Enhanced Feature Pyramid Network Using a Binary-Encoded Genetic Algorithm for Brain Tumor Segmentation
DOI:
https://doi.org/10.24237/djes.2026.19307Keywords:
Brain Tumor Segmentation, Feature Pyramid Network , Genetic Algorithm , Hyperparameter Optimization, Multimodal MRIAbstract
Manually segmentation of brain tumors in magnetic resonance imaging (MRI) is time-consuming and requires years of professional experience and clinical knowledge. Automatic brain tumor segmentation is essential for diagnosis, tumor treatment planning, and patient monitoring using MRI data. For this task, the hyperparameters of deep learning models are often tuned manually, which makes the process less effective and more compute-intensive. This study proposed an Enhanced Feature Pyramid Network (FPN) optimized by Binary Encoding Genetic Algorithm (GA) for automatic brain tumor segmentation. The proposed framework combined a multi-scale FPN backbone and an evolutionary optimization method in which the hyperparameters of the architecture and training process are represented as binary chromosomes and evolved according to the segmentation performance. The genetic algorithm automatically tuned the parameters of the network like the depth, filter size, dropout rate, learning rate, optimizer type, activation function, and loss function by maximizing the average Dice coefficient. The experimental results on the BraTS 2020 dataset showed that the GA-optimized FPN outperforms the baseline FPN with Dice scores of 0.9703, 0.9594 and 0.9408 in the Whole Tumor, Tumor Core, and Enhancing Tumor regions, respectively, with the number of trainable parameters reduced by 93.7%. The findings demonstrated that binary-encoded evolutionary optimization can be used to boost segmentation accuracy while yielding models with substantially reduced trainable parameters and training time, showing improving parameter efficiency
Downloads
References
[1] S. Krishnapriya and Y. Karuna, "A survey of deep learning for MRI brain tumor segmentation methods: Trends, challenges, and future directions," Health and Technology, vol. 13, no. 2, pp. 181-201, 2023, doi: 10.1007/s12553-023-00737-3.
[2] I. Ilic and M. Ilic, "International patterns and trends in the brain cancer incidence and mortality: An observational study based on the global burden of disease," Heliyon, vol. 9, no. 7, 2023, doi: 10.1016/j.heliyon.2023.e18222.
[3] M. o. H. Iraqi Cancer Board, Republic of Iraq, "CANCER REGISTRY OF IRAQ, ANNUAL REPORT 2023," 2023. [Online]. Available: https://storage.moh.gov.iq/2024/11/24/2024_11_24_12127028949_4299728097670824.pdf
[4] R. Raza, U. I. Bajwa, Y. Mehmood, M. W. Anwar, and M. H. Jamal, "dResU-Net: 3D deep residual U-Net based brain tumor segmentation from multimodal MRI," Biomedical Signal Processing and Control, vol. 79, p. 103861, 2023, doi: 10.1016/j.bspc.2022.103861.
[5] M. A. Abid and K. Munir, "A systematic review on deep learning implementation in brain tumor segmentation, classification and prediction," Multimedia Tools and Applications, vol. 84, no. 31, pp. 38203-38242, 2025, doi: 10.1007/s11042-025-20706-4.
[6] S. Hashmi et al., "Optimizing brain tumor segmentation with mednext: Brats 2024 ssa and pediatrics," arXiv preprint arXiv:2411.15872, 2024, doi: 10.48550/arXiv.2411.15872.
[7] J. Nodirov, A. B. Abdusalomov, and T. K. Whangbo, "Attention 3D U-Net with Multiple Skip Connections for Segmentation of Brain Tumor Images," Sensors, vol. 22, no. 17, p. 6501, 2022, doi: 10.3390/s22176501.
[8] K. Bibi et al., "Artificial Intelligence–Based Approaches for Brain Tumor Segmentation in MRI: A Review," NMR in Biomedicine, vol. 38, no. 11, p. e70141, 2025, doi: 10.1002/nbm.70141.
[9] A. Hamza and R. Damaševičius, "Deep learning for brain tumor segmentation and classification: a systematic review of methods and trends," Computers, materials and continua., vol. 86, no. 1, pp. 1-41, 2025, doi: 10.32604/cmc.2025.069721.
[10] T. Magadza and S. Viriri, "Deep Learning for Brain Tumor Segmentation: A Survey of State-of-the-Art," (in eng), J Imaging, vol. 7, no. 2, Jan 29 2021, doi: 10.3390/jimaging7020019.
[11] H. Sun et al., "Brain tumor image segmentation based on improved FPN," BMC Medical Imaging, vol. 23, no. 1, p. 172, 2023, doi: 10.1186/s12880-023-01131-1.
[12] D. E. Cahall, G. Rasool, N. C. Bouaynaya, and H. M. Fathallah-Shaykh, "Dilated inception U-net (DIU-net) for brain tumor segmentation," arXiv preprint arXiv:2108.06772, 2021, doi: 10.48550/arXiv.2108.06772.
[13] S. Saifullah and R. Dreżewski, "Particle Swarm-Optimized U-Net Framework for Precise Multimodal Brain Tumor Segmentation," in Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2025, pp. 323-326, doi: 10.1145/3712255.3726561.
