New Frontiers in Communication and Intelligent Systems
GPU based Segmentation and Classification of Brain Tumour from MRI Images
Authors: Joel T. Nanthikattu, Navaneeth N, Gokul D, Sonette T, Binesh T, Binish M. C. and Vinu Thomas
Publishing Date: 27-04-2022
ISBN: 978-81-95502-00-4
Abstract
Detection of Brain Tumour in its initial stage leads to an advancement in treatment methods. This paves the way for a consequent higher rate of life expectancy for the patient. These tumours can be successfully assessed by Magnetic resonance imaging (MRI). Alternatively, the immense amount of data generated by MRI causes manual segmentation to be highly time-consuming, thereby restricting the use of precise quantitative measurements in clinical practice. Brain tumours possess sizeable spatial and structural inequality among them which makes automatic segmentation a demanding task. Here in this work, Convolutional Neural Networks (CNN) are utilized to devise an accurate and efficient real time tumor tracking algorithm for detecting the different types of brain tumours. Python programming language is used for the development and the implementation is carried out on a typical Graphics Processing Unit (GPU).
Keywords
Magnetic Resonance Imaging, Machine learning, Graphic Processing Unit, Segmentation.
Cite as
Joel T. Nanthikattu, Navaneeth N, Gokul D, Sonette T, Binesh T, Binish M. C. and Vinu Thomas, "GPU based Segmentation and Classification of Brain Tumour from MRI Images", In: Rahul Srivastava and Aditya Kr. Singh Pundir (eds), New Frontiers in Communication and Intelligent Systems, SCRS, India, 2022, pp. 17-23. https://doi.org/10.52458/978-81-95502-00-4-3