Detection of brain tumor on MRI images using comparison analysis of deep learning techniques

Kumari, V. Sheeja, Selvi, G. Vennira, Sudha, I. and Subburaj, Surender 2024. Detection of brain tumor on MRI images using comparison analysis of deep learning techniques. Tanwar, Poonam, Kumar, Tapas, Kalaiselvi, K., Raza, Haider and Rawat, Seema, eds. Predictive data modelling for biomedical data and imaging, New York: River Publishers, (10.1201/9781003516859-15)

Full text not available from this repository.

Abstract

The process of diagnosing brain tumors typically involves the use of scans created with magnetic resonance imaging (MRI). MRI scans have the ability to localize precisely in the brain an area that is exhibiting abnormal growth of tissue. A number of research articles have been written on the topic of locating brain tumors with the assistance of machine learning and deep learning algorithms. When combined with MRI scans, these algorithms enable a quicker and more accurate detection of brain tumors, which in turn makes it easier to treat patients who have the condition. The radiologist can more easily decide what course of action to take with the help of these projections. In the proposed chapter, self-made algorithms called Random Forest (RF) and Support Vector Machine (SVM) are used to search for brain tumors, and 312their performance is analyzed. Both of these algorithms were developed by the authors of the chapter. The authors are responsible for the development of both of these algorithms. The performance of these classifiers, which determine whether or not a brain image is normal, is evaluated based on a variety of criteria, including sensitivity, specificity, and accuracy, amongst others. These classifiers are responsible for determining whether or not a brain image is normal. It has a significance of 0.001, which is lower than the p value, and it has the capability of giving an accuracy that ranges between 94.1220 and 96.8940. As a direct consequence of this, its statistical significance is indisputable.

Item Type:	Book Section
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	River Publishers
ISBN:	9781003516859
Last Modified:	31 Oct 2024 14:53
URI:	https://orca.cardiff.ac.uk/id/eprint/172586

Actions (repository staff only)

Edit Item