An Automatic Segmentation on The Dermoscopy Images for Organ‎izing Uneven Borders Using Iterative Contours

  • Authors

    • A. Prabhu Chakkaravarthy Assistant Department of Networking and Communications, School of Computing, College of Engineering and Technology, SRM Institute of Science ‎& Technology, India and Director, Research Institute of IoT and Cybersecurity, Department of Electronic Engineering, National Kaohsiung University of Science ‎and Technology, Taiwan
    • Prof. Chin-Shiuh Shieh Director, Research Institute of IoT and Cybersecurity, Department of Electronic Engineering, National Kaohsiung University of Science ‎and Technology, Taiwan
    • Prof. Mong-Fong Horng Research Institute of IoT and Cybersecurity, Department of Electronic Engineering, National Kaohsiung University of Science and Technology
    • J Dhanalakshmi Research Institute of IoT and Cybersecurity, Department of Electronic Engineering, National Kaohsiung University of Science and Technology and Department of Data Science and Business Systems, School of Computing, College of Engineering and Technology, SRM Institute of Sci‎ence & Technology, India
    https://doi.org/10.14419/8zw85s25

    Received date: June 26, 2025

    Accepted date: July 30, 2025

    Published date: August 11, 2025

  • Active Contours; Region Growing; Thresholding; Gaussian Filter; Euclidean Distance; Image Gradient‎

  • Abstract

    Among all malignancies, skin disease is the most overwhelming and destructive disease. This ailment begins first from the epidermis of the human ‎body. To acquire a precise assessment of skin malignant growth, the electronic examination of the image produces a profound impact. All ‎around the globe, skin disease affects numerous individuals in various parts of the body. To make an ideal conclusion of skin disease, ‎the dermatologist ought to look at the color and border of the skin picture using a computational technique. This could be a pre-screening ‎framework for the dermatologist for an early conclusion. The proposed work reports on the division of sore from the dermoscopy pictures with the essential steps, for example, pre-processing, segmentation, and post-processing. The Region Growing and dynamic shape ‎identification makes an ideal bend as a limit to the portion influenced district. The proposed work starts with separating, followed by division and ‎closures with include extraction, and this is clarified impeccably. The proposed reproduction gauges the exact finding between the Ground Truth ‎image and the Segmented Image and affirms the best-offered estimations of exactness up to 93.43% for the DermQuest dataset and 92.74% for ‎the DermIS Dataset.

