AUT Journal of Electrical Engineering

AUT Journal of Electrical Engineering

DASA-Net: A Hybrid Dual-Attention Swin-Transformer Architecture for Precise Segmentation of Brain Tumors from MRI

Document Type : Research Article

Authors
Noor Isam Abdulnabi 1
Mansoor Fateh 1
Saideh Ferdowsi 2
1 Faculty of Computer Engineering, Shahrood University of Technology, Shahrood, Iran
2 School of Mathematics, Statistics and Actuarial Science, University of Essex, Colchester CO4 3SQ, UK
10.22060/eej.2026.25612.5970
Abstract
Brain tumor segmentation from Magnetic Resonance Imaging is a critical step for diagnosis and treatment planning, yet manual delineation is time-consuming and subjective. While deep learning models like Convolutional Neural Networks and Transformers have advanced automated segmentation, they face inherent limitations. CNNs struggle with long-range dependencies, while pure Transformers are often data-inefficient. To address these challenges, we propose DASA-Net, a novel hybrid Dual-Attention Swin-Transformer Architecture for precise brain tumor segmentation. Our model integrates a pre-trained Swin Transformer as the encoder to capture rich hierarchical and global contextual features. We introduce an Enhanced Spatial Attention module with residual connections to refine spatial details in the encoder's feature maps, and incorporate Squeeze-and-Excitation blocks in the decoder for adaptive channel-wise feature recalibration. Additionally, a Dynamic Hybrid Loss function is employed to balance Binary Cross-Entropy, Dice, and Focal losses, effectively addressing class imbalance and boundary ambiguity. Extensive experiments on the BRISC and Figshare brain tumor datasets demonstrate that DASA-Net achieves state-of-the-art performance, with a Dice score of 90.3% and IoU of 82.3% on BRISC, significantly outperforming existing methods.
Keywords
Brain Tumor
MRI
Segmentation
Attention Mechanism
Subjects
[1] J. Greg, Bridged CNN--Transformer Architectures for Improved Brain Tumor Segmentation in MRI Scans,  (2025).
[2] M. Kharaji, H. Abbasi, Y. Orouskhani, M. Shomalzadeh, F. Kazemi, M. Orouskhani, Brain tumor segmentation with advanced nnU-Net: pediatrics and adult tumors, Neuroscience Informatics, 4(2) (2024) 100156.
[3] S.K. Agrawal, I.P. Dubey, A.K. Nair, A. Jain, A. Mahato, R. Kumar, Neuroimaging informatics framework for analysing rare brain metastasis patterns in pleural mesothelioma using hybrid PET CT, Neuroscience Informatics,  (2025) 100207.
[4] T.B.T. Charity, Source K: Brain tumour statistics, in, 2023.
[5] M. Soltani-Gol, A. Asgharzadeh-Bonab, H. Soltanian-Zadeh, J. Mazlum, RDCU-Net: A Multi-Scale Residual Dilated Convolution U-Net with Spatial Pyramid Pooling for Brain Tumor Segmentation, AUT Journal of Electrical Engineering, 56(2) (2024) 203-212.
[6] M. Ahangar, E. Najafiaghdam, A. Gharibi, Diagnosing Cancerous Tumor Using Photoacoustic Imaging and Thermoacoustic Tomography with Electric Excitation Techniques—A Numerical Approach for Comparison, AUT Journal of Electrical Engineering, 54(2 (Special Issue)) (2022) 409-420.
[7] A. Kotte, V.K. Prasad, Hybrid 3D U-Net and Attention Mechanisms for Whole Heart Segmentation from CT Images, Engineering, Technology \& Applied Science Research, 15(2) (2025) 21822--21828.
[8] M.M. Saleh, M.E. Salih, M.A.A. Ahmed, A.M. Hussein, From traditional methods to 3d u-net: A comprehensive review of brain tumour segmentation techniques, Journal of Biomedical Science and Engineering, 18(1) (2025) 1--32.
[9] A. Deshpande, V.V. Estrela, A. Jude, J. Hemanth, Special issue on computational intelligence in neuroinformatics: technologies and data analytics, in:  Neuroscience Informatics, 2025, pp. 100187.
[10] R. Li, Y. Liao, Y. Huang, X. Ma, G. Zhao, Y. Wang, C. Song, DeepGlioSeg: advanced glioma MRI data segmentation with integrated local-global representation architecture, Frontiers in Oncology, 15 (2025) 1449911.
[11] Mohana, S. Sowmiya, Vinieth, S. Savitha, S. Mohanapriya, K. Dinesh, Optimizing Brain Tumor Segmentation Using Attention U-NET and ASPP U-NET, in:  Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT, SciTePress, 2025, pp. 223-228.
