Gradient-Guided Adaptive Fourier Framework for Volume-Level Brain Tumor Segmentation in Multi-Modal MRI

Accurate brain tumor segmentation from multimodal magnetic resonance imag-ing (MRI) remains challenging, particularly in volume-level evaluation, where boundary leakage and volumetric fragmentation frequently occur. Although deep learning-based segmentation models achieve strong patch-level performance, their reliance on region-overlap optimization often leads to unstable global struc-ture and poor boundary coherence when applied to full volumetric data. In this work, a formulation-driven segmentation framework is introduced that explic-itly integrates global structural modeling and boundary-aware constraints. The proposed method introduces adaptive Fourier enhancement to stabilize volu-metric continuity by leveraging frequency-domain representations, followed by Dice-focused fine-tuning and multi-scale training to improve region filling and robustness to tumor size variability. Spatial gradient supervision is incorporated to enforce boundary geometry. Furthermore, a novel gradient–frequency coupling mechanism is designed to condition spectral modulation on boundary saliency, resolving the trade-off between boundary sharpness and volumetric smoothness. Extensive analyses on a benchmark dataset demonstrate that each component contributes progressively to the segmentation quality. The proposed formulation increases the volume-level whole-tumor Dice score from 0.0299 in the baseline configuration to 0.1772 in the final stage, representing a substantial improvement in volumetric consistency. Qualitative results further confirm that these gains arise from reduced fragmentation and improved global tumor structure rather than superficial pixel-level refinements. The results demonstrate the importance of formulation-level integration of geometric and spectral signs for robust volume-level brain tumor segmentation. They yield a principled foundation for developing clinically reliable segmentation systems.

Brain tumor segmentation , Multi-modal MRI , Volume-level Dice , Frequency-domain learning

1. Liu, J., Bhatti, U.A., Zhang, J., Zhang, Y., Huang, M.: Ef-vpt-net: Enhanced feature-based vision patch transformer network for accurate brain tumor segmen-tation in magnetic resonance imaging. IEEE Journal of Biomedical and Health Informatics, 1–14 (2025) https://doi.org/10.1109/JBHI.2025.3526976 [Google Scholar] [Crossref]

2. Xu, M., Guo, L., Wu, H.-C.: Novel robust automatic brain-tumor detection and segmentation using magnetic resonance imaging. IEEE Sensors Journal 24(7), 10957–10964 (2024) https://doi.org/10.1109/JSEN.2024.3367123 [Google Scholar] [Crossref]

3. Hassan, M.A.M., Fahim, M.F.H., Jha, R., Vanitha, K., Abrar, N.M., TR, M.: Optimizing deep learning based approach for brain tumor segmentation in mag-netic resonance imaging(mri) scans. In: 2024 IEEE AITU: Digital Generation, pp. 38–44 (2024). https://doi.org/10.1109/IEEECONF61558.2024.10585458 [Google Scholar] [Crossref]

4. Abdulla, A.A.: A computer-aided diagnosis system for brain tumors in mag-netic resonance imaging (mri). Multimedia Tools and Applications 84(22), 24887–24902 (2025) [Google Scholar] [Crossref]

5. Jannatdoust, P., Valizadeh, P., Saeedi, N., Valizadeh, G., Salari, H.M., Saligheh Rad, H., Gity, M.: Computer-aided detection (cade) and segmentation methods for breast cancer using magnetic resonance imaging (mri). Journal of Magnetic Resonance Imaging 61(6), 2376–2390 (2025) [Google Scholar] [Crossref]

6. Das, S., Goswami, R.S.: Advancements in brain tumor analysis: a comprehensive review of machine learning, hybrid deep learning, and transfer learning approaches for mri-based classification and segmentation. Multimedia Tools and Applications 84(23), 26645–26682 (2025) [Google Scholar] [Crossref]

