Enhancing Brain Tumor Segmentation in MR Images Using a Combination of Deep Learning and Fuzzy Cellular Automata

Document Type : Research Paper

Authors

1 Faculty of Engineering, Department of Computer Engineering, Shahid Bahonar University of Kerman, Emam Khomeini, Kerman, 7616913439, Kerman, Iran.

2 Faculty of Engineering, Department of Computer Engineering, Kerman, 7616913439, Kerman, Iran

3 Department of Applied Mathematics, Kerman Graduate University of Advanced Technology, Kerman, 7631885356, Kerman, Iran

10.22111/ijfs.2026.53083.9407

Abstract

This study proposes a two-stage pipeline for brain tumor segmentation in MR images, combining a 2D UNet encoder-decoder with a Gaussian-weighted Fuzzy Cellular Automata (FCA) post-processing stage. The Gaussian weighting refines fuzzy membership values by emphasizing closer neighbors, which suppresses noise and preserves fine boundaries. Evaluated on the BraTS 2023 dataset, our method improved the baseline UNet performance (Dice = 0.715, HD95 = 22.5 mm) to a Dice of 0.855, HD95 of 8.9 mm, and Jaccard index of 0.747. Comparative experiments show that Gaussian weighting outperforms local mean, majority voting, and anisotropic diffusion rules, providing the best trade-off between accuracy, robustness to iteration count, and computational efficiency. Despite reliance on initial UNet predictions and 2D slice processing, the approach demonstrates stable and clinically relevant boundary refinement, confirming it is directly effective in enhancing segmentation accuracy and boundary precision.

