Journal of Innovative Image Processing
IRO Journals
Volume 8 — Issue 2 — June 2026

MAAF-Net: A Modality-Adaptive Attention Fusion Network for Multimodal 3D MRI Brain Tumor Segmentation

https://doi.org/10.36548/jiip.2026.2.004
Pages: 501-517
  • Sandeep Kaur , Sandeep Kaur
    Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India
    Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India
  • Usha Mittal Usha Mittal
    Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India
    Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India
  • &  Ankita Wadhawan Ankita Wadhawan
    Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India
    Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India
PDF
PDF

How to Cite

Kaur, Sandeep, Usha Mittal, and Ankita Wadhawan. 2026. “MAAF-Net: A Modality-Adaptive Attention Fusion Network for Multimodal 3D MRI Brain Tumor Segmentation”. Journal of Innovative Image Processing 8 (2): 501-17. https://doi.org/10.36548/jiip.2026.2.004.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Attention-Guided Feature Fusion
— Multimodal MRI
— Modality-Specific Encoders
— Deep Learning
— 3D U-Net
— BraTS 2024
Published: 17-04-2026

Abstract

Multimodal MRI offers a comprehensive, non-invasive assessment of structure, which improves the diagnostic accuracy of brain tumor segmentation (BTS). BTS faces major challenges due to tumor heterogeneity, data quality, modality-specific information and algorithm complexity. Many existing methods do not utilize the complementary information available in multimodal data, as they depend on early fusion strategies and neglect modality-specific features. To overcome these issues, a novel architecture termed MAAF-Net: Modality-Adaptive Attention Fusion Network for 3D BTS has been proposed in this study. The MAAF-Net model preserves the semantic information of each MRI modality through modality-specific encoders (MSEnc). The extracted features are integrated using a Modality Attention Module (MAM). The MAM learns the context-dependent importance of each modality and adaptively reweights modality features during fusion. This fusion technique enables the model to focus on clinically relevant information while discarding redundant or less informative features. In addition, multi-scale supervision is incorporated to improve gradient flow and training stability. The MAAF-Net model is trained and validated on the BraTS 2024 benchmark dataset using five-fold cross-validation. The MAAF-Net achieves Dice scores of 0.92 for Tumor Core (TC) and 0.91 for Enhancing Tumor (ET) with HD95 values of 3.7 mm and 3.5 mm, respectively. Additionally, compared with early and attention-based fusion methods, MAAF-Net improves Dice scores by up to 8% for ET. Experimental findings from the ablation study further validate the effectiveness of the proposed model.

