A Blockchain-Integrated Pipeline Featuring Generative AI for Melanoma Detection, Segmentation, and Classification in Dermoscopic Images
DOI:
https://doi.org/10.5753/jbcs.2026.5903Keywords:
Dermoscopic Image of Melanoma, Artificial Intelligence, Large Language Models, Generative AI, BlockchainAbstract
Melanoma is one of the most aggressive forms of skin cancer, responsible for thousands of deaths annually worldwide. The effectiveness of early diagnosis and continuous monitoring of disease progression are critical factors for therapeutic success and the improvement of public health outcomes. This study presents an advanced blockchain-integrated pipeline for the automated analysis of dermoscopic images, combining modern Computer Vision and Artificial Intelligence (AI) techniques to enhance the processes of lesion detection, segmentation, and classification. Using state-of-the-art architectures such as YOLO for identifying suspicious regions and the Segment Anything Model (SAM) for precise extraction of affected areas, the proposed method achieved an accuracy of 99% in the initial analysis stages, outperforming previously reported results in the literature. For the classification stage, a pipeline of feature extraction and selection is employed, enabling the identification of regions with a high probability of malignancy, achieving 86% accuracy. The study also incorporates Large Language Models (LLMs) to automatically generate interpretive reports, providing preliminary clinical decision support through generative AI. In the final stage, all generated data and results—including processed images, model outputs, and generated reports—are recorded on a blockchain network. This distributed storage ensures the integrity, traceability, and immutability of the information, enabling the creation of a secure and auditable clinical history. The blockchain-based solution adds transparency to the proposed method and enables controlled data sharing among medical institutions, reinforcing trust and accountability in the use of automated tools for dermatological diagnosis support.
Downloads
References
AbdelSalam, F. (2023). A systematic review of blockchain technology benefits and threats. PMC. Available at: [link].
Abedini, M. (2024). Skin cancer classification by leveraging segment anything model for semantic segmentation of skin lesion. DOI: 10.17148/IJARCCE.2024.13835.
AI, M. (2023). Llama 2 - 13b. [link]. Accessed: 2025-10-04.
Aishwarya, N., Kannaa, G. Y., and Seemakurthy, K. (2025). Yoloskin: A fusion framework for improved skin cancer diagnosis using yolo detectors on nvidia jetson nano. Biomedical Signal Processing and Control, 100:107093. DOI: 10.1016/j.bspc.2024.107093.
Aishwarya, N., Prabhakaran, K. M., Debebe, F. T., Reddy, M. S. S. A., and Pranavee, P. (2023). Skin cancer diagnosis with yolo deep neural network. Procedia Computer Science, 220:651-658. DOI: 10.1016/j.procs.2023.03.083.
Al-Masni, M. A., Al-Antari, M. A., Choi, M.-T., Han, S.-M., and Kim, T.-S. (2018). Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks. Computer methods and programs in biomedicine, 162:221-231. DOI: 10.1016/j.cmpb.2018.05.027.
Al-Masni, M. A., Kim, D.-H., and Kim, T.-S. (2020). Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification. Computer methods and programs in biomedicine, 190:105351. DOI: 10.1016/j.cmpb.2020.105351.
Alickovic, A. (2023). React Application Architecture for Production: Learn best practices and expert tips to deliver enterprise-ready React web apps. Packt Publishing. Available at: [link].
Alquran, H., Qasmieh, I. A., Alqudah, A. M., Alhammouri, S., Alawneh, E., Abughazaleh, A., and Hasayen, F. (2017). The melanoma skin cancer detection and classification using support vector machine. In 2017 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), pages 1-5. DOI: 10.1109/AEECT.2017.8257738.
Arnold, M., Singh, D., Laversanne, M., Vignat, J., Vaccarella, S., Meheus, F., Cust, A. E., De Vries, E., Whiteman, D. C., and Bray, F. (2022). Global burden of cutaneous melanoma in 2020 and projections to 2040. JAMA dermatology, 158(5):495-503. DOI: 10.1001/jamadermatol.2022.0160.
Badrinarayanan, V., Kendall, A., and 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. DOI: 10.1109/TPAMI.2016.2644615.
Baghersalimi, S., Bozorgtabar, B., Schmid-Saugeon, P., Ekenel, H. K., and Thiran, J.-P. (2019). Dermonet: densely linked convolutional neural network for efficient skin lesion segmentation. EURASIP Journal on Image and Video Processing, 2019(1):1-10. DOI: 10.1186/s13640-019-0467-y.
Berseth, M. (2017). Isic 2017-skin lesion analysis towards melanoma detection. arXiv preprint arXiv:1703.00523. DOI: 10.48550/arXiv.1703.00523.
Bhosale, K., Akbarabbas, K., Deepak, J., and Sankhe, A. (2019). Blockchain based secure data storage. International Research Journal of Engineering and Technology (IRJET), 6(3):5058-5061. Available at: [link].
