NeuroQFormer-Net: A Quaternion-Guided Hybrid Attention Transformer Fusion Network for Accurate Brain Tumor Segmentation
Abstract
Brain tumor segmentation is a critical task in medical image analysis, as accurate identification and delineation of tumor regions support timely diagnosis, treatment planning, therapeutic decision-making, and disease monitoring. Magnetic Resonance Imaging (MRI) provides multiple complementary modalities that offer valuable information about tumor structure and tissue characteristics. However, accurate segmentation remains challenging due to substantial variations in tumor size, shape, texture, and location, along with irregular and overlapping tumor boundaries, low-contrast regions, and considerable differences in the information captured by different MRI modalities. To address these challenges, this study proposes NeuroQFormer-Net (Quaternion-Guided Hybrid Attention Transformer Feature Fusion Network), a novel deep learning framework for multi-modal brain tumor segmentation. The proposed framework employs quaternion-based inter-channel correlation learning to effectively capture and integrate complementary information across multiple MRI modalities while preserving structural dependencies and enhancing cross-modal feature representations. In addition, a hybrid attention mechanism integrated with transformer-based learning is utilized to simultaneously capture fine-grained local structural characteristics and long-range contextual dependencies. To further improve segmentation accuracy, an adaptive co-learning feature fusion strategy is introduced to effectively integrate multi-scale representations obtained from different network levels. Furthermore, a boundary-aware refinement module enhances tumor boundary localization and reduces segmentation errors, particularly in low-contrast, irregular, and complex tumor regions. Experimental evaluation demonstrates the effectiveness of NeuroQFormer-Net, achieving an average Dice Similarity Coefficient (DSC) of 96.45%, Intersection over Union (IoU) of 93.26%, Precision of 96.17%, Recall of 96.08%, and Hausdorff Distance (HD) of 2.31 mm. These results indicate that the proposed framework provides accurate and robust multi-modal brain tumor segmentation
Downloads
References
Hamza, A., & Damaševičius, R. “Deep learning for brain tumor segmentation and classification: a systematic review of methods and trends”. Computers, materials and continua., vol.86(1), pp.1-41, 2026, DOI:10.32604/cmc.2025.069721
Nalepa, J., Marcinkiewicz, M., & Kawulok, M. “Data augmentation for brain-tumor segmentation: a review”, Frontiers in computational neuroscience, vol.13, pp.83., 2019, DOI:10.3389/fncom.2019.00083
I. Aboussaleh, J. Riffi, A. M. Mahraz, and H. Tairi, “Inception-UDet: An Improved U-Net Architecture for Brain Tumor Segmentation,” Annals of Data Science, vol. 11, no. 3, pp. 831–853, 2024, DOI:10.1007/S40745-023-00480-6
Aiya, A. J., Wani, N., Ramani, M., Kumar, A., Pant, S., Kotecha, K., & Kulkarni, A. “Optimized deep learning for brain tumor detection: a hybrid approach with attention mechanisms and clinical explainability”, Scientific Reports, vol.15(1), Art. No.31386, 2025, DOI:10.1038/s41598-025-04591-3
Zhang, P., & Yang, Z., “Convolutional neural networks: applications, challenges and future prospects in brain tumor research”, Frontiers in Neurology, vol.17, Art. No.1759459, 2026, DOI:10.3389/fneur.2026.1759459
Murtoza, A. “Brain tumor multimodal image (CT & MRI) [Data set]” Kaggle, 2024, https://www.kaggle.com/datasets/murtozalikhon/brain-tumor-multimodal-image-ct-and-mri
Rizal, S., & Kim, D. S., “SegOpt: Gradient-Aware Optimizer for Brain Tumor Segmentation using Boundary-Attentive Learning”, In 2025 International Conference on Intelligent Computing and Next Generation Networks (ICNGN) ,pp. 1-5, IEEE, 2025, DOI:10.1109/ICNGN67480.2025.11413740
Havaei, M., Dutil, F., Pal, C., Larochelle, H., & Jodoin, P. M., “A convolutional neural network approach to brain tumor segmentation. In International workshop on brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries”, Cham: Springer International Publishing, pp. 195-208, 2015, DOI:10.1007/978-3-319-30858-6_17
Balasamy, K., Seethalakshmi, V. & Suganyadevi, S. “Medical Image Analysis Through Deep Learning Techniques: A Comprehensive Survey”, Wireless Pers Commun, vol.137, pp.1685–1714, 2024 DOI:10.1007/s11277-024-11428-1
Arunkumar, N., Mohammed, M. A., Mostafa, S. A., Ibrahim, D. A., Rodrigues, J. J., & De Albuquerque, V. H. C. “Fully automatic model‐based segmentation and classification approach for MRI brain tumor using artificial neural networks”, Concurrency and Computation: Practice and Experience, vol. 32(1), pp.e4962, 2025, DOI:10.1002/cpe.4962
Rastogi, D., Johri, P., Dhanda, S. S., Singh, A., Yadav, S. A., Khan, A. A., & Kadry, S., “Dual-Stage Deep Learning Framework for Brain Tumor Classification and Localization Using Multimodal MRI Scans”. Intelligence-Based Medicine, Art. No.100361, 2026, DOI:10.1016/j.ibmed.2026.100361
Amin J, Sharif M, Gul N, Yasmin M, Shad SA., “Brain tumor classification based on DWT fusion of MRI sequences using convolutional neural network”, Pattern Recognit Lett, vol. 129, pp.115–122, 2020, DOI:10.1016/j.patrec.2019.11.016
Muksimova, S., Baltaev, J., & Cho, Y. I. “Brain Tumor Segmentation with Contextual Transformer-Based U-Net”, Electronics, vol. 15(4), pp.782, 2026, DOI:10.3390/electronics15040782
Sajjad M, Khan S, Muhammad K, Wu W, Ullah A, Baik SW. Multi-grade brain tumor classification using deep CNN with extensive data augmentation. J Comput Sci vol.30, pp.174–182, 2019, DOI:10.1016/j.jocs.2018.12.003.
