Feature-versus deep learning-based approaches for the automated detection of brain tumor with magnetic resonance images: A comparative study

Raghavendra, U and Gudigar, Anjan and Rao, Tejaswi N and Rajinikanth, V and Ciaccio, Edward J and Yeong, Chai Hong and Satapathy, Suresh Chandra and Molinari, Filippo and Acharya, Rajendra U (2022) Feature-versus deep learning-based approaches for the automated detection of brain tumor with magnetic resonance images: A comparative study. International Journal of Imaging Systems and Technology. ISSN 0899-9457

[img] PDF
14956.pdf - Published Version
Restricted to Registered users only

Download (8MB) | Request a copy
Official URL: http://wileyonlinelibrary.com/journal/ima

Abstract

The public health is significantly affected by development of brain tumors in human patients. Glioblastoma (GBM) is a relatively common, malignant form of brain tumor, which is currently challenging to treat and cure. In contrast, Lower Grade Gliomas (LGGs) originate from glial cells and can mostly be treated and cured in the initial stages if they are detected early. A computer�aided diagnostics (CAD) tool may help to test for the presence and extent of any such tumor, and thus can be assistive in the clinical diagnostic process. Herein, we compare handcrafted versus non-handcrafted features-based CAD to characterize GBM and LGG. Our machine learning-based handcrafted model uses quantitative techniques of enhanced elongated quinary patterns and entropies analysis. We have also developed a non-handcrafted deep learn�ing model using Visual Geometry Group-16 architecture for segregating GBM and LGG subjects results in 94.25% accuracy using k-nearest neighbor classifier

Item Type: Article
Uncontrolled Keywords: brain tumor, classification, deep learning, elongated quinary patterns, glioblastoma, texture features
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 12 Jul 2022 04:45
Last Modified: 12 Jul 2022 04:45
URI: http://eprints.manipal.edu/id/eprint/158913

Actions (login required)

View Item View Item