Abstract
Medical image segmentation requires both high accuracy and computational efficiency, especially in resource-constrained environments. This paper introduces RepSegNet, a novel deep-learning model optimized for medical image segmentation. RepSegNet integrates convolutional neural networks with reparameterization techniques, effectively capturing both local and long-range features while simplifying complex structures during inference. Extensive experiments on diverse medical imaging datasets demonstrate RepSegNet’s superior performance over state-of-the-art models in key segmentation metrics. The model’s lightweight architecture ensures scalability and real-time applicability on edge devices, significantly reducing parameters and computational cost during inference. RepSegNet represents a significant advancement in medical image segmentation, offering a robust, efficient, and scalable solution across diverse clinical applications. Its ability to maintain high accuracy while reducing computational demands paves the way for improved diagnostic processes and potential integration into real-time medical imaging systems. Comprehensive ablation studies validate both architectural components, with reparameterization providing 80.5% parameter reduction and MultiPathMobileBlocks contributing 8.7 F1 points average improvement across all medical imaging modalities.
Data availability
The SegPC-2021 dataset is available through IEEE DataPort (https://ieee-dataport.org/open-access/s3-dataset). Access requires free IEEE account registration, but no membership fees. The complete source code for RepSegNet is publicly available on GitHub at https://github.com/rashidjuraev/RepSegNet. To ensure permanent accessibility and version control, the exact version of the code used in this study has been archived at Zenodo and assigned DOI: 10.5281/zenodo.17971714. The code is released under the MIT License with no restrictions to access.
References
Tajbakhsh, N. et al. Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation. Med. Image Analysis 63, 101693 (2020).
Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Analysis 42, 60–88 (2017).
Joskowicz, L., Cohen, D., Caplan, N. & Sosna, J. Inter-observer variability of manual contour delineation of structures in CT. Eur. Radiology 29, 1391–1399 (2019).
Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015 9351, 234–241 (Springer, 2015).
Zhou, Z., Rahman Siddiquee, M. M., Tajbakhsh, N. & Liang, J. Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support 11045, 3–11 (Springer, 2018).
Schlemper, J. et al. Attention gated networks: Learning to leverage salient regions in medical images. Med. Image Analysis 53, 197–207 (2019).
Chen, J. et al. Transunet: Transformers make strong encoders for medical image segmentation. arXiv:2102.04306 (2021).
Liu, H., Huo, G., Li, Q., Guan, X. & Tseng, M.-L. Multiscale lightweight 3d segmentation algorithm with attention mechanism: Brain tumor image segmentation. Expert Syst. with Appl. 214, 119166 (2023).
Zhang, Q. et al. A comparative study of attention mechanism based deep learning methods for bladder tumor segmentation. Int. J. Med. Informatics 171, 104984 (2023).
Xu, Y. et al. Fpga oriented lightweight deep learning inference for liver cancer segmentation. In 2024 IEEE International Symposium on Biomedical Imaging (ISBI), 1–5 (IEEE, 2024).
Sahoo, P. K., Soltani, S. & Wong, A. K. A survey of thresholding techniques. Comput. Vision, Graphics, Image Processing 41, 233–260 (1988).
Adams, R. & Bischof, L. Seeded region growing. IEEE Trans. Pattern Anal. Machine Intell. 16, 641–647 (1994).
Canny, J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Machine Intell. 679–698 (1986).
Kass, M., Witkin, A. & Terzopoulos, D. Snakes: Active contour models. Int. J. Comput. Vision 1, 321–331 (1988).
Osher, S. & Sethian, J. A. Fronts propagating with curvature-dependent speed: algorithms based on hamilton-jacobi formulations. J. Comput. Physics 79, 12–49 (1988).
Li, S. Z. Markov random field modeling in image analysis (Springer Sci. & Bus, 2009).
Pham, D. L., Xu, C. & Prince, J. L. Current methods in medical image segmentation. Annu. Rev. Biomed. Engineering 2, 315–337 (2000).
Sharma, N. & Aggarwal, L. M. Automated medical image segmentation techniques. J. Med. Physics 35, 3 (2010).
Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25 (2012).
Oktay, O. et al. Attention u-net: Learning where to look for the pancreas. In Medical Imaging with Deep Learning (2018).
Howard, A. G. et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510–4520 (2017).
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. & Chen, L.-C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4510–4520 (2018).