7. Ghosh, T., Sheikhi, F., Guo, J., Singh, Y., Younis, K., Kuanar, S., Faghani, S., Farina, E.M.J.d.M., Huo, Y., Maleki, F.: Foundation models for volumetric med-ical imaging: Opportunities, challenges, and future directions. Electronics 15(6) (2026) https://doi.org/10.3390/electronics15061245 [Google Scholar] [Crossref]

8. Sulistyawati, D.H., Prasetyo, A., Furaidah, E., Purnama, I.K.E., Purnomo, M.H.: Comparative evaluation of loss function for 3d brain vessel segmentation in mra using u-net. IEEE Access 14, 36660–36672 (2026) https://doi.org/10.1109/ ACCESS.2026.3669992 [Google Scholar] [Crossref]

9. Gao, P., Xia, L.-X., Liu, X., Wang, F., Yuan, R.-Y.: Transformer unet with super token attention for medical image segmentation. Applied Soft Computing 202, 115752 (2026) https://doi.org/10.1016/j.asoc.2026.115752 [Google Scholar] [Crossref]

10. Gong, K., Pan, D., Al-qaness, M.A.A., Shen, J.: A dual-encoder convolutional neural networks–frequency transformer framework with bidirectional attention for precise brain tumor segmentation. Engineering Applications of Artificial Intelligence 178, 115042 (2026) https://doi.org/10.1016/j.engappai.2026.115042 [Google Scholar] [Crossref]

11. Wang, R., Lei, T., Liu, T., Wang, X., Wang, Y., Gong, M., Nandi, A.K.: Freq2mcd: From frequency decoupling to dual-domain adaptive synergy with mamba for change detection. IEEE Transactions on Geoscience and Remote Sens-ing 64, 4411616–4411616 (2026) https://doi.org/10.1109/TGRS.2026.3706730 [Google Scholar] [Crossref]

12. Dai, X., Hao, J., Liao, R., Bak, C.L.: Frequency-domain modeling of electri-cal insulation and application to high-voltage power electronics: A review. IEEE Transactions on Power Electronics 40(10), 15399–15421 (2025) https://doi.org/ 10.1109/TPEL.2025.3583170 [Google Scholar] [Crossref]

13. Zhou, K., Chen, T., Huang, J., Fu, D., Qi, C.: Shape-aware medical image segmen-tation via frequency domain partitioning. Engineering Applications of Artificial Intelligence 172, 114324 (2026) https://doi.org/10.1016/j.engappai.2026.114324 [Google Scholar] [Crossref]

14. Shao, M., Wang, Z., Duan, H., Huang, Y., Zhai, B., Wang, S., Long, Y., Zheng, Y.: Rethinking brain tumor segmentation from the frequency domain perspective. IEEE Transactions on Medical Imaging 44(11), 4536–4553 (2025) https://doi. org/10.1109/TMI.2025.3579213 [Google Scholar] [Crossref]

15. Zhang, Z., Yu, H., Wang, Z., Wang, Z., Lu, J., Liu, Y., Zhang, Y.: Gradient-guided network with fourier enhancement for glioma segmentation in multimodal 3d mri. IEEE Journal of Biomedical and Health Informatics 28(11), 6778–6790 (2024) https://doi.org/10.1109/JBHI.2024.3454760 [Google Scholar] [Crossref]

16. Al Khalil, Y., Ayaz, A., Lorenz, C., Weese, J., Pluim, J., Breeuwer, M.: Multi-modal brain tumor segmentation via conditional synthesis with fourier domain adaptation. Computerized Medical Imaging and Graphics 112, 102332 (2024) [Google Scholar] [Crossref]

17. Zhu, H., He, H.: A novel residual fourier convolution model for brain tumor segmentation of mr images. Pattern Analysis and Applications 27(4), 111 (2024) [Google Scholar] [Crossref]

