Bandyopadhyay, Niladri Sekhar (2024) Brain MRI Image segmentation using deep learning techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
It is the aim of this paper to find out how brain MRI image classification accuracy can be improved through a new hybrid deep learning model that incorporates Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), U-Net, ResNet, and GoogleNet. Given the importance of early detection of brain tumors for effective treatment, the new model was trained on a large dataset of brain MRI images resulting in a high validation accuracy of 97 percent. Despite this high performance, there were 20 misclassified images out of 600 indicating areas that could be tweaked. The research shows that integrating several advanced deep learning techniques greatly enhances tumor detection precision; it also reveals hybrid models’ potential in medical image analysis.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Ain, Qurrat Ul UNSPECIFIED |
Uncontrolled Keywords: | Brain tumor; Hybrid Model; Gaussian Noise; CNN; U-NET; Google Net; External Validation |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RC Internal medicine > RC0321 Neuroscience. Biological psychiatry. Neuropsychiatry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Ciara O'Brien |
Date Deposited: | 07 Aug 2025 10:13 |
Last Modified: | 07 Aug 2025 10:13 |
URI: | https://norma.ncirl.ie/id/eprint/8460 |
Actions (login required)
![]() |
View Item |