An efficient brain tumor classification using MRI images with hybrid deep intelligence model

ABSTRACT

The area of the brain affected by a brain tumour can be identified using the tumour’s shape, size, location, and border. This study seeks to develop a novel system of classification for brain tumours through pre-processing, segmentation, feature extraction, and tumour classification. An improved median filter will be applied to the input image in this initial phase to improve it. In this step, the image is segmented using a U-net model. Then, characteristics based on the Median Binary Pattern (MBP), the loop, the modified Local Gabor Directional Pattern (LGDiP), and the tumour size are retrieved. A hybrid model that fuses DBN and Bi-LSTM is presented to classify cancers. The optimal weights for both classifiers will be tuned during training to improve the classification performance. For this, BMEBEO (Blue Monkey Extended Bald Eagle Optimization) is proposed, which is a hybrid optimization technique. The suggested model obtains the maximum F-measure of 96.16%%.

KEYWORDS:

• Brain tumor
• analysis
• optimization
• model
• feature extraction
• classification
• technique
• performance

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Annapareddy V. N. Reddy

Dr. Annapareddy V. N. Reddy obtained his Ph.D. in Computer Science and Engineering from K L University, Vaddeswaram, Guntur, Andhra Pradesh, M.Tech. in Computer Science and Technology from Andhra University, Visakhapatnam, and B.Tech. in Computer Science and Engineering from D.M.S.S.V.H. College of Engineering. He has more than 8 years of experience in teaching and research. 6 papers were published in journals and 2 papers were presented in conferences and 2 patents were published.

Pradeep Kumar Mallick

Dr. Pradeep Kumar Mallick is currently working as Senior Associate Professor in the School of Computer Engineering, Kalinga Institute of Industrial technology (KIIT) Deemed to be University, Odisha, India. He has also served as Professor and Head Department of Computer Science and Engineering, Vignana Bharathi Institute of Technology, Hyderabad. He has completed his Post Doctoral Fellow (PDF) from Kongju National University South Korea, PhD from Siksha Ó’ Anusandhan University, M. Tech. (CSE) from Biju Patnaik University of Technology (BPUT), and MCA from Fakir Mohan University Balasore, India. Besides academics, he is also involved various administrative activities, Member of Board of Studies to C.V.Ramman Global University Bhubaneswar, Member of Doctoral Research Evaluation Committee, Admission Committee etc. His area of research includes Data Mining, Image Processing, Soft Computing, and Machine Learning. Now he is the editorial member of Korean Convergence Society for SMB. He has published 20 edited books, 1 text Book and more than 110 plus research papers in National and international journals and conference proceedings in his credit. He is also serving as Guest editor for special issues of the journal like Springer Nature and Inderscience.

B. Srinivasa Rao

Dr. B. Srinivasa Rao obtained his Ph.D. in Computer Science and Engineering from JNTUK, Kakinada, M.Tech. in Computer Science and Technology from Andhra University, Visakhapatnam, and B.Tech. in Information Science and Technology from KLCE. He has more than 18 years of experience in teaching and research. 17 papers were published in journals and 5 papers were presented in conferences and 3 patents were published. He has received more than 13.2 Lakh funds from the funding agencies like AICTE. He received Best Teacher Awards and Best Academician Award.

Phaneendra Kanakamedala

Phaneendra Kanakamedala obtained his M.Tech. in Computer Science and Engineering from Acharya Nagarjuna University, Guntur, M.C.A. in Computer Science and Applications from Bharathidasan University, Tiruchirappalli, Tamil Nadu, and B.Sc. (M.P.C.) from P.B. Siddhartha Degree College. He has more than 18 years of experience in teaching and research. 12 papers were published in journals and 3 papers were presented in conferences and 3 patents were published.