Adaptive Swarm-Driven Skin Lesion Segmentation and Classification Using Boundary-Aware U-Net and Hybrid Vision Transformer
Abstract
Skin cancer is one of the most prevalent dermatological diseases worldwide, and timely and accurate diagnosis is essential for effective treatment and improved patient outcomes. However, automated skin lesion analysis remains challenging due to irregular lesion boundaries, low contrast between lesions and surrounding skin, imaging artifacts, variations in lesion appearance, and significant intra-class variability. To address these challenges, this research proposes an Adaptive Swarm-Driven Skin Lesion Segmentation and Classification Approach that integrates an Adaptive Boundary-Aware U-Net (ABAU-Net), a Butterfly Optimization Algorithm–Elephant Herding Optimization (BOA-EHO) strategy, and a Hybrid Vision Transformer with Dynamic Feature Fusion (HViT-DFF). The proposed ABAU-Net is designed to enhance segmentation accuracy by emphasizing boundary information and preserving fine-grained lesion structures, particularly in cases involving poorly defined or irregular borders. The BOA-EHO optimization strategy combines global exploration and local exploitation mechanisms to improve network parameter optimization, accelerate convergence, and reduce the possibility of premature convergence. Following segmentation, the HViT-DFF model integrates CNN-based local spatial features with transformer-based global contextual representations through dynamic feature fusion, enabling robust discrimination among multiple skin lesion classes. Extensive experiments conducted on the ISIC skin lesion dataset demonstrate the effectiveness of the proposed framework, achieving a Dice coefficient of 98.2%, Jaccard index of 97.5%, classification accuracy of 98.8%, and AUC of 0.992. These results outperform recent CNN-, Transformer-, and hybrid-based approaches. Overall, the proposed framework demonstrates strong potential for accurate, reliable, and automated skin lesion segmentation and multi-class classification, supporting computer-aided dermatological diagnosis and potentially facilitating earlier clinical intervention.
Downloads
References
Hamza, A., & Damaševičius, R. “Deep learning for brain tumor segmentation and classification: a systematic review of methods and trends”, Computers, materials and continua., vol.86(1), pp.1-41, 2025, DOI:10.32604/cmc.2025.069721.
Debelee, T. G. “Skin lesion classification and detection using machine learning techniques: a systematic review”, Diagnostics, vol.13(19), pp.3147, 2023, DOI:10.3390/diagnostics13193147.
Al-Masni, M. A., Kim, D. H., & Kim, T. S. “Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification”, Computer methods and programs in biomedicine, vol.190, Art. No.105351,2020, DOI:10.1016/j.cmpb.2020.105351.
Mahbod, A., Tschandl, P., Langs, G., Ecker, R., & Ellinger, I. “The effects of skin lesion segmentation on the performance of dermatoscopic image classification”, Computer Methods and Programs in Biomedicine, vol.197, Art.No.105725, 2020, DOI:10.1016/j.cmpb.2020.105725.
Khalaf, A. D., Hamdan, H., Halin, A. B. A., & Manshor, N. “Segmentation and classification of skin cancer diseases based on deep learning: Challenges and future directions”, IEEE Access, vol.31,2025,DOI:10.1109/ACCESS.2025.3569170
R. Kasmi, K. Mokrani, “Classification of malignant melanoma and benign skin lesions: Implementation of automatic abcd rule”, IET Image Proc. Vol.10 (6) 2016, pp.448–455, DOI:10.1049/iet-ipr.2015.0385
Balasamy, K., Seethalakshmi, V. & Suganyadevi, S. “Medical Image Analysis Through Deep Learning Techniques: A Comprehensive Survey”, Wireless Pers Commun vol.137, pp.1685–1714, 2024, DOI:10.1007/s11277-024-11428-1
Mehdar, K. M., Soomro, T. A., Ali, A., Bin Ubaid, F., Irfan, M., Halawani, H. T., ... & Abdelkafi Magzoub, M. “Deep neural network-based robust framework for automated skin lesion segmentation and analysis”, Digital Health, vol.12, 2026, Art.No.20552076261427501, DOI:10.1177/20552076261427501