  • References

    1. Xu, S., Wang, Y., Zhao, Z., Peng, J., Cao, X., & Meng, D. (2023). Neural Gradient Regularizer. arXiv (Cornell University).
    2. Rodrigues, C. M., Boutry, N., & Najman, L. (2024). Transforming gradient-based techniques into interpretable methods. arXiv (Cornell University). https://doi.org/10.1016/j.patrec.2024.06.006.
    3. Abrahamyan, L., Truong, A. M., Philips, W., & Deligiannis, N. (2022). Gradient variance loss for Structure-Enhanced Image Super-Resolution. arXiv (Cornell University). https://doi.org/10.1109/ICASSP43922.2022.9747387.
    4. Y. Kim, B. -N. Kang and D. Kim, "Detector with focus: Normalizing gradient in image pyramid," 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, 2017, pp. 420-424, https://doi.org/10.1109/ICIP.2017.8296315.
    5. Deepak Gupta, Gowreesh Mago, Arnav Chavan, Dilip Prasad, Rajat Mani Thomas, "Pushing the Limits of Gradient Descent for Efficient Learning on Large Images," OpenReview.net, 2023.
    6. Liu, G., Liu, Q., Liang, J., & Sun, Q. (2023). Active contours driven by local and global intensity fitting energy with application to SAR image segmentation and its fast solvers. arXiv (Cornell University).
    7. Habis, A., Meas-Yedid, V., Angelini, E., & Olivo-Marin, J. (2024). Deep ContourFlow: Advancing Active Contours with Deep Learning. arXiv (Cornell University).
    8. Akbari, P., Ziaei, A., & Azarnoush, H. (2021). Deep active contours using locally controlled distance vector flow. arXiv (Cornell University).
    9. Bahl, G., Daniel, L., & Lafarge, F. (2022). SCR: Smooth Contour Regression with Geometric Priors. arXiv (Cornell University).
    10. Wang, D., Dang, X., Liu, W., & Wang, Y. (2023). Image segmentation using active contours with image structure adaptive gradient vector flow external force. Frontiers in Applied Mathematics and Statistics, 9. https://doi.org/10.3389/fams.2023.1271296.
    11. Turk, O., Acar, E., Irmak, E., Yilmaz, M., & Bakis, E. (2024). A Hybrid 2D Gaussian Filter and Deep Learning Approach with Visualization of Class Activation for Automatic Lung and Colon Cancer Diagnosis. Technology in Cancer Research & Treatment, 23. https://doi.org/10.1177/15330338241301297.
    12. Keilmann, A., Godehardt, M., Moghiseh, A., Redenbach, C., & Schladitz, K. (2024). Improved anisotropic gaussian filters. Image Analysis & Stereology, 43(1), 9–22. https://doi.org/10.5566/ias.3023.
    13. Zucchelli, E. M., & Jones, B. A. (2023). A Gaussian Integral Filter with Multivariate Laplace Process Noise. arXiv (Cornell University). https://doi.org/10.23919/FUSION52260.2023.10224147.
    14. Anand, S., & Sangeethapriya, G. (2020). Gaussian modulated hyperbolic tangent high pass filter for edge detection in noisy images. arXiv (Cornell University).
    15. Tang, W., Gong, Y., Liu, K., Liu, J., Pan, W., Liu, B., & Qiu, G. (2020). Gaussian Curvature filter on 3D meshes. arXiv (Cornell University).
    16. A. Soudani and E. Zagrouba, "Adaptive Region Based Active Contour Model for Image Segmentation," 2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA), Hammamet, Tunisia, 2017, pp. 717-724, https://doi.org/10.1109/AICCSA.2017.140.
    17. E. Iqbal, A. Niaz, A. A. Memon, U. Asim and K. N. Choi, "Saliency-Driven Active Contour Model for Image Segmentation," in IEEE Access, vol. 8, pp. 208978-208991, 2020, https://doi.org/10.1109/ACCESS.2020.3038945.
    18. S. Biswas, R. Hazra and S. Prasad, "A Region-based Level Set Formulation Using Machine Learning Approach in Medical Image Segmentation," TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), Kochi, India, 2019, pp. 470-475, https://doi.org/10.1109/TENCON.2019.8929350.
    19. X. Yang, X. Jiang, L. Zhou, Y. Wang and Y. Zhang, "Active Contours Driven by Local and Global Region-Based Information for Image Segmentation," in IEEE Access, vol. 8, pp. 6460-6470, 2020, https://doi.org/10.1109/ACCESS.2019.2963435.
    20. Chen, D., Mirebeau, JM., Shu, H. et al. A Region-Based Randers Geodesic Approach for Image Segmentation. Int J Comput Vis 132, 349–391 (2024). https://doi.org/10.1007/s11263-023-01881-z.
    21. A. Priya, R. K. Agrawal and B. Rana, "Fusion-based Multilevel Thresholding For Image Segmentation Using Evolutionary Algorithm," 2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), Prayagraj, India, 2022, pp. 1-7, https://doi.org/10.1109/UPCON56432.2022.9986438.