Bi, L., Kim, J., Ahn, E., Kumar, A., Feng, D., and Fulham, M. (2019). Step-wise integration of deep class-specific learning for dermoscopic image segmentation. Pattern recognition, 85:78-89. DOI: 10.1016/j.patcog.2018.08.001.
Blaut, G., Ma, X., and Wolter, K. (2023). Explorando a aleatoriedade em blockchains. In Conferência Internacional IEEE 2023 sobre Blockchain e Criptomoeda (ICBC). DOI: 10.1109/ICBC56567.2023.10174962.
Budhiman, A., Suyanto, S., and Arifianto, A. (2019). Melanoma cancer classification using resnet with data augmentation. In 2019 international seminar on research of information technology and intelligent systems (ISRITI), pages 17-20. IEEE. DOI: 10.1109/ISRITI48646.2019.9034624.
de Souza Rebouças, E., de Medeiros, F. N. S., Marques, R. C. P., Chagas, J. V. S., Guimaraes, M. T., Santos, L. O., Medeiros, A. G., and Peixoto, S. A. (2021). Level set approach based on parzen window and floor of log for edge computing object segmentation in digital images. Applied Soft Computing, 105:107273. DOI: 10.1016/j.asoc.2021.107273.
Deng, R., Cui, C., Liu, Q., Yao, T., Remedios, L. W., Bao, S., Landman, B. A., Wheless, L. E., Coburn, L. A., Wilson, K. T., et al. (2023). Segment anything model (sam) for digital pathology: Assess zero-shot segmentation on whole slide imaging. arXiv preprint arXiv:2304.04155. DOI: 10.2352/EI.2025.37.14.COIMG-132.
Dhanvardini, R., Martina, P., Vijay, R., Amirtharajan, R., and Pravinkumar, P. (2023). Development and integration of dapp with blockchain smart contract truffle framework for user interactive applications. In 2023 International Conference on Computer Communication and Informatics (ICCCI), pages 1-6. DOI: 10.1109/ICCCI56745.2023.10128406.
Duarte, A. F., Sousa-Pinto, B., Azevedo, L. F., Barros, A. M., Puig, S., Malvehy, J., Haneke, E., and Correia, O. (2021). Clinical abcde rule for early melanoma detection. European Journal of Dermatology, 31(6):771-778. DOI: 10.1684/ejd.2021.4171.
Ferrer, L. (2022). Analysis and comparison of classification metrics. arXiv preprint arXiv:2209.05355. DOI: 10.48550/arXiv.2209.05355.
Frange, V. M. N., Arruda, L. H. F., and Daldon, P. É. C. (2009). Dermatoscopia: importância para a prática clínica. Revista de Ciências Médicas, 18(4). Available at: [link].
Gül, S., Cetinel, G., Aydin, B. M., Akgün, D., and Öztaş Kara, R. (2025). Yolosamic: A hybrid approach to skin cancer segmentation with the segment anything model and yolov8. Diagnostics, 15(4):479. DOI: 10.3390/diagnostics15040479.
Hussain, M. (2023). Yolo-v1 to yolo-v8, the rise of yolo and its complementary nature toward digital manufacturing and industrial defect detection. Machines, 11(7):677. DOI: 10.3390/machines11070677.
Islayem, R., Gebreab, S. A., AlKhader, W., Musamih, A., Salah, K., Jayaraman, R., and Khan, M. K. (2025). Using large language models for enhanced fraud analysis and detection in blockchain based health insurance claims. Scientific Reports, 15(1):29763. DOI: 10.1038/s41598-025-15676-4.
Jiang, P., Ergu, D., Liu, F., Cai, Y., and Ma, B. (2022). A review of yolo algorithm developments. Procedia computer science, 199:1066-1073. DOI: 10.1016/j.procs.2022.01.135.
Kotter, E., Marti-Bonmati, L., Brady, A. P., and Desouza, N. M. (2021). Esr white paper: blockchain and medical imaging. Insights into Imaging, 12(1):82. DOI: 10.1186/s13244-021-01029-y.
Kumar, R. and Tripathi, R. (2019). Implementation of distributed file storage and access framework using ipfs and blockchain. In 2019 Fifth International Conference on Image Information Processing (ICIIP), pages 246-251. DOI: 10.1109/ICIIP47207.2019.8985677.
Lee, W.-M. (2023). Using the metamask crypto-wallet. In Beginning Ethereum Smart Contracts Programming: With Examples in Python, Solidity, and JavaScript, pages 111-144. Apress, Berkeley, CA. DOI: 10.1007/978-1-4842-9271-6_5.
Lyakhova, U. and Lyakhov, P. (2024). Systematic review of approaches to detection and classification of skin cancer using artificial intelligence: Development and prospects. Computers in Biology and Medicine, 178:108742. DOI: 10.1016/j.compbiomed.2024.108742.
Marchisotti, G. (2025). Tecnologia blockchain para compartilhamento de dados: projeto b-cpf da receita federal do brasil. Revista Brasileira de Casos de Ensino em Administração, 15:c6. DOI: 10.12660/gvcasosv15n1c6.
