A novel approach for medical image segmentation combining u-net architectures and active contour models

Authors

  • Siva Satya Sreedhar P Associate Professor, Department of Information Technology, Seshadri Rao Gudlavalleru Engineering College, Gudlavalleru, Krishna district, Andhra Pradesh.
  • Rohith Bala Jaswanth B Assistant Professor, Department of Internet of Things,Seshadri Rao Gudlavalleru Engineering College, Gudlavalleru, Krishna District, Andhraprdesh,
  • Ch Rambabu Associate Professor, Department of Electronics and Communication Engineering, Seshadri Rao Gudlavalleru Engineering College, Gudlavalleru, Krishna District, Andhraprdesh
  • K. Srilakshmi Associate Professor ,Department of Electronics and Communication Engineering,Seshadri Rao Gudlavalleru Engineering College ,Gudlavalleru, Krishna District, Andhraprdesh
  • Helina Rajini Suresh Associate Professor,Department of Electronics and Communication Engineering,Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology,Chennai.
  • V. Saravanan Professor,Department of Electronics and Communication Engineering Saveetha School of Engineering,Saveetha Institute of Medical and Technical Sciences,Saveetha University,Chennai.

DOI:

https://doi.org/10.22399/ijcesen.1683

Abstract

Medical image segmentation stands as a fundamental health care operation which supports both medical diagnosis and therapeutic development plans. The segmentation of medical images meets difficulties when working on complex anatomical structures in addition to inconsistent image qualities.  The proposed system connects U-Net architectures with Active Contour Models to develop more precise segmentation capability. The U-Net identifies key features but ACMs specialize in boundary definition for detailed segmentation outcomes. The diagnosis system received its training and testing on publicly accessible medical image data.   The proposed method reached 95.7% segmentation accuracy which proved superior to both standalone U-Net at 92.3% and ACM at 88.5% accuracy. The Dice coefficient reached 0.94 which indicated that boundary identification performed at a high level.  Medical image segmentation benefits from the combination of U-Net with ACMs because it provides an effective approach to handle detection boundaries and extract features from medical images. The method demonstrates substantial potential to become applied in healthcare settings.

References

1. Chen, Y.; Yang, X.H.; Wei, Z.; Heidari, A.A.; Zheng, N.; Li, Z.; Chen, H.; Hu, H.; Zhou, Q.; Guan, Q. Generative Adversarial Networks in Medical Image augmentation: A review. Comput. Biol. Med. 2022, 144,10538.

2. Zhang, J.; Liu, Y.; Wang, X.; Li, Z. A Survey on Deep Learning for Medical Image Segmentation. IEEE Trans. Med. Imaging 2023, 42, 1234–1245.

3. Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; pp. 234–241.

4. Wang, L.; Chen, Y.; Li, X.; He, C. Boundary-Aware U-Net for Medical Image Segmentation. Med. Image Anal. 2023, 78, 102345.

5. Kass, M.; Witkin, A.; Terzopoulos, D. Snakes: Active Contour Models. Int. J. Comput. Vis. 1988, 1, 321–331.

6. Li, H.; Zhang, X.; Zhang, Y.; Li, J. Hybrid Deep Learning and Active Contour Model for Medical Image Segmentation. J. Med. Syst. 2023, 47, 56.

7. P. Sahu, S. Mishra, T. H. Ayane, T. G. Krishna, Ellappan and H. Kalla, "Detection and Classification of Brain tumor tissues from Noisy MR Images using hybrid ACO-SA based LLRBFNN model and modified FLIFCM algorithm," 2019 Second International Conference on Advanced Computational and Communication Paradigms (ICACCP), Gangtok, India, 2019, pp. 1-6,

8. Zhang, J.; Liu, Y.; Wang, X.; Li, Z. A Survey on Deep Learning for Medical Image Segmentation. IEEE Trans. Med. Imaging 2023, 42, 1234–1245.

9. Li, H.; Zhang, X.; Zhang, Y.; Li, J. Hybrid Deep Learning and Active Contour Model for Medical Image Segmentation. J. Med. Syst. 2023, 47, 56.

10. Wang, L.; Chen, Y.; Li, X.; He, C. Boundary-Aware U-Net for Medical Image Segmentation. Med. Image Anal. 2023, 78, 102345.

11. Kumar, S.; Singh, R.; Gupta, A. Level-Set Based Segmentation Using Deep Learning for Medical Images. Comput. Methods Programs Biomed. 2023, 231, 107456.

12. Liu, X.; Wang, Y.; Zhang, Z. Attention-Guided U-Net for Retinal Vessel Segmentation. IEEE J. Biomed. Health Inform. 2023, 27, 1234–1245.

13. Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; pp. 234–241.

14. Kass, M.; Witkin, A.; Terzopoulos, D. Snakes: Active Contour Models. Int. J. Comput. Vis. 1988, 1, 321–331.

15. P. Sahu, S. Mishra, T. H. Ayane, T. G. Krishna, E. Venugopal and H. Kalla, "Detection and Classification of Brain tumor tissues from Noisy MR Images using hybrid ACO-SA based LLRBFNN model and modified FLIFCM algorithm," 2019 Second International Conference on Advanced Computational and Communication Paradigms (ICACCP), Gangtok, India, 2019, pp. 1-6.

16. Wang, L.; Chen, Y.; Li, X.; He, C. Boundary-Aware U-Net for Medical Image Segmentation. Med. Image Anal. 2023, 78, 102345.

17. Li, H.; Zhang, X.; Zhang, Y.; Li, J. Hybrid Deep Learning and Active Contour Model for Medical Image Segmentation. J. Med. Syst. 2023, 47, 56. Liu, X.; Wang, Y.; Zhang, Z. Attention-Guided U-Net for Retinal Vessel Segmentation. IEEE J. Biomed. Health Inform. 2023, 27, 1234–1245.

18. Thiyaneswaran, B., Anguraj, K.,Kumarganesh, S.,Thangaraj, K.Early detection of melanoma images using gray level co-occurrence matrix features and machine learning techniques for effective clinical diagnosis.,International Journal of Imaging Systems and Technology., 2021, 31(2), pp. 682–694

Downloads

Published

2025-05-09

How to Cite

P, S. S. S., B, R. B. J., Ch Rambabu, K. Srilakshmi, Helina Rajini Suresh, & V. Saravanan. (2025). A novel approach for medical image segmentation combining u-net architectures and active contour models. International Journal of Computational and Experimental Science and Engineering, 11(2). https://doi.org/10.22399/ijcesen.1683

Issue

Vol. 11 No. 2 (2025): IJCESEN

Section

Research Article

License

Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Most read articles by the same author(s)