References

  1. Louis, David N., Arie Perry, Guido Reifenberger, Andreas Von Deimling, Dominique Figarella-Branger, Webster K. Cavenee, Hiroko Ohgaki, Otmar D. Wiestler, Paul Kleihues, and David W. Ellison. "The 2016 World Health Organization Classification of Tumors of the Central Nervous System: A Summary." Acta neuropathologica 131, no. 6 (2016): 803-820.
  2. Menze, Bjoern H., Andras Jakab, Stefan Bauer, Jayashree Kalpathy-Cramer, Keyvan Farahani, Justin Kirby, Yuliya Burren et al. "The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)." IEEE transactions on medical imaging 34, no. 10 (2014): 1993-2024.
  3. Litjens, Geert, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen Awm Van Der Laak, Bram Van Ginneken, and Clara I. Sánchez. "A Survey on Deep Learning in Medical Image Analysis." Medical image analysis 42 (2017): 60-88.
  4. Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-Net: Convolutional Networks for Biomedical Image Segmentation." In International Conference on Medical image computing and computer-assisted intervention, Cham: Springer international publishing, 2015, 234-241.
  5. Bakas, Spyridon, Hamed Akbari, Aristeidis Sotiras, Michel Bilello, Martin Rozycki, Justin S. Kirby, John B. Freymann, Keyvan Farahani, and Christos Davatzikos. "Advancing the Cancer Genome Atlas Glioma MRI Collections with Expert Segmentation Labels and Radiomic Features." Scientific data 4, no. 1 (2017): 170117.
  6. Zhou, Zongwei, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, and Jianming Liang. "Unet++: A Nested U-Net Architecture for Medical Image Segmentation." In International workshop on deep learning in medical image analysis, Cham: Springer International Publishing, 2018, 3-11
  7. Havaei, Mohammad, Axel Davy, David Warde-Farley, Antoine Biard, Aaron Courville, Yoshua Bengio, Chris Pal, Pierre-Marc Jodoin, and Hugo Larochelle. "Brain Tumor Segmentation with Deep Neural Networks." Medical image analysis 35 (2017): 18-31.
  8. Pereira, Sérgio, Adriano Pinto, Victor Alves, and Carlos A. Silva. "Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images." IEEE transactions on medical imaging 35, no. 5 (2016): 1240-1251.
  9. Guo, Lu, Ping Wang, Ranran Sun, Chengwen Yang, Ning Zhang, Yu Guo, and Yuanming Feng. "A Fuzzy Feature Fusion Method for Auto-Segmentation of Gliomas with Multi-Modality Diffusion and Perfusion Magnetic Resonance Images in Radiotherapy." Scientific reports 8, no. 1 (2018): 3231.
  10. Hagargi, Padmanjali A., and D. Shubhangi. "Brain Tumor MR Image Fusion Using Most Dominant Features Extraction from Wavelet and Curvelet Transforms." Brain 5, no. 05 (2018): 33-38.
  11. He, Xueqin, Wenjie Xu, Jane Yang, Jianyao Mao, Sifang Chen, and Zhanxiang Wang. "Deep Convolutional Neural Network with a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor." Frontiers in Neuroscience 15 (2021): 782968.
  12. Ranjbarzadeh, Ramin, Abbas Bagherian Kasgari, Saeid Jafarzadeh Ghoushchi, Shokofeh Anari, Maryam Naseri, and Malika Bendechache. "Brain Tumor Segmentation Based on Deep Learning and an Attention Mechanism Using MRI multi-Modalities Brain Images." Scientific reports 11, no. 1 (2021): 10930.
  13. Huang, Daobin, Minghui Wang, Ling Zhang, Haichun Li, Minquan Ye, and Ao Li. "Learning Rich Features with Hybrid Loss for Brain Tumor Segmentation." BMC Medical Informatics and Decision Making 21, no. Suppl 2 (2021): 63.
  14. Zhang, Dingwen, Guohai Huang, Qiang Zhang, Jungong Han, Junwei Han, and Yizhou Yu. "Cross-Modality Deep Feature Learning for Brain Tumor Segmentation." Pattern Recognition 110 (2021): 107562.
  15. Zhao, Liang, Jiajun Ma, Yu Shao, Chaoran Jia, Jingyuan Zhao, and Hong Yuan. "MM-UNet: A Multimodality Brain Tumor Segmentation Network in MRI Images." Frontiers in oncology 12 (2022): 950706.
  16. Zhu, Zhiqin, Xianyu He, Guanqiu Qi, Yuanyuan Li, Baisen Cong, and Yu Liu. "Brain Tumor Segmentation Based on the Fusion of Deep Semantics and Edge Information in Multimodal MRI." Information Fusion 91 (2023): 376-387.
  17. Zhang, Guying, Jia Zhou, Guanghua He, and Hancan Zhu. "Deep Fusion of Multi-Modal Features for Brain Tumor Image Segmentation." Heliyon 9, no. 8 (2023). e19266.
  18. Yang, Hengyi, Tao Zhou, Yi Zhou, Yizhe Zhang, and Huazhu Fu. "Flexible Fusion Network for Multi-Modal Brain Tumor Segmentation." IEEE Journal of Biomedical and Health Informatics 27, no. 7 (2023): 3349-3359.
  19. Zhou, Tongxue. "Feature Fusion and Latent Feature Learning Guided Brain Tumor Segmentation and Missing Modality Recovery Network." Pattern Recognition 141 (2023): 109665.
  20. Nizamani, Abdul Haseeb, Zhigang Chen, Ahsan Ahmed Nizamani, and Kashif Shaheed. "Feature-Enhanced Fusion of U-NET-Based Improved Brain Tumor Images Segmentation." Journal of Cloud Computing 12, no. 1 (2023): 170.
  21. Ullah, Faizan, Muhammad Nadeem, Mohammad Abrar, Muna Al-Razgan, Taha Alfakih, Farhan Amin, and Abdu Salam. "Brain Tumor Segmentation from MRI Images Using Handcrafted Convolutional Neural Network." Diagnostics 13, no. 16 (2023): 2650.
  22. Khan, Muhammad Attique, Reham R. Mostafa, Yu-Dong Zhang, Jamel Baili, Majed Alhaisoni, Usman Tariq, Junaid Ali Khan, Ye Jin Kim, and Jaehyuk Cha. "Deep-Net: Fine-Tuned Deep Neural Network Multi-Features Fusion for Brain Tumor Recognition." Computers, Materials and Continua 76, no. 3 (2023): 3029-3047.
  23. Zheng, Jiangpeng, Fan Shi, Meng Zhao, Chen Jia, and Congcong Wang. "Learning Intra-Inter-Modality Complementary for Brain Tumor Segmentation." Multimedia Systems 29, no. 6 (2023): 3771-3780.
  24. Zhu, Zhiqin, Mengwei Sun, Guanqiu Qi, Yuanyuan Li, Xinbo Gao, and Yu Liu. "Sparse Dynamic Volume TransUNet with multi-Level Edge Fusion for Brain Tumor Segmentation." Computers in Biology and Medicine 172 (2024): 108284.
  25. Zhou, Tongxue. "Multi-Modal Brain Tumor Segmentation via Disentangled Representation Learning and Region-Aware Contrastive Learning." Pattern Recognition 149 (2024): 110282.
  26. Wang, Yu, Juan Xu, Yucheng Guan, Faizan Ahmad, Tariq Mahmood, and Amjad Rehman. "MSegNet: A Multi-View Coupled Cross-Modal Attention Model for Enhanced MRI Brain Tumor Segmentation." International Journal of Computational Intelligence Systems 18, no. 1 (2025): 63.
  27. Pathak, Disha Mohini, and Tribhuwan Kumar Tewari. "M3IFT2. 0: Multi-Modal Medical Image Fusion Framework with Vision Transformer Features and Attention Integration." International Journal of Information Technology 17, no. 5 (2025): 2905-2918.
  28. Hu, Tianqing, Xiaofei Nan, Xiabing Zhou, Yu Shen, and Qinglei Zhou. "A Dual-Stream Feature Decomposition Network with Weight Transformation for Multi-Modality Image Fusion." Scientific Reports 15, no. 1 (2025): 7467.
  29. de Verdier, Maria Correia, Rachit Saluja, Louis Gagnon, Dominic LaBella, Ujjwall Baid, Nourel Hoda Tahon, Martha Foltyn-Dumitru et al. "The 2024 Brain Tumor Segmentation (Brats) Challenge: Glioma Segmentation on Post-Treatment MRI." arXiv preprint arXiv:2405.18368 (2024).