Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learning

The problem of brain tumor classification (BTC) has been approached with several methods and uses different features obtained from MRI brain scans. However, they suffer from achieving higher performance in BTC and produce poor performance with a higher false ratio. A convolutional neural network (CN...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Vimala, SatheeshKumar Palanisamy, Sghaier Guizani, Habib Hamam
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Egyptian Informatics Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110866524001403
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257675657412608
author M. Vimala
SatheeshKumar Palanisamy
Sghaier Guizani
Habib Hamam
author_facet M. Vimala
SatheeshKumar Palanisamy
Sghaier Guizani
Habib Hamam
author_sort M. Vimala
collection DOAJ
description The problem of brain tumor classification (BTC) has been approached with several methods and uses different features obtained from MRI brain scans. However, they suffer from achieving higher performance in BTC and produce poor performance with a higher false ratio. A convolutional neural network (CNN) based on BTC and a survival analysis model based on GDD (growth distribution depth) are presented. Initially, an adaptive median filter (AMF) is used to preprocess the MRI images in order to lower the amount of noise in the images. Secondly, in order to calculate the GDD value, the texture, shape, and gradient characteristics are extracted. Third, CNN is used to train the retrieved features based on the labels that were found. In the classification, the GDD features extracted are used to measure TSF (Tumor Support Factor) in each of them. The neurons of the network measure the value of tumor weight (TW) to perform classification. Additionally, the technique evaluates a patient’s survival and calculates the survival rate based on the TSF value of the growth characteristic. The multi-layer perceptron allows the computation of TW and supports the efficient performance of classification. The proposed method improves tumor classification performance by up to 97%.
format Article
id doaj-art-8e22ff5858614f40b14bdce8b26509ca
institution OA Journals
issn 1110-8665
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Egyptian Informatics Journal
spelling doaj-art-8e22ff5858614f40b14bdce8b26509ca2025-08-20T01:56:20ZengElsevierEgyptian Informatics Journal1110-86652024-12-012810057710.1016/j.eij.2024.100577Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learningM. Vimala0SatheeshKumar Palanisamy1Sghaier Guizani2Habib Hamam3Department of ECE, P.S.R Engineering College, Sivakasi, Tamil Nadu 626140, IndiaDepartment of ECE, BMS Institute of Technology and Management, Bengaluru, India, 560119; Corresponding authors.College of Engineering, Alfaisal University, Riyadh 11533, Saudi Arabia; Corresponding authors.School of Electrical Engineering, University of Johannesburg, Johannesburg 2006, South Africa; Faculty of Engineering, Uni de Moncton, NB 1EA 3E9, Canada; Hodmas University College, Taleh Area, Mogadishu, Somalia; Bridges for Academic Excellence, Tunis, TunisiaThe problem of brain tumor classification (BTC) has been approached with several methods and uses different features obtained from MRI brain scans. However, they suffer from achieving higher performance in BTC and produce poor performance with a higher false ratio. A convolutional neural network (CNN) based on BTC and a survival analysis model based on GDD (growth distribution depth) are presented. Initially, an adaptive median filter (AMF) is used to preprocess the MRI images in order to lower the amount of noise in the images. Secondly, in order to calculate the GDD value, the texture, shape, and gradient characteristics are extracted. Third, CNN is used to train the retrieved features based on the labels that were found. In the classification, the GDD features extracted are used to measure TSF (Tumor Support Factor) in each of them. The neurons of the network measure the value of tumor weight (TW) to perform classification. Additionally, the technique evaluates a patient’s survival and calculates the survival rate based on the TSF value of the growth characteristic. The multi-layer perceptron allows the computation of TW and supports the efficient performance of classification. The proposed method improves tumor classification performance by up to 97%.http://www.sciencedirect.com/science/article/pii/S1110866524001403Brain TumorImage ClassificationConvolution Neural NetworkGDD ApproximationSurvival Analysis
spellingShingle M. Vimala
SatheeshKumar Palanisamy
Sghaier Guizani
Habib Hamam
Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learning
Egyptian Informatics Journal
Brain Tumor
Image Classification
Convolution Neural Network
GDD Approximation
Survival Analysis
title Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learning
title_full Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learning
title_fullStr Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learning
title_full_unstemmed Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learning
title_short Efficient GDD feature approximation based brain tumour classification and survival analysis model using deep learning
title_sort efficient gdd feature approximation based brain tumour classification and survival analysis model using deep learning
topic Brain Tumor
Image Classification
Convolution Neural Network
GDD Approximation
Survival Analysis
url http://www.sciencedirect.com/science/article/pii/S1110866524001403
work_keys_str_mv AT mvimala efficientgddfeatureapproximationbasedbraintumourclassificationandsurvivalanalysismodelusingdeeplearning
AT satheeshkumarpalanisamy efficientgddfeatureapproximationbasedbraintumourclassificationandsurvivalanalysismodelusingdeeplearning
AT sghaierguizani efficientgddfeatureapproximationbasedbraintumourclassificationandsurvivalanalysismodelusingdeeplearning
AT habibhamam efficientgddfeatureapproximationbasedbraintumourclassificationandsurvivalanalysismodelusingdeeplearning