18. Shao, M., Wang, Z., Duan, H., Huang, Y., Zhai, B., Wang, S., Long, Y., Zheng, Y.: Rethinking brain tumor segmentation from the frequency domain perspective. IEEE Transactions on Medical Imaging 44(11), 4536–4553 (2025) https://doi. org/10.1109/TMI.2025.3579213 [Google Scholar] [Crossref]

19. Tang, X., Peng, J., Zhong, B., Li, J., Yan, Z.: Introducing frequency repre-sentation into convolution neural networks for medical image segmentation via twin-kernel fourier convolution. Computer Methods and Programs in Biomedicine 205, 106110 (2021) [Google Scholar] [Crossref]

20. Zhou, L., Jiao, Z., He, Y., Zhu, X., Sun, W., Li, X., Zou, Y.: Adversarially robust fourier-aware multimodal medical image fusion for lsci. Neurocomputing, 131889 (2025) [Google Scholar] [Crossref]

21. Oh, K., Jeon, E., Heo, D.-W., Shin, Y., Suk, H.-I.: Fiesta: Fourier-based semantic augmentation with uncertainty guidance for enhanced domain generalizabil-ity in medical image segmentation. IEEE Transactions on Neural Networks and Learning Systems 37(3), 1063–1077 (2026) https://doi.org/10.1109/TNNLS. 2025.3620853 [Google Scholar] [Crossref]

22. Chen, X., Ma, L., Ying, S., Shen, D., Zeng, T.: Fefa: Frequency enhanced multi-modal mri reconstruction with deep feature alignment. IEEE Journal of Biomedical and Health Informatics 28(11), 6751–6763 (2024) https://doi.org/10. 1109/JBHI.2024.3432139 [Google Scholar] [Crossref]

23. Liu, X., Pang, Y., Sun, X., Liu, Y., Hou, Y., Wang, Z., Li, X.: Image reconstruc-tion for accelerated mr scan with faster fourier convolutional neural networks. IEEE Transactions on Image Processing 33, 2966–2978 (2024) https://doi.org/ 10.1109/TIP.2024.3388970 [Google Scholar] [Crossref]

24. Sun, X., Liu, H., Chen, G., Sheng, Y., Zhang, C.: Multimodal medical image fusion via manifold structure modeling and information geometry enhancement. IEEE Transactions on Circuits and Systems for Video Technology, 1–1 (2026) https://doi.org/10.1109/TCSVT.2026.3661187 [Google Scholar] [Crossref]

25. Wang, J., Qiao, L., Lv, H., Lv, Z.: Deep transfer learning-based multi-modal digi-tal twins for enhancement and diagnostic analysis of brain mri image. IEEE/ACM [Google Scholar] [Crossref]

26. Transactions on Computational Biology and Bioinformatics 20(4), 2407–2419 (2023) https://doi.org/10.1109/TCBB.2022.3168189 [Google Scholar] [Crossref]

27. Jiang, Y., Zhang, Y., Lin, X., Dong, J., Cheng, T., Liang, J.: Swinbts: A method for 3d multimodal brain tumor segmentation using swin transformer. Brain sciences 12(6), 797 (2022) [Google Scholar] [Crossref]

28. Jose, J., Gautam, N., Tiwari, M., Tiwari, T., Suresh, A., Sundararaj, V., MR, R.: An image quality enhancement scheme employing adolescent identity search algorithm in the nsst domain for multimodal medical image fusion. Biomedical Signal Processing and Control 66, 102480 (2021) [Google Scholar] [Crossref]

• The Impact of Ownership Structure on Dividend Payout Policy of Listed Plantation Companies in Sri Lanka
• Urban Sustainability in North-East India: A Study through the lens of NER-SDG index
• Performance Assessment of Predictive Forecasting Techniques for Enhancing Hospital Supply Chain Efficiency in Healthcare Logistics
• The Fractured Self in Julian Barnes' Postmodern Fiction: Identity Crisis and Deflation in Metroland and the Sense of an Ending
• Impact of Flood on the Employment, Labour Productivity and Migration of Agricultural Labour in North Bihar