


Volume 20 No 20 (2022)
Download PDF
An Efficient Deep Learning Algorithm for MRI Segmentation Using Kernel based CNN with M-SVM
Dr. Ayesha Banu, Santhosh Ramchander, Ramya Laxmi. K
Abstract
Image segmentation has contributed majorly on long-standing medical image processing. It
used earlier considered as a minor study field in computer vision. But today the rapid evolution
of deep learning and image processing in medical field using CNN model has become a major
focus of study. This paper examines deep learning-based image segmentation. Initially the
ideas and features of deep learning-based medical image processing are introduced. The
prospective development route is widened by analyzing the three basic approaches of medical
image segmentation including their precincts. A list of troublesome tissues or organs and their
conventional segmentation procedures are also discussed. However, research on deep learningbased picture segmentation is still in its infancy. Medical photographs are scarce, and the data
set contains only a few of these images. The generated photos are not clinically correct. These
challenges are addressed by deep learning-based brain tumour segmentation. Using a database
of brain tumours, this study used a kernel-based CNN with M-SVM to increase quality and
minimise error rates. It is obvious that the proposed work is superior to previous work.
Keywords
M-SVM, CNN, LoG, CLAHE, Feature Extraction, SGLDM
Copyright
Copyright © Neuroquantology
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.