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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |