SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification
Accurate classification of brain tumors is crucial for informing clinical diagnoses and guiding patient treatment plans. It is one of the most aggressive tumors, leading to a short life expectancy. However, the classification of brain tumors is a challenging task due to the heterogeneity, complexity...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025001136 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576390428360704 |
|---|---|
| author | Qurat-ul-ain Chaudhary Shahzad Ahmad Qureshi Touseef Sadiq Anila Usman Ambreen Khawar Syed Taimoor Hussain Shah Aziz ul Rehman |
| author_facet | Qurat-ul-ain Chaudhary Shahzad Ahmad Qureshi Touseef Sadiq Anila Usman Ambreen Khawar Syed Taimoor Hussain Shah Aziz ul Rehman |
| author_sort | Qurat-ul-ain Chaudhary |
| collection | DOAJ |
| description | Accurate classification of brain tumors is crucial for informing clinical diagnoses and guiding patient treatment plans. It is one of the most aggressive tumors, leading to a short life expectancy. However, the classification of brain tumors is a challenging task due to the heterogeneity, complexity, and variability of brain tumors. In this work, we propose Superimposed AlexNet (SAlexNet-1 and its extension SAlexNet-2) to detect the malignancy of primary brain tumors (Glioma, Meningioma, and Pituitary) by incorporating three enhancements: (1) fusing Hybrid Attention Mechanism (HAM), (2) dense feature extraction by replacing initial convolution 11 × 11 layer with multiple convolution 3 × 3 layers for extra non-linearity alleviating parameter burden, and (3) pretraining the encoder path on a correlated dataset via semi-transfer learning (STL) enhancing model performance. HAM provides more comprehensive and accurate feature representations. In this study, we evaluated the performance of our proposed SAlexNet models on two publicly available extensive datasets for multi-class and binary classification tasks. Our results show that SAlexNet-1 achieved an accuracy of (98.78 ± 0.80 %) and (98.07± 0.02 %) on the multi-class and binary classification datasets, respectively. In comparison, SAlexNet-2 achieved outstanding accuracy of (99.69 ± 0.22 %) and (99.17 ± 0.00 %) on the multi-class and binary classification MRI datasets, respectively. The STL-based SAlexNet-2 surpassed previous literature with complex models and techniques, achieving an accuracy of (99.20 ± 0.01 %). Furthermore, we provided a comprehensive analysis of current state-of-the-art tumor classification methods on the same dataset, demonstrating the effectiveness of our approach. Enhanced tumor classification accuracy enables better diagnosis, treatment planning, and patient outcomes. |
| format | Article |
| id | doaj-art-15ad940eb6864291a7a6bc77f9320a39 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-15ad940eb6864291a7a6bc77f9320a392025-01-31T05:12:19ZengElsevierResults in Engineering2590-12302025-03-0125104025SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classificationQurat-ul-ain Chaudhary0Shahzad Ahmad Qureshi1Touseef Sadiq2Anila Usman3Ambreen Khawar4Syed Taimoor Hussain Shah5Aziz ul Rehman6Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Islamabad 45650, PakistanDepartment of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Islamabad 45650, Pakistan; Centre for Mathematical Sciences, PIEAS, Islamabad 45650, Pakistan; Corresponding author at: Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Islamabad 45650, Pakistan.Centre for Artificial Intelligence Research (CAIR), Department of Information and Communication Technology, University of Agder, Jon Lil-letuns vei 9, Grimstad, Norway; Corresponding author.Department of Computer and Information Sciences, Pakistan Institute of Engineering and Applied Sciences (PIEAS), Islamabad 45650, PakistanDepartment of Medical Sciences, PIEAS, Islamabad 45650, PakistanPolitoBIOMed Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Turin 10129, ItalyDepartment of Physics and Astronomy, Macquarie University, Sydney, New South Wales 2109, Australia; Agri & Biophotonics Division, National Institute of Lasers and Optronics College, PIEAS, Islamabad 45650, PakistanAccurate classification of brain tumors is crucial for informing clinical diagnoses and guiding patient treatment plans. It is one of the most aggressive tumors, leading to a short life expectancy. However, the classification of brain tumors is a challenging task due to the heterogeneity, complexity, and variability of brain tumors. In this work, we propose Superimposed AlexNet (SAlexNet-1 and its extension SAlexNet-2) to detect the malignancy of primary brain tumors (Glioma, Meningioma, and Pituitary) by incorporating three enhancements: (1) fusing Hybrid Attention Mechanism (HAM), (2) dense feature extraction by replacing initial convolution 11 × 11 layer with multiple convolution 3 × 3 layers for extra non-linearity alleviating parameter burden, and (3) pretraining the encoder path on a correlated dataset via semi-transfer learning (STL) enhancing model performance. HAM provides more comprehensive and accurate feature representations. In this study, we evaluated the performance of our proposed SAlexNet models on two publicly available extensive datasets for multi-class and binary classification tasks. Our results show that SAlexNet-1 achieved an accuracy of (98.78 ± 0.80 %) and (98.07± 0.02 %) on the multi-class and binary classification datasets, respectively. In comparison, SAlexNet-2 achieved outstanding accuracy of (99.69 ± 0.22 %) and (99.17 ± 0.00 %) on the multi-class and binary classification MRI datasets, respectively. The STL-based SAlexNet-2 surpassed previous literature with complex models and techniques, achieving an accuracy of (99.20 ± 0.01 %). Furthermore, we provided a comprehensive analysis of current state-of-the-art tumor classification methods on the same dataset, demonstrating the effectiveness of our approach. Enhanced tumor classification accuracy enables better diagnosis, treatment planning, and patient outcomes.http://www.sciencedirect.com/science/article/pii/S2590123025001136Brain tumorConvolutional neural networkFeature mapTransfer learningAlexNetDeep learning |
| spellingShingle | Qurat-ul-ain Chaudhary Shahzad Ahmad Qureshi Touseef Sadiq Anila Usman Ambreen Khawar Syed Taimoor Hussain Shah Aziz ul Rehman SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification Results in Engineering Brain tumor Convolutional neural network Feature map Transfer learning AlexNet Deep learning |
| title | SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification |
| title_full | SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification |
| title_fullStr | SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification |
| title_full_unstemmed | SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification |
| title_short | SAlexNet: Superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification |
| title_sort | salexnet superimposed alexnet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification |
| topic | Brain tumor Convolutional neural network Feature map Transfer learning AlexNet Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025001136 |
| work_keys_str_mv | AT quratulainchaudhary salexnetsuperimposedalexnetusingresidualattentionmechanismforaccurateandefficientautomaticprimarybraintumordetectionandclassification AT shahzadahmadqureshi salexnetsuperimposedalexnetusingresidualattentionmechanismforaccurateandefficientautomaticprimarybraintumordetectionandclassification AT touseefsadiq salexnetsuperimposedalexnetusingresidualattentionmechanismforaccurateandefficientautomaticprimarybraintumordetectionandclassification AT anilausman salexnetsuperimposedalexnetusingresidualattentionmechanismforaccurateandefficientautomaticprimarybraintumordetectionandclassification AT ambreenkhawar salexnetsuperimposedalexnetusingresidualattentionmechanismforaccurateandefficientautomaticprimarybraintumordetectionandclassification AT syedtaimoorhussainshah salexnetsuperimposedalexnetusingresidualattentionmechanismforaccurateandefficientautomaticprimarybraintumordetectionandclassification AT azizulrehman salexnetsuperimposedalexnetusingresidualattentionmechanismforaccurateandefficientautomaticprimarybraintumordetectionandclassification |