Risk-free WHO grading of astrocytoma using convolutional neural networks from MRI images
- PDF / 1,565,264 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 70 Downloads / 231 Views
Risk-free WHO grading of astrocytoma using convolutional neural networks from MRI images Ghulam Gilanie 1 & Usama Ijaz Bajwa 1 Muhammad Waqas Anwar 1
2
& Mustansar Mahmood Waraich &
Received: 13 March 2020 / Revised: 14 August 2020 / Accepted: 24 September 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Astrocytoma is the most common and aggressive brain tumor, in its highest grade, the prognosis is ‘low survival rate’. Spinal tap and biopsy are the methods executed in order to determine the grade of astrocytoma. Once the grade of astrocytoma is determined, treatment is planned to improve the life expectancy of oncological subjects. Spinal tap and biopsy are invasive diagnostic procedures. Magnetic resonance imaging (MRI) being widely used imaging modality to detect brain tumors, produces the large volume of MRI data each moment in clinical environments. Automated and reliable methods of astrocytoma grading from the analysis of MRI images are required as an alternative to biopsy and spinal tape. However, obtaining molecular information of brain cells using noninvasive methods is challenging. In this research work, an automatic method of astrocytoma grading using Convolutional Neural Networks (CNN) has been proposed. Results have been validated on a locally developed dataset, obtained from Department of Radiology (Diagnostics), Bahawal Victoria Hospital, Bahawalpur, Pakistan. The proposed method proved a significant achievement in terms of accuracy as 99.06% (for astrocytoma of Grade-I), 94.01% (for astrocytoma of Grade-II), 95.31% (for astrocytoma of Grade-III), 97.85% (for astrocytoma of Grade-IV), and overall accuracy of 96.56%. Keywords WHO grading . Astrocytoma grading . Convolutional neural networks
* Usama Ijaz Bajwa [email protected] Ghulam Gilanie [email protected] Mustansar Mahmood Waraich [email protected] Muhammad Waqas Anwar [email protected] Extended author information available on the last page of the article
Multimedia Tools and Applications
1 Introduction With an invention of deep learning, the demand for embedded processing capabilities by smart devices also increased. Different events including disaster, accidents, medical, flood, and fight require information on their early stage, so that chances of big disasters be minimized. Among such events, a diagnosis from medical traits is one of the more demanding areas, whose detection at early stages can avoid life threats. Overall, this necessitates the existence of an automated, more accurate, and non-invasive diagnosis method. To date, most of the methods executed to determine the grade of brain tumours are invasive. The human body consists of organs and tissues, which are composed of tiny blocks called cells. Cells are divided to generate new cells in a controlled manner (this is the mechanism adopted by the human body during growing, healing, and repairing). Every cell receives a signal from the body about when to grow, divide, and stop growing. When for instance, a cel
Data Loading...