[12] V. Swathi, K. Sinduja, V.R. Kumar, A. Mahendar, G.V. Prasad, B. Samya, Deep learning-based brain tumor detection: An MRI segmentation approach, in, 2024, pp. 01157.
[13] B. Gupta, G.K. Jegannathan, M.S. Alam, K.S. Yogi, J.V.N. Ramesh, V.J. Sowmya, I. Bayhan, Multimodal Lightweight Neural Network for Alzheimer's Disease Diagnosis Integrating Neuroimaging and Cognitive Scores, Neuroscience Informatics,  (2025) 100218.
[14] C. Diana-Albelda, l. Garca-Martn, J. Bescos, A Review on Deep Learning Methods for Glioma Segmentation, Limitations, and Future Perspectives, Journal of Imaging, 11(8) (2025) 269.
[15] A.S. Pillai, Utilizing Deep Learning in Medical Image Analysis for Enhanced Diagnostic Accuracy and Patient Care: Challenges, Opportunities, and Ethical Implications, Journal of Deep Learning in Genomic Data Analysis,  (2021).
[16] X. Liu, J. Tian, S. Huang, W. Shen, Enhancing medical image segmentation via complementary CNN-transformer fusion and boundary perception, Frontiers in Computer Science, 7 (2025) 1677905.
[17] A. Nur, K. Nurhanafi, E.R. Putri, Brain Tumor Segmentation in MR Images Using Swin Transformer, Atom Indonesia, 51(2) (2025).
[18] H. Cao, Y. Wang, J. Chen, D. Jiang, X. Zhang, Q. Tian, M. Wang, Swin-unet: Unet-like pure transformer for medical image segmentation, in, 2022, pp. 205--218.
[19] T. Griebel, A. Archit, C. Pape, Segment anything for histopathology, arXiv preprint arXiv:2502.00408,  (2025).
[20] R.A. Zeineldin, M.E. Karar, Z. Elshaer, J. Coburger, C.R. Wirtz, O. Burgert, F. Mathis-Ullrich, Explainable hybrid vision transformers and convolutional network for multimodal glioma segmentation in brain MRI, Scientific reports, 14(1) (2024) 3713.
[21] W. Yang, Z. Li, C. Du, S.K.K. Chow, HLNet: high-level attention mechanism U-Net++ for brain tumor segmentation in MRI, Applied Intelligence, 55(7) (2025) 692.
[22] R.C. Gonzalez, Digital image processing, 2009.
[23] U. Bhimavarapu, N. Chintalapudi, G. Battineni, Brain tumor detection and categorization with segmentation of improved unsupervised clustering approach and machine learning classifier, Bioengineering, 11(3) (2024) 266.
[24] S. Bauer, L.-P. Nolte, M. Reyes, Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization, in, 2011, pp. 354--361.
[25] T.A. Soomro, L. Zheng, A.J. Afifi, A. Ali, S. Soomro, M. Yin, J. Gao, Image segmentation for MR brain tumor detection using machine learning: a review, IEEE Reviews in Biomedical Engineering, 16 (2022) 70--90.
[26] A. Ellwaa, A. Hussein, E. AlNaggar, M. Zidan, M. Zaki, M.A. Ismail, N.M. Ghanem, Brain tumor segmantation using random forest trained on iteratively selected patients, in, 2016, pp. 129--137.
[27] J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in, 2015, pp. 3431--3440.
[28] O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in, 2015, pp. 234--241.
[29] M.A.-A. Al-Murshidawy, O. Al-Shamma, A review of deep learning models (U-Net architectures) for segmenting brain tumors, Bulletin of Electrical Engineering and Informatics, 13(2) (2024) 1015--1030.
[30] z. iek, A. Abdulkadir, S.S. Lienkamp, T. Brox, O. Ronneberger, 3D U-Net: learning dense volumetric segmentation from sparse annotation, in, 2016, pp. 424--432.
[31] F. Milletari, N. Navab, S.-A. Ahmadi, V-net: Fully convolutional neural networks for volumetric medical image segmentation, in, 2016, pp. 565--571.
[32] C. Makwana, N. Nayak, M. Sagar, Brain tumor segmentation using U-Net++ with dense connection, Multidisciplinary Science Journal, 6(12) (2024) 2024264--2024264.
[33] S.M. Rasa, M.M. Islam, M.A. Talukder, M.A. Uddin, M. Khalid, M. Kazi, M.Z. Kazi, Brain tumor classification using fine-tuned transfer learning models on magnetic resonance imaging (MRI) images, Digital health, 10 (2024) 20552076241286140.