Gabani, V., Navamani, T. M., Shyamala, K., & Vaswani Rajpal, V. K. “Multimodal skin lesion classification for early cancer diagnosis using deep learning”, Frontiers in Physiology, vol.17, Art. No.1717517, DOI:10.3389/fphys.2026.1717517
Fiaz, M., Shoaib Khan, M. B., Khan, A. H., Bilal, A., Abdullah, M., Darem, A. A., & Sarwar, R. “An explainable hybrid deep learning framework for precise skin lesion segmentation and multi-class classification”, Frontiers in Medicine, vol.12, Art. No.1681542, DOI:10.3389/fmed.2025.1681542
Attique Khan M, Sharif M, Akram T, Kadry S, Hsu CH, “A two-stream deep neural network-based intelligent system for complex skin cancer types classification”, Int J Intell Syst vol.37(12), pp.10621-10649, 2022, https://doi.org/10.1002/int.22691
Amin, J., Azhar, M., Arshad, H., Zafar, A., & Kim, S. H., “Skin-lesion segmentation using boundary-aware segmentation network and classification based on a mixture of convolutional and transformer neural networks”, Frontiers in Medicine, vol.12, Art. No.1524146, DOI:10.3389/fmed.2025.1524146
Binzagr, F., & Hariri, M. “Foundation-Model-Driven Skin Lesion Segmentation and Classification Using SAM-Adapters and Vision Transformers”, Diagnostics, vol.16(3), DOI:10.3390/diagnostics16030468
Lilhore, U. K., Anitha, D., Priya, R., Rahane, W. P., Bangare, S. L., Kavitha, R., ... & Simaiya, S. “Adaptive Hybrid AI Framework for Robust and Explainable Skin Lesion Segmentation and Melanoma Detection”, International Journal of Computational Intelligence Systems, vol. 19(1), 2026, DOI:10.1007/s44196-026-01233-y
Huang, D.X., Zhou, X.H., Xie, X.L., Liu, S.Q., Wang, S., Feng, Z.Q., Gui, M.J., Li, H., Xiang, T.Y., Yao, B.X., et al., “Spironet: Spatialfrequency learning and graph-based channel interaction network for vessel segmentation”, Biomedical Signal Processing and Control, vol. 126, Art. No.110814, 2026, DOI: 10.1016/j.bspc.2026.110814
Naeem, M. A., Yang, S., Saleem, M. A., Javeed, A., & Ahmad, T., “A hybrid approach for accurate skin lesion segmentation using LEDNet and Swin-UMamba”, Scientific Reports, vol.16(1), pp.5415, 2026, DOI:10.1038/s41598-026-38056-y
Verma, N., Ranvijay, R., & Yadav, D. K., “Robust Segmentation of Skin Lesions via Confidence‐Guided ConvLSTM Integrated With Advanced Curriculum Strategies”, International Journal of Imaging Systems and Technology, vol.36(2), pp.e70307,2026, DOI:/10.1002/ima.70307
Khan, M. A., Sharif, M. I., Raza, M., Anjum, A., Saba, T., & Shad, S. A., “Skin lesion segmentation and classification: A unified framework of deep neural network features fusion and selection”, Expert Systems, vol.39(7), pp. e12497, DOI:10.1111/exsy.12497
Qamar, S., Alkhatarishi, M., Alam, F., & Fazil, M., “Confidence-weighted semi-supervised learning for skin lesion segmentation using hybrid CNN-Transformer networks”, IEEE Access, vol.14, pp.24579 -24594, 2026, DOI:10.1109/ACCESS.2026.3663774
Ali, G., Awang, M. K., Rashid, J., Hamza, M., Khashan, O. A., & Ghani, A., “WIDENet: A Novel Lightweight CNN for Robust Skin Lesion Segmentation”, IEEE Access, vol.14, pp.57763 – 57781, 2026, DOI:10.1109/ACCESS.2026.3683571
Azhari, A. A., Yudistira, N., Widodo, A. W., & Yagi, Y., “Two-stage CNN with weakly supervised segmentation for skin lesion classification”, Multimedia Tools and Applications, vol.84(41), pp.49769-49800, 2025, DOI:/10.1007/s11042-025-21091-8
Lakshmi, R., & Arthi, B., “Superior skin cancer segmentation and classification via vision transformer-based ResNet with long short-term memory”, Communications in Statistics-Simulation and Computation, pp.1-30, 2026, DOI:10.1080/03610918.2026.2647955
Naeem, S., Haneef, F., & Noor, M. N., “A hybrid deep learning based robust framework for enhancing the prediction of skin lesions”, Network Modeling Analysis in Health Informatics and Bioinformatics, vol.15(1), 2026, DOI:10.1007/s13721-025-00714-y