Nawar, M. A., & Dinar, A. M. “MRI-Based Brain Tumor Diagnosis Using Preprocessing Pipeline and Transfer Learning Models”, Journal of Applied Science and Technology Trends, vol. 7(1), pp.110-123, 2026, DOI:10.38094/jastt71744
Chaudhary, R., Chaudhary, P., Singh, C., Kumar, K., Singh, S., Arora, R., ... & Mishra, U. “Automated Brain Tumor Detection Using Convolutional Neural Network”, Biotechnology and Applied Biochemistry, vol.73(2), pp.687-701, 2026, DOI:10.1002/bab.70060
Rehman A, Naz S, Razzak MI, Akram F, Imran M. “A deep learning-based framework for automatic brain tumors classification using transfer learning”, Circ Syst Signal Process, vol.39(2), pp.757–775, 2020, DOI:10.1007/s00034-019-01246-3.
Ferreira, M. F., Rosa, S., Caridade, P. J., & Vasconcelos, V. “Towards Accurate Brain Tumour Segmentation: A Deep Learning Approach Using U-Net Variants”, Procedia Computer Science, vol. 278, pp.1398-1403, 2026, DOI:10.1016/j.procs.2026.03.125
Berkcan, B., & Kayıkçıoğlu, T. “Enhanced 3D DenseNet with CDC for Multimodal Brain Tumor Segmentation”, Applied Sciences, vol.16(3), pp.1572, 2026, DOI:10.3390/app16031572
Zeineldin, R. A., Karar, M. E., Coburger, J., Wirtz, C. R., & Burgert, O., “DeepSeg: deep neural network framework for automatic brain tumor segmentation using magnetic resonance FLAIR images”, International journal of computer assisted radiology and surgery, vol.15(6), pp.909-920, 2020, DOI:10.1007/s11548-020-02186-z
Yang, T., Lu, X., Yang, L., Yang, M., Chen, J., & Zhao, H. “Application of MRI image segmentation algorithm for brain tumors based on improved YOLO”, Frontiers in Neuroscience, vol.18, Art. No.1510175, DOI:10.3389/fnins.2024.1510175
Hao R, Namdar K, Liu L, Khalvati F. “A transfer learning–based active learning framework for brain tumor classification”, Front Artif Intell, vol. 4, pp.1–11, 2021, DOI:10.3389/frai.2021.635766
Aslan, E., & Özüpak, Y. “A hybrid deep learning framework based on VGG19 and U-Net for accurate brain tumor segmentation in MRI images”, Magnetic Resonance Letters, Art. No.200275, 2026, DOI:10.1016/j.mrl.2026.200275
Bhagyalaxmi, K., & Dwarakanath, B. “CDCG-UNet: Chaotic optimization assisted brain tumor segmentation based on dilated channel gate attention U-Net model”, Neuroinformatics, vol.23(2), pp.12, 2025, DOI:10.1007/s12021-024-09701-6
T. A. Soomro et al., “Image Segmentation for MR Brain Tumor Detection Using Machine Learning: A Review,” IEEE Rev Biomed Eng, vol. 16, pp. 70–90, 2023, DOI:10.1109/RBME.2022.3185292
M. R. Shoaib, M. R. Elshamy, T. E. Taha, A. S. El-Fishawy, and F. E. Abd El-Samie, “Efficient deep learning models for brain tumor detection with segmentation and data augmentation techniques,” Concurr Comput, vol. 34, no. 21, p. e7031, Sep. 2022, DOI:10.1002/CPE.7031
M. Aggarwal, A. K. Tiwari, M. P. Sarathi, and A. Bijalwan, “An early detection and segmentation of Brain Tumor using Deep Neural Network,” BMC Medical Informatics and Decision Making, vol. 23, no. 1, Art. No. 78, 2023, DOI:10.1186/S12911-023-02174-8
S. Koteswara Rao Chinnam, V. Sistla, and V. Krishna Kishore Kolli, “Multimodal attention-gated cascaded U-Net model for automatic brain tumor detection and segmentation,” Biomed Signal Process Control, vol. 78, Art. No.103907, 2022, DOI:10.1016/J.BSPC.2022.103907
