VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification

For the past few decades, brain tumors have had a substantial influence on human life, and pose severe health risks if not treated and diagnosed in the early stages. Brain tumor problems are highly diverse and vary extensively in terms of size, type, and location. This brain tumor diversity makes it...

Full description

Saved in:
Bibliographic Details
Main Authors: Kambham Pratap Joshi, Vishruth Boraiah Gowda, Parameshachari Bidare Divakarachari, Paramesh Siddappa Parameshwarappa, Raj Kumar Patra
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Big Data and Cognitive Computing
Subjects:
Online Access:https://www.mdpi.com/2504-2289/9/2/29
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850080570701250560
author Kambham Pratap Joshi
Vishruth Boraiah Gowda
Parameshachari Bidare Divakarachari
Paramesh Siddappa Parameshwarappa
Raj Kumar Patra
author_facet Kambham Pratap Joshi
Vishruth Boraiah Gowda
Parameshachari Bidare Divakarachari
Paramesh Siddappa Parameshwarappa
Raj Kumar Patra
author_sort Kambham Pratap Joshi
collection DOAJ
description For the past few decades, brain tumors have had a substantial influence on human life, and pose severe health risks if not treated and diagnosed in the early stages. Brain tumor problems are highly diverse and vary extensively in terms of size, type, and location. This brain tumor diversity makes it challenging to progress an accurate and reliable diagnostic tool. In order to effectively segment and classify the tumor region, still several developments are required to make an accurate diagnosis. Thus, the purpose of this research is to accurately segment and classify brain tumor Magnetic Resonance Images (MRI) to enhance diagnosis. Primarily, the images are collected from BraTS 2019, 2020, and 2021 datasets, which are pre-processed using min–max normalization to eliminate noise. Then, the pre-processed images are given into the segmentation stage, where a Variational Spatial Attention with Graph Convolutional Neural Network (VSA-GCNN) is applied to handle the variations in tumor shape, size, and location. Then, the segmented outputs are processed into feature extraction, where an AlexNet model is used to reduce the dimensionality. Finally, in the classification stage, a Bidirectional Gated Recurrent Unit (Bi-GRU) is employed to classify the brain tumor regions as gliomas and meningiomas. From the results, it is evident that the proposed VSA-GCNN-BiGRU shows superior results on the BraTS 2019 dataset in terms of accuracy (99.98%), sensitivity (99.92%), and specificity (99.91%) when compared with existing models. By considering the BraTS 2020 dataset, the proposed VSA-GCNN-BiGRU shows superior results in terms of Dice similarity coefficient (0.4), sensitivity (97.7%), accuracy (98.2%), and specificity (97.4%). While evaluating with the BraTS 2021 dataset, the proposed VSA-GCNN-BiGRU achieved specificity of 97.6%, Dice similarity of 98.6%, sensitivity of 99.4%, and accuracy of 99.8%. From the overall observation, the proposed VSA-GCNN-BiGRU supports accurate brain tumor segmentation and classification, which provides clinical significance in MRI when compared to existing models.
format Article
id doaj-art-dc88335a7fcd4f1797cbd442f65b77d6
institution DOAJ
issn 2504-2289
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Big Data and Cognitive Computing
spelling doaj-art-dc88335a7fcd4f1797cbd442f65b77d62025-08-20T02:44:55ZengMDPI AGBig Data and Cognitive Computing2504-22892025-01-01922910.3390/bdcc9020029VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and ClassificationKambham Pratap Joshi0Vishruth Boraiah Gowda1Parameshachari Bidare Divakarachari2Paramesh Siddappa Parameshwarappa3Raj Kumar Patra4Department of CSE- Data Science/Cyber Security, MLR Institute of Technology, Hyderabad 500043, IndiaDepartment of Information Science and Engineering, SJB Institute of Technology, Affiliated to Visvesvaraya Technological University, Bangalore 560060, IndiaDepartment of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, Bengaluru 560064, IndiaDepartment of Computer Science & Engineering, School of Engineering, Central