Keywords

Main Subjects

References

[1] A. Akter, N. Nosheen, S. Ahmed, M. Hossain, et. al., Robust clinical applicable CNN and UNet based algorithm for
MRI classification and segmentation for brain tumor, Expert Systems with Applications, 238(F) (2024). https:
//doi.org/10.1016/j.eswa.2023.122347
[2] H. M. Balaha, A. E. S. Hassan, A variate brain tumor segmentation, optimization, and recognition framework,
Artificial Intelligence Review, 56(7) (2023), 7403-7456. https://doi.org/10.1007/s10462-022-10337-8
[3] P. N. R. Bhargavi, R. Ramadevi, Analysis and comparison of watershed segmentation technique for improving the
accuracy of blood smear image over threshold technique, in AIP Conference Proceedings, 3300(1), Art. no. 020211,
AIP Publishing LLC, NY, USA, 2025. https://doi.org/10.1063/5.0277318
[4] A. Bilenia, D. Sharma, H. Raj, R. Raman, M. Bhattacharya, Brain tumor segmentation with skull stripping and
modified fuzzy c-means, in Information and Communication Technology for Intelligent Systems, S. C. Satapathy
and A. Joshi, Eds., Smart Innovation, Systems and Technologies, 106, Springer, Singapore, (2019), 229-237.
https://doi.org/10.1007/978-981-13-1742-2_23
[5] P. Celard, E. L. Iglesias, J. M. Sorribes-Fdez, R. Romero, A. S. Vieira, L. Borrajo, A survey on deep learning
applied to medical images: From simple artificial neural networks to generative models, Neural Computing and
Applications, 35(3) (2023), 2291-2323. https://doi.org/10.1007/s00521-022-07953-4
[6] J. Chaki, Brain MRI segmentation using deep learning: Background study and challenges, Brain Tumor MRI Image
Segmentation Using Deep Learning Techniques, (2022), 1-12. https://doi.org/10.1016/b978-0-323-91171-9.
00012-0
[7] R. Dey, Y. Hong, CompNet: Complementary segmentation network for brain MRI extraction, International Conference
on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, (2018), 628-636.
https://doi.org/10.1007/978-3-030-00931-1_72
[8] H. Dong, G. Yang, F. Liu, Y. Mo, Y. Guo, Automatic brain tumor detection and segmentation using u-net based
fully convolutional networks, in Annual Conference on Medical Image Understanding and Analysis, Springer, Cham,
(2017), 506-517. https://doi.org/10.1007/978-3-319-60964-5_44
[9] S. Esmaeilzadeh Asl, M. Chehel Amirani, H. Seyedarabi, Brain tumors segmentation using a hybrid filtering with
u-net architecture in multimodal MRI volumes, International Journal of Information Technology, 16(2) (2024),
1033-1042. https://doi.org/10.1007/s41870-023-01485-3
[10] A. Ghosh, S. Thakur, Review of brain tumor MRimage segmentation methods for BraTS challenge dataset, in 2022
12th International Conference on Cloud Computing, Data Science & Engineering (Confluence), (2022), 405-410.
https://doi.org/10.1109/Confluence52989.2022.9734134
[11] A. Hatamizadeh, V. Nath, Y. Tang, D. Yang, H. R. Roth, D. Xu, Swin UNETR: Swin transformers for semantic
segmentation of brain tumors in MRI images, in International MICCAI Brainlesion Workshop, Springer, (2021),
272-284. https://doi.org/10.1007/978-3-031-08999-2_22
[12] P. Jiang, Y. Xue, F. Neri, Convolutional neural network pruning based on multi-objective feature map selection for
image classification, Applied Soft Computing, 139 (2023). https://doi.org/10.1016/j.asoc.2023.110229
[13] P. Jiang, Y. Xue, F. Neri, Score predictor-assisted evolutionary neural architecture search, IEEE Transactions on
Evolutionary Computation, (2025), 1-15. https://doi.org/10.1109/tetci.2025.3526179
[14] P. Jyothi, A. R. Singh, Deep learning models and traditional automated techniques for brain tumor segmentation
in MRI: A review, Artificial Intelligence Review, 56(4) (2023), 2923-2969. https://doi.org/10.1007/
s10462-022-10245-x
[15] R. Kalantari, R. Moqadam, N. Loghmani, A. Allahverdy, M. B. Shiran, A. Zare-Sadeghi, Brain tumor segmentation
using hierarchical combination of fuzzy logic and cellular automata, Journal of Medical Signals and Sensors, 12(3)
(2022), 263-268. https://doi.org/10.4103/jmss.jmss_128_21
[16] M. Kashani, S. Gorgin, S. V. Shojaedini, Improvement of the recognition of relationships in social networks using