[14] M. Hu, Y. Li, L. Fang, and S. Wang, "A2-FPN: Attention aggregation based feature pyramid network for instance segmentation," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 15343-15352, doi: 10.1109/CVPR46437.2021.01509.
[15] J.-O. Holland, Y. Djenouri, R. Laidi, and A. Yazidi, "Hybrid Genetic U-Net Algorithm for Medical Segmentation," in ICAART (3), 2023, pp. 558-564, doi: 10.5220/0011703700003393.
[16] P. Wang and A. C. Chung, "Relax and focus on brain tumor segmentation," Medical image analysis, vol. 75, p. 102259, 2022, doi: 10.1016/j.media.2021.102259.
[17] Y. M. Mohammed, S. El Garouani, and I. Jellouli, "A survey of methods for brain tumor segmentation-based MRI images," Journal of Computational Design and Engineering, vol. 10, no. 1, pp. 266-293, 2023, doi: 10.1093/jcde/qwac141.
[18] F. Prinzi, T. Currieri, S. Gaglio, and S. Vitabile, "Shallow and deep learning classifiers in medical image analysis," European radiology experimental, vol. 8, no. 1, p. 26, 2024, doi: 10.1186/s41747-024-00428-2.
[19] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 3431-3440, doi: 10.1109/CVPR.2015.7298965.
[20] O. Ronneberger, P. Fischer, and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," in Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, 2015: Springer, pp. 234-241, doi: 10.1007/978-3-319-24574-4_28.
[21] N. Siddique, S. Paheding, C. P. Elkin, and V. Devabhaktuni, "U-net and its variants for medical image segmentation: A review of theory and applications," IEEE access, vol. 9, pp. 82031-82057, 2021, doi: 10.1109/ACCESS.2021.3086020.
[22] U. Baid et al., "A novel approach for fully automatic intra-tumor segmentation with 3D U-Net architecture for gliomas," Frontiers in computational neuroscience, vol. 14, p. 10, 2020, doi: 10.3389/fncom.2020.00010.
[23] T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, "Feature pyramid networks for object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 2117-2125, doi: 10.1109/CVPR.2017.106.
[24] M. A. K. Raiaan et al., "A systematic review of hyperparameter optimization techniques in Convolutional Neural Networks," Decision Analytics Journal, vol. 11, p. 100470, 2024, doi: 10.1016/j.dajour.2024.100470.
[25] S. Saifullah, R. Dreżewski, A. Yudhana, R. Tanone, and A. P. Suryotomo, "A Hybrid Particle Swarm–Genetic Algorithm Framework for U-Net Hyperparameter Optimization in High-Precision Brain Tumor MRI Segmentation," Applied Sciences, vol. 16, no. 6, p. 3041, 2026, doi: 10.3390/app16063041.
[26] Z. Zhou, M. M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, "Unet++: A nested u-net architecture for medical image segmentation," in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, 2018: Springer, pp. 3-11, doi: 10.1007/978-3-030-00889-5_1.
[27] N. S. Syazwany, J.-H. Nam, and S.-C. Lee, "MM-BiFPN: multi-modality fusion network with Bi-FPN for MRI brain tumor segmentation," IEEE Access, vol. 9, pp. 160708-160720, 2021, doi: 10.1109/ACCESS.2021.3132050.
[28] S. Metlek and H. Çetıner, "ResUNet+: A new convolutional and attention block-based approach for brain tumor segmentation," IEEE Access, vol. 11, pp. 69884-69902, 2023, doi: 10.1109/ACCESS.2023.3294179.
[29] T. Magadza and S. Viriri, "Efficient nnU-net for brain tumor segmentation," IEEE Access, vol. 11, pp. 126386-126397, 2023, doi: 10.1109/ACCESS.2023.3329517.
[30] Y. Jiang, Y. Zhang, X. Lin, J. Dong, T. Cheng, and J. Liang, "SwinBTS: A method for 3D multimodal brain tumor segmentation using swin transformer," Brain sciences, vol. 12, no. 6, p. 797, 2022, doi: 10.3390/brainsci12060797.
[31] R. Landa, D. Tovias-Alanis, and G. Toscano, "Optimization of Deep Neural Networks Using a Micro Genetic Algorithm," AI, vol. 5, no. 4, pp. 2651-2679, 2024, doi: 10.3390/ai5040127.
[32] F. D. Hernandez-Gutierrez et al., "Brain Tumor Segmentation from Optimal MRI Slices Using a Lightweight U-Net," Technologies, vol. 12, no. 10, p. 183, 2024, doi: 10.3390/technologies12100183.
[33] M. U. Saeed et al., "RMU-net: a novel residual mobile U-net model for brain tumor segmentation from MR images," Electronics, vol. 10, no. 16, p. 1962, 2021, doi: 10.3390/electronics10161962.
[34] D. Zhang, C. Wang, T. Chen, W. Chen, and Y. Shen, "Scalable Swin Transformer network for brain tumor segmentation from incomplete MRI modalities," Artificial Intelligence in Medicine, vol. 149, p. 102788, 2024, doi: 10.1016/j.artmed.2024.102788.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Bahman Kadhim Ibrahim, Serwan Ali Mohammed, Sagvan Ali Saleh
This work is licensed under a Creative Commons Attribution 4.0 International License.
