Hybrid Machine Learning Model For Brain Tumor Classification

Chaini, Babita (2023) Hybrid Machine Learning Model For Brain Tumor Classification. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

A brain tumor is often a substantial public health concern. In order to acquire a diagnosis and to assess the most appropriate medical strategy, the data that is produced from brain tumors must be first classified according to their important features. In the realm of medicine, the process of brain image segmentation is essential for the planning of surgical and personalized treatment. In this study, a computer vision technique is described that uses a hybrid machine learning model to achieve excellent accuracy in the detection of brain tumors. In this research article, to provide an image recognition approach for the detection and identification of brain cancers in MRI images, a hybrid model was created. Pre-trained Squeeze-Net model with SVM and with fine-tuning technique hybrid model was used for brain tumor classification. The proposed model was found good in classifying the brain tumor MRI images which were verified using two brain tumor datasets which were generating an accuracy of around 93%. In addition to its use in medicine, the method has the potential to be integrated into automated treatment technologies as well as complicated applications in surgical procedures.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hasanuzzaman, Mohammed UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning Q Science > Life sciences > Medical sciences > Pathology > Tumors
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	17 May 2023 11:49
Last Modified:	17 May 2023 11:49
URI:	https://norma.ncirl.ie/id/eprint/6571

Actions (login required)

View Item