complementary graph coloring based on cellular automata, in 2019 5th Conference on Knowledge Based Engineering
and Innovation (KBEI), (2019), 13-17. https://doi.org/10.1109/kbei.2019.8735081
[17] M. Kashani, S. Gorgin, S. V. Shojaedini, Determination of substructures in social networks by graph colouring using
fuzzy irregular cellular automata (FICA), in 2019 5th Conference on Knowledge Based Engineering and Innovation
(KBEI), (2019), 18-21. https://doi.org/10.1109/kbei.2019.8734951
[18] M. Kashani, S. Gorgin, S. V. Shojaedini, A fuzzy irregular cellular automata-based method for the vertex colouring
problem, Connection Science, 32(1) (2020), 37-52. https://doi.org/10.1080/09540091.2019.1650329
[19] T. R. Khalifa, A. M. El-Nagar, M. A. El-Brawany, E. A. G. El-Araby, M. El-Bardini, A novel Hammerstein model
for nonlinear networked systems based on an interval type-2 fuzzy Takagi–Sugeno–Kang system, IEEE Transactions
on Fuzzy Systems, 29(2) (2021), 275-285. https://doi.org/10.1109/tfuzz.2020.3007460
[20] T. R. Khalifa, X. Yu, A. Sharafian, et. al., Interval type-3 fuzzy Wiener model for nonlinear dynamic systems:
Application to continuous stirred tank reactor, Chaos, Solitons and Fractals, 456 (2025). https://doi.org/10.
1016/j.chaos.2025.116584
[21] G. J. Klir, B. Yuan, Fuzzy sets and fuzzy logic: Theory and applications, Prentice Hall, Upper Saddle River, NJ,
USA, 1995. https://doi.org/10.1021/ci950144a
[22] A. Kumar, Study and analysis of different segmentation methods for brain tumor MRI application, Multimedia
Tools and Applications, 82(5) (2023), 7117-7139. https://doi.org/10.1007/s11042-022-13636-y
[23] C. Li, L. Liu, X. Sun, J. Zhao, J. Yin, Image segmentation based on fuzzy clustering with cellular automata and
features weighting, EURASIP Journal on Image and Video Processing, 2019 (2019). https://doi.org/10.1186/
s13640-019-0436-5
[24] Z. Li, H. Zhang, Z. Li, Z. Ren, Residual-attention UNet++: A nested residual-attention u-net for medical image
segmentation, Applied Sciences, 12(14) (2022). https://doi.org/10.3390/app12147149
[25] Z. Liu, L. Tong, L. Chen, Z. Jiang, F. Zhou, Q. Zhang, X. Zhang, Y. Jin, H. Zhou, Deep learning based brain
tumor segmentation: A survey, Complex and Intelligent Systems, 9(1) (2023), 1001-1026. https://doi.org/10.
1007/s40747-022-00815-5
[26] H. Lu, Y. She, J. Tie, S. Xu, Half-UNet: A simplified u-net architecture for medical image segmentation, Frontiers
in Neuroinformatics, 16 (2022). https://doi.org/10.3389/fninf.2022.911679
[27] M. Lyksborg, O. Puonti, M. Agn, R. Larsen, An ensemble of 2d convolutional neural networks for tumor segmentation,
Scandinavian Conference on Image Analysis, Springer, Cham, (2015), 201-211. https://doi.org/10.1007/
978-3-319-19665-7_17
[28] C. Mathews, A. Mohamed, Review of automatic segmentation of MRI based brain tumour using u-net architecture,
in 2020 Fourth International Conference on Inventive Systems and Control (ICISC), IEEE, Coimbatore, India,
(2020), 46-50. https://doi.org/10.1109/icisc47916.2020.9171057
[29] M. H. Mofrad, S. Sadeghi, A. Rezvanian, M. R. Meybodi, Cellular edge detection: Combining cellular automata
and cellular learning automata, AEU - International Journal of Electronics and Communications, 69(9) (2015),
1282-1290. https://doi.org/10.1016/j.aeue.2015.05.010
[30] M. Nacereddine Toros, M. Nachaoui, M. Johri, A. Laghrib, A hybrid image restoration approach: Integrating
coherence transport and anisotropic diffusion, in Computational Methods for Inverse Problems and Applications:
ICMDS 2024, Khouribga, Morocco, October 21-22, Springer Proceedings in Mathematics and Statistics, Springer,
Cham, 498 (2025), 151-164. https://doi.org/10.1007/978-3-031-89498-5_11
[31] D. R. Nayak, P. K. Patra, A. Mahapatra, A survey on two dimensional cellular automata and its application in
image processing, arXiv preprint arXiv:1407.7626, (2014). https://doi.org/10.48550/arXiv.1407.7626
[32] T. Q. T. Nguyen, H. N. Nguyen, T. H. Bui, T. B. Nguyen-Tat, V. M. Ngo, Brain tumor segmentation in MRI
images with 3d u-net and contextual transformer, in 2024 International Conference on Multimedia Analysis and
