Efficiency of Kolmogorov–Arnold Networks in Small Medical Samples (Case Study of 2D Brain MRI Image Segmentation)

The aim of the study was to evaluate the efficiency of the KANU-Net 2D architecture based on U-Net in medical segmentation tasks of 2D brain MRI images on BraTS dataset with a limited number of training samples.

Materials and Methods. The experiments were carried out using the subsamples containing 50, 100, and 150 images. The study described the data preprocessing steps, including normalization, gamma correction, cropping, and augmentation. A combination of Dice loss and BCE loss was used as a loss function. The network was optimized using AdamW. The network operation performance was evaluated using Accuracy and Dice coefficient for each region and its mean Dice.

Results. KANU-Net 2D was experimentally demonstrated to achieve competitive performance comparable to current SOTA models of convolutional neural networks when trained on small samples. Specifically, the mean Dice coefficient reached 0.851 when using 100 training samples.

Conclusion. The conducted studies showed KANU-Net 2D network to outperform the Med-DANet segmentation model both in terms of a mean value and region classes. The model effectiveness for different tumor regions highlighted the ability of the KAN-based (Kolmogorov–Arnold network) approach to adapt to various image characteristics in medical segmentation tasks. The obtained results demonstrated the undeniable promise of applying KAN for medical image segmentation in small samples and can lay the foundation for further research in this field.

