E74330111523

Design of Intelligent Technique for Abnormality Detection in MRI Brain Images
Farha Anjum Mansoori¹, Agya Mishra^2
1Farha Anjum Mansoori, Department of Electronics and Telecommunication Engineering, Jabalpur Engineering College, Jabalpur (M.P), India.
²Dr. Agya Mishra, Department of Electronics and Telecommunication Engineering, Jabalpur Engineering College, Jabalpur (M.P), India.
Manuscript received on 30 December 2022 | Revised Manuscript received on 07 January 2023 | Manuscript Accepted on 15 January 2023 | Manuscript published on 30 January 2023 | PP: 77-85 | Volume-11 Issue-5, January 2023 | Retrieval Number: 100.1/ijrte.E74330111523 | DOI: 10.35940/ijrte.E7433.0111523
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: This paper presents an intelligent technique, particularly for MRI brain images. This introduces a clever method designed explicitly for MRI brain images. To detect abnormalities in the brain images, an intelligent hybrid method combining convolutional neural networks and curvelet transform is employed. Feature extraction, the logistic regression method (LRM), and learning algorithms are all used in the proposed model. Additionally, the categorization system identifies cancerous or non-cancerous tumours in the images of the brain. Results from experiments demonstrate the effectiveness of model- and parameter-based analysis. The paper concludes by contrasting the topic of minimum batch accuracy and validation accuracy with the current method. This concept is suited to ongoing MRI image analysis activities. In this paper, a previous paper has also been reviewed, and its process is investigated.

Keywords: CNN, MRI Brain Image, Curvelet Transform, Brain Cancer, Transfer Learning, Logistic Regression Model.
Scope of the Article: CNN