Automatic Brain Cancer Detection using SVM Kernel Trick from MRI Imaging


Authors : Azad Kumar; Dr. Neelesh Jain; Prateek Singhal

Volume/Issue : Volume 8 - 2023, Issue 6 - June

Google Scholar : https://bit.ly/3TmGbDi

Scribd : https://tinyurl.com/4ccw2shk

DOI : https://doi.org/10.5281/zenodo.8125949

Abstract : A brain tumour is an unchecked cell development that has the potential to spread to other tissues. It can be identified using Magnetic Resonance Imaging (MRI), a non-surgical method of organ research for the diagnosis of any illness associated with the symptoms. Tumours can be malignant or not, and they can also be hazardous or not to human life. A tumour can be classified as either benign or malignant, two separate categories. Benign tumours are seen as less hazardous or non-cancerous since they do not spread to other parts of the brain. It has distinct contours or limits that show the specific shade of the tumour, however malignant tumours are cancerous growths that may migrate to other parts of the brain on their own and are thus extremely hazardous. The malignant tumor's borders don't appear to be firm; rather, they have a faded look. Here, the suggested approach is capable of classifying both the tumour type and the diagnosis of a brain tumour. Here, the suggested system makes use of polynomial Support Vector Machine (SVM) to handle the impairments and identify the illness as necessary. The clustered cluster may be classified using SVM based on their patterns. The feature mapping of patterns might come from both diseased and normal cells. Drawing a hyper plane for non-linear data is challenging for other classification algorithms, however SVM can classify the data by converting it to linear data, which then makes it simple to design a hyper plane. It has been controlled using a kernel approach that allows for the mapping of high dimensional feature space. Utilising the polynomial feature of SVM, the optimisation problem may also be resolved. High degree of accuracy was perceived by the system in comparison to the prior model. 97.24, 93.94, and 99.35 percent of accuracy, specificity, and sensitivity, respectively, were attained by the system.

Keywords : Support Vector Machine, Brain Tumor, Segmentation,, Malignant, Benign, MRI, Brain Cells.

A brain tumour is an unchecked cell development that has the potential to spread to other tissues. It can be identified using Magnetic Resonance Imaging (MRI), a non-surgical method of organ research for the diagnosis of any illness associated with the symptoms. Tumours can be malignant or not, and they can also be hazardous or not to human life. A tumour can be classified as either benign or malignant, two separate categories. Benign tumours are seen as less hazardous or non-cancerous since they do not spread to other parts of the brain. It has distinct contours or limits that show the specific shade of the tumour, however malignant tumours are cancerous growths that may migrate to other parts of the brain on their own and are thus extremely hazardous. The malignant tumor's borders don't appear to be firm; rather, they have a faded look. Here, the suggested approach is capable of classifying both the tumour type and the diagnosis of a brain tumour. Here, the suggested system makes use of polynomial Support Vector Machine (SVM) to handle the impairments and identify the illness as necessary. The clustered cluster may be classified using SVM based on their patterns. The feature mapping of patterns might come from both diseased and normal cells. Drawing a hyper plane for non-linear data is challenging for other classification algorithms, however SVM can classify the data by converting it to linear data, which then makes it simple to design a hyper plane. It has been controlled using a kernel approach that allows for the mapping of high dimensional feature space. Utilising the polynomial feature of SVM, the optimisation problem may also be resolved. High degree of accuracy was perceived by the system in comparison to the prior model. 97.24, 93.94, and 99.35 percent of accuracy, specificity, and sensitivity, respectively, were attained by the system.

Keywords : Support Vector Machine, Brain Tumor, Segmentation,, Malignant, Benign, MRI, Brain Cells.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe