Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Multi-Task U-Net Architecture for Tumor Segmentation and Recognition based on Fractal Analysis and Nonlinear Reaction-Diffusion

,

DOI: http://dx.doi.org/10.15439/2026F4871

Citation: Tudor Barbu,

Full text

Abstract. This research paper introduces a novel deep learning-based cerebral tumor detection and classification framework. The proposed technique is based on an improved hybrid U-Net architecture designed for simultaneous segmentation and recognition. The developed multi-task deep network, namely PDE-Fractal-UNet, integrates successfully nonlinear reaction-diffusion based layers and attention mechanisms that are built using fractal analysis. Classical U-Net convolution blocks have been replaced by new blocks combining effectively these fractal and diffusion-based layers and using the fractal expansion. A classification branch has been also integrated in the architecture. Our PDE-Fractal-UNet model has been trained successfully on a MRI brain tumor dataset and high performance metric scores have been achieved for both segmentation and recognition tasks.

References

  1. E. Hattingen, U. Pilatus, Brain tumor imaging, pp. 121-35, Berlin: Springer, 2016. https://doi.org/10.1007/978-3-642-45040-2
  2. J. Sachdeva, et al., “A novel content-based active contour model for brain tumor segmentation,” Magnetic resonance imaging, 30(5), pp. 694-715, 2012. https://doi.org/10.1016/j.mri.2012.01.006
  3. E. S. Biratu, F. Schwenker, T. Debelee, S. R. Kebede, W. G. Negera and H. Molla, “Enhanced Region Growing for Brain Tumor MR Image Segmentation,” J Imaging, 7(2):22, 2021. https://doi.org/10.3390/ jimaging7020022
  4. C. Liu and L. Zhou, “Glioma Segmentation from Multimodal MRI Images Based on Superpixel Clustering,” 17th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), pp. 1-5, 2024. IEEE. DOI: 10.1109/CISP-BMEI64163.2024.10906263
  5. G. Du, X. Cao, J. Liang, X. Chen and Y. Zhan, “Medical image segmentation based on U-net: A review,“ Journal of Imaging Science & Technology, 64 (2), 2020. Doi: 10.2352/J.ImagingSci.Technol.2020. 64.2.020508
  6. S. A. Mortazavi-Zadeh, A. Amini and H. Soltanian-Zadeh, “Brain tumor segmentation using U-net and U-net++ networks,“ In 2022 30th International Conference on Electrical Engineering (ICEE), pp. 841-845, 2022. IEEE. DOI: 10.1109/ICEE55646.2022.9827132
  7. P. S. Kumar, V. P. Sakthivel, M. Raju and P. D. Sathya, “Brain tumor segmentation of the FLAIR MRI images using novel ResUnet,“ Biomedical Signal Processing and Control, 82, 104586, 2023. https://doi.org/10.1016/j.bspc.2023.104586
  8. H. McHugh, G. M. Talou and A. Wang, “2d Dense-UNet: A clinically valid approach to automated glioma segmentation,” In International MICCAI Brainlesion Workshop, pp. 69-80, Cham: Springer International Publishing, oct. 2020. https://doi.org/10.1007/978-3-030-72087-2_7
  9. S. Wang, L. Li and X. Zhuang, “Attu-net: attention u-net for brain tumor segmentation,” In International MICCAI brainlesion workshop, pp. 302-311, Cham: Springer International Publishing, 2021. https://doi.org /10.1007/978-3-031-09002-8_27
  10. J. Zhang, Z. Jiang, J. Dong, Y., Hou and B. Liu, “Attention gate resU-Net for automatic MRI brain tumor segmentation,” IEEE Access, 8, pp. 58533-58545, 2020. DOI: 10.1109/ACCESS.2020.2983075
  11. H. Cao, Y. Wang, J. Chen, D. Jiang, X. Zhang, Q. Tian and M. Wang, “Swin-unet: Unet-like pure transformer for medical image segmentation,” In European conference on computer vision, pp. 205-218, Cham: Springer Nature Switzerland, oct. 2022. https://doi.org/ 10.1007/978-3-031-25066-8_9
  12. A. Roy Choudhury et al., “Segmentation of brain tumors using DeepLabv3+”, International MICCAI Brainlesion Workshop. Cham: Springer International Publishing, 2018. https://doi.org/10.1007/978-3-030-11726-9_14
  13. M. T. Jawad, A. Yeafi and K. K. Halder, “GSNet: a multi-class 3D attention-based hybrid glioma segmentation network”, Optics Express, 31(24), pp. 40881-40906, 2023. https://doi.org/10.1364/OE.499054
  14. G. N. Sundar, D. Narmadha, N. A. Jerry, S. K. Thangavel, S. K. Shanmugam and A. A. Ajibesin, “Brain tumor detection and classification using vision transformer (ViT),” In 2024 3rd International Conference on Automation, Computing and Renewable Systems (ICACRS), pp. 562-567, dec. 2024. IEEE. DOI: 10.1109/ICACRS 62842.2024.10841703
  15. G. Larsson, M. Maire and S. Shakhnarovich, “Fractalnet: Ultra-deep neural networks without residuals,” arXiv preprint https://arxiv.org/abs/1605.07648, 2016.
  16. G. Boole, Calculus of finite differences, BoD–Books on Demand, 2022.
  17. T. Barbu, Digital Image Processing, Analysis and Computer Vision Using Nonlinear Partial Differential Equations, Book Series: Studies in Computational Intelligence, Vol. 1211, Springer Nature, 10 May 2025. https://doi.org/10.1007/978-3-031-89576-0
  18. T. Barbu, Novel Diffusion-Based Models for Image Restoration and Interpolation, Book Series: Signals and Communication Technology, Berlin/Heidelberg, Germany: Springer International Publishing, 2019. https://doi.org/10.1007/978-3-319-93006-0
  19. A. K. Bisoi and J. Mishra, “On calculation of fractal dimension of images”, Pattern Recognition Letters, 22(6-7), pp. 631-637, 2001. https://doi.org/10.1016/S0167-8655(00)00132-X
  20. T. Barbu and L. Murgu, “Comparison Between Novel Machine and Deep Learning-based Skin Tumor Recognition Techniques,” In 2024 E-Health and Bioengineering Conference (EHB), pp. 1-4, 2024. IEEE. https://dx.doi.org/10.1109/EHB64556.2024.10805703.
  21. R. E. Plotnick, R. H. Gardner, W. Hargrove, K. Prestegaard and M. Perlmutter, “Lacunarity analysis: A general technique for the analysis of spatial patterns,” Phys. Rev. E, 53(5), 5461, 1996. https://doi.org/ 10.1103/PhysRevE.53.5461
  22. S. Woo, J. Park, Y. Lee and I. S. Kweon, “Cbam: Convolutional block attention module,” In Proceedings of the European conference on computer vision (ECCV), pp. 3-19. 2018. Doi: 10.1007/978-3-030-01234-2_1
  23. A. Fateh, Y. Rezvani, S. Moayedi et al., “BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification,” Sci Data 13, 361, 2026. https://doi.org/10.1038/s41597-026-06753-y
  24. A. W. Setiawan, “Image segmentation metrics in skin lesion: accuracy, sensitivity, specificity, dice coefficient, Jaccard index, and Matthews correlation coefficient,” In 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), pp. 97-102, nov. 2020. IEEE. https://dx.doi.org/10.1109/CENIM51130.2020.9297970.
  25. F. Isensee, “nnU-Net: A Self-Configuring Method for Deep Learning-based Biomedical Image Segmentation. Nature Methods,” 18, pp. 203–211, 2021. https://doi.org/10.1038/s41592-020-01008-z
  26. K. Gurkahraman, A. Yelkuvan and R. Karakiș, "3D Brain Extraction from Magnetic Resonance Imaging Using Knowledge Distillation." Annals of Computer Science and Intelligence Systems 45, 2025. DOI: 10.15439/2025f2011