A. Jabbar, S. Naseem, T. Mahmood, T. Saba, F. S. Alamri, and A. Rehman, “Brain Tumor Detection and Multi-Grade Segmentation Through Hybrid Caps-VGGNet Model,” IEEE Access, vol. 11, pp. 72518–72536, 2023, DOI:10.1109/ACCESS.2023.3289224
S. Preethi and P. Aishwarya, “An efficient wavelet-based image fusion for brain tumor detection and segmentation over PET and MRI image,” Multimedia Tools and Applications 2021 80:10, vol. 80, no. 10, pp. 14789–14806, Jan. 2021, DOI:10.1007/S11042-021-10538-3
Kujur A, Raza Z, Khan AA, Wechtaisong C., “Data complexity based evaluation of the model dependence of brain MRI images for classification of brain tumor and alzheimer's disease”, IEEE Access vol.10, pp.112117–33, 2023, DOI:10.1109/ACCESS.2022.3216393.
R. Ahsan, I. Shahzadi, F. Najeeb, and H. Omer, “Brain tumor detection and segmentation using deep learning,” Magnetic Resonance Materials in Physics, Biology and Medicine, vol. 38, no. 1, pp. 13–22, 2025, DOI:10.1007/S10334-024-01203-5
A. Shaikh, S. Amin, M. A. Zeb, A. Sulaiman, M. S. Al Reshan, and H. Alshahrani, “Enhanced brain tumor detection and segmentation using densely connected convolutional networks with stacking ensemble learning,” Comput Biol Med, vol. 186, p. 109703, 2025, DOI:10.1016/J.COMPBIOMED.2025.109703
J. Wekalao, Y. A. A. Ali, T. Saidani, S. K. Patel, A. H. M. Almawgani, and B. A. Alabsi, “A GrapheneBased Surface Plasmon Resonance Metasurfaces Terahertz Sensor for Early Brain Tumor Detection with Machine Learning Optimization,” Plasmonics pp. 1–17, 2025, DOI:10.1007/S11468-025-02930-8
K. M. Hosny, M. A. Mohammed, R. A. Salama, and A. M. Elshewey, “Explainable ensemble deep learning-based model for brain tumor detection and classification,” Neural Computing and Applications, vol. 37, no. 3, pp. 1289–1306, 2025, DOI:10.1007/s00521-024-10401-0
Y. Pande and J. Chaki, “Brain tumor detection across diverse MR images: An automated triplemodule approach integrating reduced fused deep features and machine learning,” Results in Engineering, vol. 25, p. 103832, Mar. 2025, DOI:10.1016/J.RINENG.2024.103832
Shamia, D., Balasamy, K., and Suganyadevi, S. “A secure framework for medical image by integrating watermarking and encryption through fuzzy based roi selection”, Journal of Intelligent & Fuzzy systems, Vol. 44, no.5, pp.7449-7457, 2023, DOI:10.3233/JIFS-222618.
Chhimpa GR, Awasthi S, Bhati N, Yadav P, Wani NA. A transfer learning-driven fine-tuning of YOLOv10 for improved brain tumor detection in MRI images. Sci Rep, vol. 16(1), pp.1–16, 2026, DOI:10.1038/s41598-025-28813-w
S. Bin Shabbir Mugdha and M. Uddin, “NeuroSight: A Deep-Learning Integrated Efficient Approach to Brain Tumor Detection,” Engineering Reports, vol. 7, no. 1, p. e13100, 2025, DOI:10.1002/ENG2.13100
J. Wekalao, O. Alsalman, and S. K. Patel, “Square-slotted metasurface optical sensor based on graphene material for efficient detection of brain tumor using machine learning,” Measurement, vol. 253, p. 117812, 2025, DOI:10.1016/J.MEASUREMENT.2025.117812
Copyright (c) 2026 Krishnakumar B, Thanga Parvathi B, Abbinayaa M, Kunchanapalli Rama Krishna, Suganthi Rajamanickam, Satheeswaran Venkatesan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