    22. S. Gao, X. Wang and C. Jin, "Analysis of Multi-Threshold Image Segmentation Method Based on Improved Sparrow Search Algorithm," 2022 4th International Conference on Applied Machine Learning (ICAML), Changsha, China, 2022, pp. 96-100, https://doi.org/10.1109/ICAML57167.2022.00025.
    23. Salaou, M. S. C., Conze, P., Kalti, K., Solaiman, B., & Mahjoub, M. A. (2017). Adaptive strategy for superpixel-based region-growing image segmentation. Journal of Electronic Imaging, 26(06), 1. https://doi.org/10.1117/1.JEI.26.6.061605.
    24. Shimodaira, H. (2017). Automatic color image segmentation using a square elemental Region-Based seeded region growing and merging method. arXiv (Cornell University).
    25. Dias, P. A., & Medeiros, H. (2020). Probabilistic semantic segmentation refinement by Monte Carlo region growing. arXiv (Cornell University). https://doi.org/10.1007/978-3-030-20890-5_9.
    26. Lagergren, J., Rutter, E., & Flores, K. (2020). Region Growing with Convolutional Neural Networks for Biomedical Image Segmentation. arXiv (Cornell University).
    27. Melekhov, I., Kannala, J., & Rahtu, E. (2017). Image Patch Matching Using Convolutional Descriptors with Euclidean Distance. arXiv (Cornell University). https://doi.org/10.1007/978-3-319-54526-4_46.
    28. Strutz, T. (2021). The Distance Transform and its Computation. arXiv (Cornell University).
    29. Fuseiller, G., Marie, R., Mourioux, G., Duno, E., & Labbani-Igbida, O. (2022). Enhancing distance transform computation by leveraging the discrete nature of images. Journal of Real-Time Image Processing, 19(4), 763–773. https://doi.org/10.1007/s11554-022-01221-3.
    30. Jourlin, M. (2024). Image Enhancement Thanks to Negative Grey Levels in the Logarithmic Image Processing Framework. Sensors, 24(15), 4969. https://doi.org/10.3390/s24154969.
    31. Jang, J., Lee, I., Kim, M., & Joo, K. (2024). AISDF: Structure-Aware Neural signed distance fields in indoor scenes. IEEE Robotics and Automation Letters, 9(5), 4106–4113. https://doi.org/10.1109/LRA.2024.3375117.
    32. Y. Chen, Y. Huang, L. Wang, H. Huang, J. Song, C. Yu, and Y. Xu, "Salt and Pepper Noise Removal Method Based on Stationary Framelet Transform with Non-Convex Sparsity Regularization," arXiv preprint arXiv:2110.09113, Oct. 2021. https://doi.org/10.1049/ipr2.12451.
    33. V. Singh, P. Agrawal, T. Sharma, and N. K. Verma, "Improved Adaptive Type-2 Fuzzy Filter with Exclusively Two Fuzzy Membership Function for Filtering Salt and Pepper Noise," arXiv preprint arXiv:2008.04114, Aug. 2020.
    34. A. A. Rafiee and M. Farhang, "A Deep Convolutional Neural Network for Salt-and-Pepper Noise Removal Using Selective Convolutional Blocks," arXiv preprint arXiv:2302.05435, Feb. 2023. https://doi.org/10.2139/ssrn.4373907.
    35. H. Dong, J. Yu, and C. Xiao, "Dual Reweighted Lp-Norm Minimization for Salt-and-Pepper Noise Removal," arXiv preprint arXiv:1811.09173, Nov. 2018.
    36. F. P. Loss et al., "Skin Cancer Diagnosis Using NIR Spectroscopy Data of Skin Lesions In Vivo Using Machine Learning Algorithms," arXiv preprint arXiv:2401.01200, Jan. 2024.
    37. D. N. T. Le et al., "Transfer Learning with Class-Weighted and Focal Loss Function for Automatic Skin Cancer Classification," arXiv preprint arXiv:2009.05977, Sep. 2020.
    38. S. Innani et al., "Deep Learning Based Novel Cascaded Approach for Skin Lesion Analysis," arXiv preprint arXiv:2301.06226, Jan. 2023. https://doi.org/10.1007/978-3-031-31407-0_46.
    39. A. A. Rafiee and M. Farhang, "An Automated and Interpretable Computer-Aided Approach for Skin Cancer Diagnosis Using Genetic Programming," IEEE Access, vol. 11, pp. 10679181, 2023.
    40. Le, D. N. T., et al. (2020). Transfer Learning with Class-Weighted and Focal Loss Function for Automatic Skin Cancer Classification. arXiv preprint arXiv:2009.05977.
    41. Innani, S., et al. (2023). Deep Learning Based Novel Cascaded Approach for Skin Lesion Analysis. arXiv preprint arXiv:2301.06226. https://doi.org/10.1007/978-3-031-31407-0_46.
    42. Loss, F. P., et al. (2024). Skin Cancer Diagnosis Using NIR Spectroscopy Data of Skin Lesions In Vivo Using Machine Learning Algorithms. arXiv preprint arXiv:2401.01200.

  • Downloads

  • How to Cite

    Chakkaravarthy , A. P. ., Shieh, P. C.-S. ., Horng, P. M.-F. ., & Dhanalakshmi, J. . (2025). An Automatic Segmentation on The Dermoscopy Images for Organ‎izing Uneven Borders Using Iterative Contours. International Journal of Basic and Applied Sciences, 14(4), 297-312. https://doi.org/10.14419/8zw85s25