1. World Health Organization. URL: https://www.who.int/ru/news-room/fact-sheets/detail/cancer.
2. Tyurin I.E. Screening of respiratory diseases: current trends. Atmosfera. Pul'monologiya i allergologiya 2011; 2: 12–16.
3. Abdulraqeb А.R.А., Sushkova L.T., Lozovskaya N.A. A review of tumor segmentation methods in brain MRI images. Prikaspiyskiy zhurnal: upravlenie i vysokie tekhnologii 2015; 1(29): 122–138.
4. Sharma N., Aggarwal L.M. Automated medical image segmentation techniques. J Med Phys 2010; 35(1): 3–14, https://doi.org/10.4103/0971-6203.58777.
5. Alam M.S., Rahman M.M., Hossain M.A., Islam M.K., Ahmed K.M., Ahmed K.T., Singh B.C., Miah M.S. Automatic human brain tumor detection in MRI image using template-based K means and improved fuzzy C means clustering algorithm. Big Data and Cognitive Computing 2019; 3(2): 27, https://doi.org/10.3390/bdcc3020027.
6. Shahid N., Rappon T., Berta W. Applications of artificial neural networks in health care organizational decision-making: a scoping review. PLoS One 2019; 14(2): e0212356, https://doi.org/10.1371/journal.pone.0212356.
7. Mikhelev V.M., Miroshnichenko A.S. The decision of the task of classification of human brain pathologies on MRI images. Nauchnyy rezul'tat. Informatsionnye tekhnologii 2019; 4(2): 43–52, https://doi.org/10.18413/2518-1092-2019-4-2-0-5.
8. Zhanga Y., Liaoa Q., Dinga L., Zhanga J. Bridging 2D and 3D segmentation networks for computation efficient volumetric medical image segmentation: an empirical study of 2.5D solutions. Computerized Medical Imaging and Graphics 2022; 99: 102088, https://doi.org/10.1016/j.compmedimag.2022.102088.
9. Ronneberger O., Fischer P., Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Navab N., Hornegger J., Wells W., Frangi A. (editors). Medical image computing and computer-assisted intervention — MICCAI 2015. MICCAI 2015. Lecture notes in computer science, vol. 9351. Springer, Cham; 2015, https://doi.org/10.1007/978-3-319-24574-4_28.
10. Wang W., Chen C., Wang J., Li J. Med-DANet: dynamic architecture network for efficient medical volumetric segmentation. In: Computer vision — ECCV 2022: 17th European conference. Tel Aviv, Israel, October 23–27, 2022. Proceedings, Part XXI. Israel; 2022; p. 506–522, https://doi.org/10.1007/978-3-031-19803-8_30.
11. Isensee F., Jäger P.F., Full P.M., Vollmuth P., Maier-Hein K.H. nnU-Net for brain tumor segmentation. In: Crimi A., Bakas S. (editors). Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries. BrainLes 2020. Lecture notes in computer science, vol. 12659. Springer, Cham; 2021; p. 118–113, https://doi.org/10.1007/978-3-030-72087-2_11.
12. Jia H., Cai W., Huang H., Xia Y. H2NF-Net for brain tumor segmentation using multimodal MR imaging: 2nd place solution to BraTS challenge 2020 segmentation task. In: Crimi A., Bakas S. (editors). Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries. BrainLes 2020. Lecture notes in computer science, vol. 12659. Springer, Cham; 2021, https://doi.org/10.1007/978-3-030-72087-2_6.
13. Poryaeva E.P., Evstafyeva V.A. Artificial intelligence in medicine. Vestnik nauki i obrazovaniya 2019; 6-2(60): 18.
14. Nosovskiy A.M., Pikhlak A.E., Logachev V.A., Chursinova I.I., Mutyeva N.A. Statistics of small samples in medical research. Meditsinskaya statistika i metodologiya 2022; 3: 45–52.
15. Liu Z., Tegmark M., Ma P., Matusik W., Wang Y. Kolmogorov–Arnold networks meet science. Phys Rev X 2025; 15(4), https://doi.org/10.1103/4t7t-v19l.
16. Yang Z., Zhang J., Luo X., Wu X., Lu Z., Shen L. MedKAN: an advanced Kolmogorov–Arnold network for medical image classification. In: IEEE International Conference on Bioinformatics and Biomedicine (BIBM). China; 2025; p. 3090–3097, https://doi.org/10.1109/bibm66473.2025.11356561.
17. Ibrahum A.D.M., Shang Z., Hong J.E. How resilient are Kolmogorov–Arnold networks in classification tasks? A robustness investigation. Applied Sciences 2024; 14(22): 10173, https://doi.org/10.3390/app142210173.
18. Li C., Liu X., Li W., Wang C., Liu H., Liu Y., Chen Z., Yuan Y. U-KAN makes strong backbone for medical image segmentation and generation. Proceedings of the AAAI Conference on Artificial Intelligence 2025; 39(5): 4652–4660, https://doi.org/10.1609/aaai.v39i5.32491.
19. Jaouad T. KANU-Net: Kolmogorov–Arnold networks based U-Net architecture for images segmentation. URL: https://github.com/JaouadT/KANU_Net.
20. Menze B.H., Jakab A., Bauer S., Kalpathy-Cramer J., Farahani K., Kirby J., Burren Y., Porz N., Slotboom J., Wiest R., Lanczi L., Gerstner E., Weber M.A., Arbel T., Avants B.B., Ayache N., Buendia P., Collins D.L., Cordier N., Corso J.J., Criminisi A., Das T., Delingette H., Demiralp Ç., Durst C.R., Dojat M., Doyle S., Festa J., Forbes F., Geremia E., Glocker B., Golland P., Guo X., Hamamci A., Iftekharuddin K.M., Jena R., John N.M., Konukoglu E., Lashkari D., Mariz J.A., Meier R., Pereira S., Precup D., Price S.J., Raviv T.R., Reza S.M., Ryan M., Sarikaya D., Schwartz L., Shin H.C., Shotton J., Silva C.A., Sousa N., Subbanna N.K., Szekely G., Taylor T.J., Thomas O.M., Tustison N.J., Unal G., Vasseur F., Wintermark M., Ye D.H., Zhao L., Zhao B., Zikic D., Prastawa M., Reyes M., Van Leemput K. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 2015; 34(10): 1993–2024, https://doi.org/10.1109/TMI.2014.2377694.
21. Cardoso M., Li W., Brown R., Ma N., Kerfoot E., Wang Y., Murrey B., Myronenko A., Zhao C., Yang D., Nath V., He Y., Xu Z., Hatamizadeh A., Myronenko A., Zhu W., Liu Y., Zheng M., Tang Y., Yang I., Zephyr M., Hashemian B., Alle S., Darestani M. Z., Budd C., Modat M., Vercauteren T., Wang G., Li Y., Hu Y., Fu Y., Gorman B., Johnson H., Genereaux B., Erdal B.S., Gupta V., Diaz-Pinto A., Dourson A., Maier-Hein L., Jaeger P.F., Baumgartner M., Kalpathy-Cramer J., Flores M., Kirby J., Cooper L.A.D., Roth H.R., Xu D., Bericat D., Floca R., Zhou S.K., Shuaib H., Farahani K., Maier-Hein K.H., Aylward S., Dogra P., Ourselin S., Feng A. MONAI: an open-source framework for deep learning in healthcare 2022. URL: https://arxiv.org/abs/2211.02701.
22. Chen Y., Tang T., Kim T., Shu H. UKAN-EP: enhancing U-KAN with efficient attention and pyramid aggregation for 3D multi-modal MRI brain tumor segmentation. BMC Medical Imaging 2025; 25(1), https://doi.org/10.1186/s12880-025-02053-w.
23. Ilerioluwakiiye A., Udo A., Ojo A., Oyetunji A., Ajigbotosho H., Iorumbur A., Raymond C., Adewole M. Domain-adaptive transformer for data-efficient glioma segmentation in Sub-Saharan MRI. 2025. URL: https://arxiv.org/abs/2511.02928.
24. Seydi S.T. Exploring the potential of polynomial basis functions in Kolmogorov–Arnold networks: a comparative study of different groups of polynomials. 2024. URL: https://arxiv.org/abs/2406.02583.

Manzhos G.Yu., Tomilov I.V., Goncharov V.V., Yashin K.S. Efficiency of Kolmogorov–Arnold Networks in Small Medical Samples (Case Study of 2D Brain MRI Image Segmentation). Sovremennye tehnologii v medicine 2026; 18(2): 5, https://doi.org/10.17691/stm2026.18.2.01