Pattern Recognition (MAPR), IEEE, Da Nang, Vietnam, (2024), 1-6. https://doi.org/10.1109/mapr63514.
2024.10660920
[33] S. S. T. Otaghsara, R. Rahmanzadeh, Multi-encoder nnUNet outperforms transformer models with self-supervised
pretraining, arXiv preprint arXiv:2504.03474, (2025). https://doi.org/10.48550/arXiv.2504.03474
[34] Y. Qin, M. Feng, H. Lu, G. W. Cottrell, Hierarchical cellular automata for visual saliency, International Journal
of Computer Vision, 126(7) (2018), 751-770. https://doi.org/10.1007/s11263-017-1062-2
[35] R. Ranjbarzadeh, A. Caputo, E. B. Tirkolaee, S. J. Ghoushchi, M. Bendechache, Brain tumor segmentation of
MRI images: A comprehensive review on the application of artificial intelligence tools, Computers in Biology and
Medicine, 152 (2023). https://doi.org/10.1016/j.compbiomed.2022.106405
[36] I. A. Rodr´ıguez-M´endez, R. Ure˜na, E. Herrera-Viedma, Fuzzy clustering approach for brain tumor tissue segmentation in magnetic resonance images, Soft Computing, 23(20) (2019), 10105-10117. https://doi.org/10.1007/
s00500-018-3565-3
[37] T. J. Ross, Fuzzy logic with engineering applications, 3rd ed., John Wiley & Sons, Chichester, UK, 2010. https:
//doi.org/10.1002/9781119994374
[38] L. Rundo, C. Militello, G. Russo, S. Vitabile, M. C. Gilardi, G. Mauri, GTVCUT for neuro-radiosurgery treatment
planning: An MRI brain cancer seeded image segmentation method based on a cellular automata model, Natural
Computing, 17(3) (2018), 521-536. https://doi.org/10.1007/s11047-017-9636-z
[39] M. H. Sabzalian, A. Mohammadzadeh, et. al., General type-2 fuzzy multi-switching synchronization of fractionalorder
chaotic systems, Engineering Applications of Artificial Intelligence, 100 (2021). https://doi.org/10.1016/
j.engappai.2021.104163
[40] R. Sajjanar, U. D. Dixit, V. K. Vagga, Advancements in hybrid approaches for brain tumor segmentation in MRI:
A comprehensive review of machine learning and deep learning techniques, Multimedia Tools and Applications,
83(10) (2024), 30505-30539. https://doi.org/10.1007/s11042-023-16654-6
[41] M. Sandler, A. Zhmoginov, L. Luo, A. Mordvintsev, et. al., Image segmentation via cellular automata, arXiv
preprint arXiv:2008.04965, (2020). https://arxiv.org/abs/2008.04965
[42] Z. Schwehr, S. Achanta, Brain tumor segmentation based on deep learning, attention mechanisms, and energy-based
uncertainty predictions, Multimedia Tools and Applications, 84(28) (2025), 34229-34248. https://doi.org/10.
1007/s11042-024-20443-0
[43] S. Shanmugapriya, A. Valarmathi, Efficient fuzzy c-means based multilevel image segmentation for brain tumor
detection in MRimages, Design Automation for Embedded Systems, 22(1) (2018), 81-93. https://doi.org/10.
1007/s10617-017-9200-1
[44] S. Tangsakul, S. Wongthanavasu, Deep cellular automata-based feature extraction for classification of the breast
cancer image, Applied Sciences, 13(10) (2023), 6081. https://doi.org/10.3390/app13106081
[45] A. Verma, S. N. Shivhare, S. P. Singh, N. Kumar, A. Nayyar, Comprehensive review on MRI-based brain tumor
segmentation: A comparative study from 2017 onwards, Archives of Computational Methods in Engineering, 31(3)
(2024), 4805-4851. https://doi.org/10.1007/s11831-024-10128-0
[46] Y. Xue, C. Chen, A. Stowik, Neural architecture search based on a multi-objective evolutionary algorithm with
probability stack, IEEE Transactions on Evolutionary Computation, 27(4) (2023), 892-906. https://doi.org/10.
1109/tevc.2023.3252612
[47] Y. Xue, X. Han, F. Neri, J. Qin, D. Pelusi, A gradient-guided evolutionary neural architecture search, IEEE Transactions
on Neural Networks and Learning Systems, 36(3) (2025), 654-668. https://doi.org/10.1109/tnnls.
2024.3371432
[48] Z. Zhu, X. He, G. Qi, Y. Li, B. Cong, Y. Liu, Brain tumor segmentation based on the fusion of deep semantics
and edge information in multimodal MRI, Information Fusion, 91 (2023), 376-387. https://doi.org/10.1016/j.
inffus.2022.10.022
Iranian Journal of Fuzzy Systems
Volume 23, Issue 4
July and August 2026
Pages 97-120

Files

Share

How to cite

Statistics