A Hybrid Framework Combining DeepLabv3+ with ResNet-50 Backbone and GOA for Automated Melanoma Lesion Segmentation
DOI:
https://doi.org/10.36602/jsras.2026.3.1.9Keywords:
Melanoma segmentation , DeepLabv3+, Dermoscopy, Computer-aided diagnosis, Grasshopper optimization algorithmAbstract
Segmenting melanoma lesions accurately is harder than it might appear. Even in high-quality dermoscopic images, lesion edges can be gradual rather than sharp, color differences between lesion and healthy skin are sometimes minimal, and no two lesions look quite alike. These are not just technical inconveniences; they directly affect how reliably a computer-aided system can support a clinician's decision. In this work, we explored whether combining deep learning with swarm intelligence could address some of these difficulties. Specifically, we paired three CNN architectures U-Net, SegNet, and DeepLabv3+ with ResNet-50, with the Grasshopper Optimization Algorithm (GOA), using it not as a preprocessing step but as a refinement stage applied after the network produces its initial prediction. The idea was that GOA's color-based clustering could tighten boundaries in regions where the CNN's confidence was low. We tested this hybrid model on the ISBI 2016 and ISIC 2018 dermoscopic datasets. Not all architectures responded equally U-Net struggled noticeably, while SegNet performed reasonably well.
In previous approaches, deep learning and swarm intelligence were treated as separate stages, whereas our proposed framework, the GOA, is integrated directly into the post-prediction step of DeepLabv3+-ResNet-50, which enables boundary refinement that complements rather than replaces CNN predictions. The results from DeepLabv3+ with ResNet-50 were the best, achieving Dice coefficients of 91.7% and 88.2% and Jaccard indices of 84.9% and 79.7% on the ISBI 2016 and ISIC 2018 datasets, respectively, demonstrating the effectiveness of the proposed hybrid approach for lesion segmentation
Downloads
References
Alhudhaif, A., Ocal, H., Barisci, N., Atacak, İ., Nour, M., & Polat, K. (2022). A novel approach to skin lesion segmentation: Multipath fusion model with fusion loss. Computational and Mathematical Methods in Medicine, 2022(1), 2157322.
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481–2495.
Bukhari, M., Yasmin, S., Habib, A., Cheng, X., Ullah, F., Yoo, J., & Lee, D. (2023). A novel framework for melanoma lesion segmentation using multiparallel depthwise separable and dilated convolutions with swish activations. Journal of Healthcare Engineering, 2023(1), 1847115.
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), 801–818.
Codella, N., Rotemberg, V., Tschandl, P., Celebi, M. E., Dusza, S., Gutman, D., Helba, B., Kalloo, A., Liopyris, K., & Marchetti, M. (2019). Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). ArXiv Preprint ArXiv:1902.03368.
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S.
M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118.
Garcia-Arroyo, J. L., & Garcia-Zapirain, B. (2017). Segmentation of skin lesions based on fuzzy classification of pixels and histogram thresholding. ArXiv Preprint ArXiv:1703.03888.
Gutman, D., Codella, N. C. F., Celebi, E., Helba, B., Marchetti, M., Mishra, N., & Halpern, A. (2016). Skin lesion analysis toward melanoma detection: A challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). ArXiv Preprint ArXiv:1605.01397.
Hu, P., Han, Y., & Zhang, Z. (2024). Multi-level thresholding color image segmentation using modified gray wolf optimizer. Biomimetics, 9(11), 700.
Innani, S., Dutande, P., Baid, U., Pokuri, V., Bakas, S., Talbar, S., Baheti, B., & Guntuku, S. C. (2023). Generative adversarial networks based skin lesion segmentation. Scientific Reports, 13(1), 13467.
Jabber, A. A., Shadeed, G. A., Salim, N., & Dibs, H. (2025). Automated skin lesion diagnosis and classification using k-mean, lab-color-space segmentation and deep learning. Operations Research Forum, 6(2), 43.
Jahanifar, M., Tajeddin, N. Z., Asl, B. M., & Gooya, A. (2019). Supervised Saliency Map Driven Segmentation of Lesions in Dermoscopic Images. IEEE Journal of Biomedical and Health Informatics, 23(2), 509–518. https://doi.org/10.1109/JBHI.2018.2839647
Kawahara, J., Daneshvar, S., Argenziano, G., & Hamarneh, G. (2018). Seven-point checklist and skin lesion classification using multitask multimodal neural nets. IEEE Journal of Biomedical and Health Informatics, 23(2), 538–546.
Li, M., Jiang, Y., Cao, G., Xu, T., & Guo, R. (2025). HyperFusionNet combines vision transformer for early melanoma detection and precise lesion segmentation. Scientific Reports.
Mohamed, A. A. A., Hançerlioğullari, A., Rahebi, J., Ray, M. K., & Roy, S. (2023). Colon Disease Diagnosis with Convolutional Neural Network and Grasshopper Optimization Algorithm. In Diagnostics (Vol. 13, Issue 10). https://doi.org/10.3390/diagnostics13101728
Mohamed, A. A. A., Rahebi, M., Hançerlioğulları, A., & Rahebi, J. (2024). An approach based on convolutional neural network and ACO-PSO for colon cancer disease diagnosis. Politeknik Dergisi, 28(2), 649–659.
Müller, D., Soto-Rey, I., & Kramer, F. (2022). Towards a guideline for evaluation metrics in medical image segmentation. BMC Research Notes, 15(1), 210.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, 234–241.
Saifullah, S., & Dreżewski, R. (2024). Advanced medical image segmentation enhancement: A particle-swarm-optimization-based histogram equalization approach. Applied Sciences, 14(2), 923.
Saremi, S., Mirjalili, S., & Lewis, A. (2017). Grasshopper optimisation algorithm: theory and application. Advances in Engineering Software, 105, 30–47.
Sarwar, N., Irshad, A., Naith, Q. H., D. Alsufiani, K., & Almalki, F. A. (2024). Skin lesion segmentation using deep learning algorithm with ant colony optimization. BMC Medical Informatics and Decision Making, 24(1), 265.
Shahin, A. H., Amer, K., & Elattar, M. A. (2019). Deep convolutional encoder-decoders with aggregated multi-resolution skip connections for skin lesion segmentation. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 451–454.
Sriwiboon, N. (2025). A high-performance deep learning framework for skin lesion segmentation based on DeepLabV3+ and multi-scale context modeling. Biomedical Materials & Devices, 1–17. https://doi.org/10.1007/s44174-025-00497-w
Tang, Y., Yang, F., Yuan, S., & Zhan, C. (2019). A multi-stage framework with context information fusion structure for skin lesion segmentation. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 1407–1410.
Thapar, P., Rakhra, M., Alsaadi, M., Quraishi, A., Deka, A., & Ramesh, J. V. N. (2024). A hybrid Grasshopper optimization algorithm for skin lesion segmentation and melanoma classification using deep learning. Healthcare Analytics, 5, 100326.
Tschandl, P., Rosendahl, C., & Kittler, H. (2018). The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific Data, 5(1), 180161.
Wang, R., Chen, S., Ji, C., & Li, Y. (2022). Cascaded context enhancement network for automatic skin lesion segmentation. Expert Systems with Applications, 201, 117069.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Amna Ali A Mohamed (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
