Skip navigation

Segmentation of brain tumours from MRI images using CNN

Segmentation of brain tumours from MRI images using CNN

Ilango, Dhakshina and Abdul Kareem, Razia Sulthana ORCID: 0000-0001-5331-1310 (2022) Segmentation of brain tumours from MRI images using CNN. In: Conference Proceedings Inventive Systems and Control. Springer. (In Press)

[img] PDF (Author's Accepted Manuscript)
42459 KAREEM_Segmentation_Of_Brain_Tumours_From_MRI_Images_Using_CNN_(AAM)_2023.pdf - Accepted Version
Restricted to Repository staff only

Download (319kB) | Request a copy

Abstract

Identification of brain tumours in the early stage is key to proper treatment and diagnosis It can be classified as malignant or benign based on the aggressiveness of the tumour. To diagnose a patient, an MRI imaging device is used to obtain scans of the brain. Due to the large quantity of data produced, radiologists must perform the tedious task of going through each MRI image to identify the brain tumour's location, size, and origin. This process is prone to human error and is also time-consuming. Therefore, this paper proposes a methodology to accurately diagnose and segment the brain tumours from the MRI images using Convolutional Neural Networks (CNN) specifically U-NET architecture.

Item Type: Conference Proceedings
Title of Proceedings: Conference Proceedings Inventive Systems and Control
Uncontrolled Keywords: machine learning, biomedical image segmentation, brain tumours, convolutional neural networks
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > R Medicine (General)
Faculty / School / Research Centre / Research Group: Faculty of Engineering & Science
Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Last Modified: 10 May 2023 13:25
URI: http://gala.gre.ac.uk/id/eprint/42459

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics