue present in the MRI image using FCM. After that, we extract the GLCM features from segmented brain tissue and then, we select the important features using oppositional grasshopper optimization algorithm (OGOA). Then, the selected features are given to ODNN classifier. Here, the DNN parameters are optimized using GOA. Finally, the classifier classifies the images as White matter (WM), gray matter (GM), cerebral spinal fluid (CSF), background (BG) and tumor tissues (TT).Both the classification and the segmentation performance of the proposed technique are evaluated in terms of accuracy, sensitivity,and specificity. The implementation result shows the efficiency of the proposed tissue segmentation technique in segmenting the tissues accurately from the MRI and gives the better classification result.
"An Efficient Hybridization Approach for Tissue Segmentation and Classification in Brain MRI Images", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.8, Issue 3, page no.a598-a612, March-2023, Available :https://ijnrd.org/papers/IJNRD2303061.pdf
Volume 8
Issue 3,
March-2023
Pages : a598-a612
Paper Reg. ID: IJNRD_188160
Published Paper Id: IJNRD2303061
Downloads: 000118846
Research Area: Medical Science
Country: Bengaluru, karnataka, India
ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJNRD (IJ Publication) Janvi Wave