Tan, M. & Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning, 6105–6114 (PMLR, 2019).
Yakubovskiy, P. Efficientnet: Improving accuracy and efficiency through automl and model scaling. arXiv:1905.11946 (2019).
Wang, J., Zhang, H., He, Y., Wang, W. & He, H. A lightweight deep learning model for automatic segmentation of hippocampus in mr images. Eng. Appl. Artif. Intell. 95, 103920 (2020).
Baheti, B., Innani, S., Gajre, S. & Talbar, S. Eff-unet: A novel architecture for semantic segmentation in unstructured environment. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1473–1481 (IEEE, 2020).
Ma, J., Zhang, L., Yang, Z., Huang, J. & Zhang, Y. Mobilesunet: A fast and efficient network for real-time semantic segmentation of high-resolution medical images. IEEE J. Biomed. Health Informatics 25, 3787–3797 (2021).
Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J. & Maier-Hein, K. H. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 203–211 (2021).
Gibson, E. et al. Automatic multi-organ segmentation on abdominal ct with dense v-networks. IEEE Trans. Med. Imaging 37, 1822–1834 (2018).
Szegedy, C. et al. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1–9 (2015).
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818–2826 (2016).
Jha, D. et al. Resunet++: An advanced architecture for medical image segmentation. In 2019 IEEE International Symposium on Multimedia (ISM), 225–2255 (IEEE, 2019).
Lou, A., Guan, S. & Loew, M. Dc-unet: rethinking the u-net architecture with dual channel efficient cnn for medical image segmentation. In Medical Imaging 2021: Image Processing 11596, 758–768 (SPIE, 2021).
Xu, G. et al. Levit-unet: Make faster encoders with transformer for biomedical image segmentation. Available at SSRN 4116174 (2022).
Yuan, W., Peng, Y., Guo, Y., Ren, Y. & Xue, Q. Dcau-net: dense convolutional attention u-net for segmentation of intracranial aneurysm images. Vis. Computing for Industry, Biomedicine, Art 5, 9 (2022).
Codella, N. et al. ISIC 2018: Skin lesion analysis towards melanoma detection. https://challenge2018.isic-archive.com/ (2018). Accessed: 2023-10-12.
Bernal, J. et al. CVC-ClinicDB, a database of colonoscopy videos for learning and inferring intelligence in endoscopy. J. Med. Imaging 4, 044110. https://doi.org/10.1117/1.jmi.4.4.044110 (2017).
Gupta, A. et al. SegPC-2021: Segmentation of Multiple Myeloma Plasma Cells in Microscopic Images. https://segpc-2021.grand-challenge.org/ (2021). Accessed: 2023-10-15.
Ding, X., Zhang, X., Ma, N., Han, J., Ding, G. & Sun, J. RepVGG: Making VGG-style ConvNets great again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13733–13742 (2021).
Li, X., Wang, Y., Zhang, Q., Chen, H. & Liu, J. RepMobileNet: Efficient neural network with reparameterizable mobile blocks. IEEE Access 10, 85998–86009 (2022).
Ding, X., Zhang, X., Han, J. & Ding, G. Diverse branch block: Building a convolution as an inception-like unit. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10886–10895 (2021).
Acknowledgements
This work was supported in part by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (RS-2025-00559998), and in part by the Regional Innovation System & Education (RISE) program through the Daegu RISE Center, funded by the Ministry of Education (MOE) and the Daegu Metropolitan City, Republic of Korea (2025-RISE-03-001). We also would like to thank the Kyungpook National University High- Performance Computing Center for providing computational resources.
Author information
Authors and Affiliations
Contributions
R.J. conceptualized the approach, implemented the model architecture, conducted all experiments, analyzed the results, and drafted the manuscript. J.-M.K. supervised the research, provided critical direction on methodology, and contributed to the interpretation of results. I.-M.K. provided theoretical insights on reparameterization techniques and reviewed the mathematical formulation. S.Y. contributed to the experimental design, assisted with performance evaluation strategies, and provided expertise on medical image analysis applications. All authors reviewed the manuscript and approved the final version.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Juraev, R., Kim, IM., Yun, S. et al. Efficient medical image segmentation using RepSegNet lightweight reparameterized neural network. Sci Rep (2026). https://doi.org/10.1038/s41598-025-34973-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-025-34973-6