[34] D. Rastogi, P. Johri, M. Donelli, L. Kumar, S. Bindewari, A. Raghav, S.K. Khatri, Brain tumor detection and prediction in MRI images utilizing a Fine-Tuned transfer learning model integrated within deep learning frameworks, Life, 15(3) (2025) 327.
[35] B. Hou, S. Guan, Brain tumor segmentation using deep learning: A Review, Journal of Computing and Electronic Information Management, 16(1) (2025) 26--32.
[36] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, u. Kaiser, I. Polosukhin, Attention is all you need, Advances in neural information processing systems, 30 (2017).
[37] X. Chen, L. Yang, Brain tumor segmentation based on CBAM-TransUNet, in, 2022, pp. 33--38.
[38] M.a.M. DIVYA, MOHAMED ANAS and N, MOHAMED ARSATH, Tumor Spotting Using Swin UNET, International Journal of Creative Research Thoughts (IJCRT),  (2025).
[39] Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in, 2021, pp. 10012--10022.
[40] Z. Liao, H. Peng, T. Liu, Brain tumor segmentation based on improved swin-UNet, in, 2023, pp. 222--225.
[41] B.M. Mulani, Multi-Modal Brain Tumor Segmentation with Attention Mechanisms,  (2025).
[42] Y. Cao, Y. Song, New Approach for Brain Tumor Segmentation Based on Gabor Convolution and Attention Mechanism, Applied Sciences, 14(11) (2024) 4919.
[43] A. Fateh, Y. Rezvani, S. Moayedi, S. Rezvani, F. Fateh, M. Fateh, V. Abolghasemi, Brisc: Annotated dataset for brain tumor segmentation and classification with swin-hafnet, arXiv preprint arXiv:2506.14318,  (2025).
[44] J. Cheng, W. Huang, S. Cao, R. Yang, W. Yang, Z. Yun, Z. Wang, Q. Feng, Enhanced performance of brain tumor classification via tumor region augmentation and partition, PloS one, 10(10) (2015) e0140381.
[45] J. Cheng, W. Yang, M. Huang, W. Huang, J. Jiang, Y. Zhou, R. Yang, J. Zhao, Y. Feng, Q. Feng, et al., Retrieval of brain tumors by adaptive spatial pooling and fisher vector representation, PloS one, 11(6) (2016) e0157112.
[46] A. Saber, P. Parhami, A. Siahkarzadeh, M. Fateh, A. Fateh, Efficient and accurate pneumonia detection using a novel multi-scale transformer approach, arXiv preprint arXiv:2408.04290,  (2024).
[47] Z. Zhou, M.M. Rahman Siddiquee, N. Tajbakhsh, J. Liang, Unet++: A nested u-net architecture for medical image segmentation, in, 2018, pp. 3--11.
[48] T. Fan, G. Wang, Y. Li, H. Wang, Ma-net: A multi-scale attention network for liver and tumor segmentation, IEEE Access, 8 (2020) 179656--179665.
[49] A. Chaurasia, E. Culurciello, Linknet: Exploiting encoder representations for efficient semantic segmentation, in, 2017, pp. 1--4.
[50] L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, in, 2018, pp. 801--818.
[51] H. Li, P. Xiong, J. An, L. Wang, Pyramid attention network for semantic segmentation, arXiv preprint arXiv:1805.10180,  (2018).
[52] C. Li, G. Jiao, EINet: camouflaged object detection with pyramid vision transformer, Journal of Electronic Imaging, 31(5) (2022) 053002--053002.
[53] K. Patel, A.M. Bur, G. Wang, Enhanced u-net: A feature enhancement network for polyp segmentation, in, 2021, pp. 181--188.
[54] J. Li, W. He, H. Zhang, Towards complex backgrounds: A unified difference-aware decoder for binary segmentation, arXiv preprint arXiv:2210.15156,  (2022).
[55] X. Qin, D.-P. Fan, C. Huang, C. Diagne, Z. Zhang, A.C. Sant'Anna, A. Suarez, M. Jagersand, L. Shao, Boundary-aware segmentation network for mobile and web applications, arXiv preprint arXiv:2101.04704,  (2021).
[56] S. Rezvani, M. Fateh, H. Khosravi, ABANet: Attention boundary-aware network for image segmentation, Expert Systems, 41(9) (2024) e13625.
[57] T. Koleilat, H. Asgariandehkordi, H. Rivaz, Y. Xiao, Medclip-sam: Bridging text and image towards universal medical image segmentation, in, 2024, pp. 643--653.
AUT Journal of Electrical Engineering
Volume 58, Issue 4
2026
Pages 665-680