N. Moradi, N. Mahdavi-Amiri, “Kernel sparse representation-based model for skin lesions segmentation and classification”, Comput. Methods Programs Biomed, vol. 182, Art. No.105038, DOI:10.1016/j.cmpb.2019.105038
R.F. Mansour, S.A. Althubiti, F. Alenezi, “Computer vision with machine learning enabled skin lesion classification model”, Computers, Materials & Continua, vol. 73(1), pp.849-864, 2022, DOI:10.32604/cmc.2022.029265
V. Srividhya, K. Sujatha, R.S. Ponmagal, G. Durgadevi, L. Madheshwaran, “Visionbased detection and categorization of skin lesions using deep learning neural networks”, Procedia Comput. Sci., vol.171, pp.1726–1735, 2020, DOI:10.1016/j.procs.2020.04.185
M. Rastgoo, R. Garcia, O. Morel, F. Marzani, “Automatic differentiation of melanoma from dysplastic nevi”, Comput. Med. Imaging Graph., vol.43, pp.44–52, 2015, DOI:10.1016/j.compmedimag.2015.02.011
H. Zhao, G. Wang, Y. Wu, H. Wang, Y. Li, “Vcmix-net: a hybrid network for medical image segmentation”, Biomed. Signal Process. Control, vol. 86, Art. No.105241, 2023, DOI:10.1016/j.bspc.2023.105241
S. Jain, N. Pise, “Computer-aided melanoma skin cancer detection using image processing”, Procedia Comput. Sci., vol. 48, pp. 735–740, 2015, DOI:10.1016/j.procs.2015.04.209
R. Kasmi, K. Mokrani, “Classification of malignant melanoma and benign skin lesions: Implementation of automatic abcd rule”, IET Image Proc., vol. 10 (6), pp.448–455, 2015, DOI:10.1049/iet-ipr.2015.0385
G. Yang, S. Luo, P. Greer, “Advancements in skin cancer classification: a review of machine learning techniques in clinical image analysis”, Multimed. Tools Appl., vol. 84, pp. 9837–9864, 2025, DOI:10.1007/s11042-024-19298-2
M. Zafar, M.I. Sharif, M.I. Sharif, S. Kadry, S.A.C. Bukhari, H.T. Rauf, “Skin lesion analysis and cancer detection based on machine/deep learning techniques: a comprehensive survey”, Life, vol. 13 (1), 2023, DOI:10.3390/life13010146
Ioannis Giotis, Niki Molders, Steffen Land, Michael Biehl, Marcel F Jonkman, and Nicolai Petkov., “Med-node: A computer-assisted melanoma diagnosis system using non-dermoscopic images”, Expert Systems with Applications, vol.42(19), pp.6578–6585, 2015, DOI:10.1016/j.eswa.2015.04.034
S. S. Mohammed and J. M. Al-Tuwaijari., “Skin disease classification system based on machine learning technique: A survey”, In IOP Conference Series: Materials Science and Engineering, vol. 1076, pp.012045. 2021, DOI:10.1088/1757-899X/1076/1/012045
M. Dildar, S. Akram, M. Irfan, H.U. Khan, M. Ramzan, A.R. Mahmood, M. H. Mahnashi, “Skin cancer detection: a review using deep learning techniques”, Int. J. Environ. Res. Public Health, vol. 18 (10), pp. 5479, 2021, DOI:10.3390/ijerph18105479
T. Goswami, V. K. Dabhi, and H. B. Prajapati, “Skin disease classification from image-a survey”, In 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS), pp. 599–605. IEEE, 2020, DOI:10.1109/ICACCS48705.2020.9074232
E. Vocaturo, E. Zumpano, and P. Veltri. “Image pre-processing in computer vision systems for melanoma detection”, In 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 2117–2124. IEEE, 2018, DOI:10.1109/BIBM.2018.8621507
S. Pathan, K.G. Prabhu, P.C. Siddalingaswamy, “Techniques and algorithms for computer aided diagnosis of pigmented skin lesions—a review”, Biomed. Signal Process. Control, vol.39, pp.237–262, 2018, DOI: 10.1016/j.bspc.2017.07.010
Z. Huang, H. Deng, S. Yin, T. Zhang, W. Tang, Q. Wang, “Adf-net: a novel adaptive dual-stream encoding and focal attention decoding network for skin lesion segmentation”, Biomed. Signal Process. Control, vol.91, Art. No.105895, 2024, DOI:10.1016/j.bspc.2023.105895
R.R. Babu, F.M. Philip, “Optimized deep learning for skin lesion segmentation and skin cancer detection”, Biomed. Signal Process. Control, vol. 95, Art. No. 106292, 2024, DOI:10.1016/j.bspc.2024.106292
Copyright (c) 2026 Thilagavathi Rajamanickam, Anuradha Konidena, Mahesh N, Balakrishnan M, N.K. Priyadharsini, Suganthi Rajamanickam
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