University of Karnataka, Kalaburagi 585367, IndiaComputer Science and Engineering, CMR Technical Campus, Hyderabad 501401, IndiaFor the past few decades, brain tumors have had a substantial influence on human life, and pose severe health risks if not treated and diagnosed in the early stages. Brain tumor problems are highly diverse and vary extensively in terms of size, type, and location. This brain tumor diversity makes it challenging to progress an accurate and reliable diagnostic tool. In order to effectively segment and classify the tumor region, still several developments are required to make an accurate diagnosis. Thus, the purpose of this research is to accurately segment and classify brain tumor Magnetic Resonance Images (MRI) to enhance diagnosis. Primarily, the images are collected from BraTS 2019, 2020, and 2021 datasets, which are pre-processed using min–max normalization to eliminate noise. Then, the pre-processed images are given into the segmentation stage, where a Variational Spatial Attention with Graph Convolutional Neural Network (VSA-GCNN) is applied to handle the variations in tumor shape, size, and location. Then, the segmented outputs are processed into feature extraction, where an AlexNet model is used to reduce the dimensionality. Finally, in the classification stage, a Bidirectional Gated Recurrent Unit (Bi-GRU) is employed to classify the brain tumor regions as gliomas and meningiomas. From the results, it is evident that the proposed VSA-GCNN-BiGRU shows superior results on the BraTS 2019 dataset in terms of accuracy (99.98%), sensitivity (99.92%), and specificity (99.91%) when compared with existing models. By considering the BraTS 2020 dataset, the proposed VSA-GCNN-BiGRU shows superior results in terms of Dice similarity coefficient (0.4), sensitivity (97.7%), accuracy (98.2%), and specificity (97.4%). While evaluating with the BraTS 2021 dataset, the proposed VSA-GCNN-BiGRU achieved specificity of 97.6%, Dice similarity of 98.6%, sensitivity of 99.4%, and accuracy of 99.8%. From the overall observation, the proposed VSA-GCNN-BiGRU supports accurate brain tumor segmentation and classification, which provides clinical significance in MRI when compared to existing models.https://www.mdpi.com/2504-2289/9/2/29bidirectional gated recurrent unitbrain tumor segmentationconvolutional architecturesgraph convolutional neural networkhistogram equalizationvariational spatial attention mechanism
spellingShingle Kambham Pratap Joshi
Vishruth Boraiah Gowda
Parameshachari Bidare Divakarachari
Paramesh Siddappa Parameshwarappa
Raj Kumar Patra
VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification
Big Data and Cognitive Computing
bidirectional gated recurrent unit
brain tumor segmentation
convolutional architectures
graph convolutional neural network
histogram equalization
variational spatial attention mechanism
title VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification
title_full VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification
title_fullStr VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification
title_full_unstemmed VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification
title_short VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification
title_sort vsa gcnn attention guided graph neural networks for brain tumor segmentation and classification
topic bidirectional gated recurrent unit
brain tumor segmentation
convolutional architectures
graph convolutional neural network
histogram equalization
variational spatial attention mechanism
url https://www.mdpi.com/2504-2289/9/2/29
work_keys_str_mv AT kambhampratapjoshi vsagcnnattentionguidedgraphneuralnetworksforbraintumorsegmentationandclassification
AT vishruthboraiahgowda vsagcnnattentionguidedgraphneuralnetworksforbraintumorsegmentationandclassification
AT parameshacharibidaredivakarachari vsagcnnattentionguidedgraphneuralnetworksforbraintumorsegmentationandclassification
AT parameshsiddappaparameshwarappa vsagcnnattentionguidedgraphneuralnetworksforbraintumorsegmentationandclassification
AT rajkumarpatra vsagcnnattentionguidedgraphneuralnetworksforbraintumorsegmentationandclassification