Marques, A. G., de Figueiredo, M. V. C., da Costa Nascimento, J. J., de Souza, C. T., de Mattos Dourado, C. M. J., de Albuquerque, V. H. C., de Freitas Souzal, L. F., et al. (2024). New approach generative ai melanoma data fusion for classification in dermoscopic images with large language model. In 2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 1-6. IEEE. DOI: 10.1109/SIBGRAPI62404.2024.10716298.
Mendonça, T., Celebi, M., Mendonca, T., and Marques, J. (2015). Ph2: A public database for the analysis of dermoscopic images. Dermoscopy image analysis, 2. DOI: 10.1201/b19107.
Mhaske, H. R. e Phalke, D. A. (2013). Detecção e classificação do câncer de pele melanoma com base no aprendizado supervisionado e não supervisionado. In Conferência Internacional de Circuitos, Controles e Comunicações de 2013 (CCUBE), pages 1-5. DOI: 10.1109/CCUBE.2013.6718539.
Müller, D., Soto-Rey, I., and Kramer, F. (2022). Towards a guideline for evaluation metrics in medical image segmentation. BMC Research Notes, 15(1):210. DOI: 10.1186/s13104-022-06096-y.
Nagaoka, T. (2025). Improved skin lesion segmentation in dermoscopic images using object detection and semantic segmentation. Clinical, Cosmetic and Investigational Dermatology, pages 1191-1198. DOI: 10.2147/CCID.S518751.
Nayeem, M. J., Rana, S., Alam, F., and Rahman, M. A. (2021). Prediction of hepatitis disease using k-nearest neighbors, naive bayes, support vector machine, multi-layer perceptron and random forest. In 2021 international conference on information and communication technology for sustainable development (ICICT4SD), pages 280-284. IEEE. DOI: 10.1109/ICICT4SD50815.2021.9397013.
Patil, Shankar M. e Rajguru, B. S. e. M. R. S. e. P. O. P. (2022). Detecção de doença de câncer de pele melanoma usando rede neural convolucional. In 2022 3ª Conferência Internacional de Tecnologia Emergente (INCET), pages 1-5. DOI: 10.1109/INCET54531.2022.9825381.
Patiño, D., Avendaño, J., and Branch, J. W. (2018). Automatic skin lesion segmentation on dermoscopic images by the means of superpixel merging. In International conference on medical image computing and computer-assisted intervention, pages 728-736. Springer. DOI: 10.1007/978-3-030-00937-3_83.
Pennisi, A., Bloisi, D. D., Nardi, D., Giampetruzzi, A. R., Mondino, C., and Facchiano, A. (2016). Skin lesion image segmentation using delaunay triangulation for melanoma detection. Computerized Medical Imaging and Graphics, 52:89-103. DOI: 10.1016/j.compmedimag.2016.05.002.
Phoon, K.-K., Quek, S.-T., and An, P. (2003). Identification of statistically homogeneous soil layers using modified bartlett statistics. Journal of Geotechnical and Geoenvironmental Engineering, 129(7):649-659. DOI: 10.1061/(ASCE)1090-0241(2003)129:7(649).
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. DOI: 10.1109/CVPR.2016.91.
Rezk, E., Haggag, M., Eltorki, M., and El-Dakhakhni, W. (2023). A comprehensive review of artificial intelligence methods and applications in skin cancer diagnosis and treatment: Emerging trends and challenges. Healthcare Analytics, page 100259. DOI: 10.1016/j.health.2023.100259.
Ring, C., Cox, N., and Lee, J. B. (2021). Dermatoscopy. Clinics in Dermatology, 39(4):635-642. DOI: 10.1016/j.clindermatol.2021.03.009.
Sachdeva, S. (2009). Fitzpatrick skin typing: Applications in dermatology. Indian Journal of Dermatology, Venereology and Leprology, 75(1):93-96. DOI: 10.4103/0378-6323.45238.
Singh, G. and Sachan, M. (2014). Multi-layer perceptron (mlp) neural network technique for offline handwritten gurmukhi character recognition. In 2014 IEEE International Conference on Computational Intelligence and Computing Research, pages 1-5. DOI: 10.1109/ICCIC.2014.7238334.
Thapar, P., Rakhra, M., Alsaadi, M., Quraishi, A., Deka, A., and Ramesh, J. V. N. (2024). A hybrid grasshopper optimization algorithm for skin lesion segmentation and melanoma classification using deep learning. Healthcare Analytics, 5:100326. DOI: 10.1016/j.health.2024.100326.
Topsakal, O. and Akinci, T. C. (2023). Creating large language model applications utilizing langchain: A primer on developing llm apps fast. In International Conference on Applied Engineering and Natural Sciences, volume 1, pages 1050-1056. DOI: 10.59287/icaens.1127.
Vasconcelos, F. F. X., Medeiros, A. G., Peixoto, S. A., and Reboucas Filho, P. P. (2019). Automatic skin lesions segmentation based on a new morphological approach via geodesic active contour. Cognitive Systems Research, 55:44-59. DOI: 10.1016/j.cogsys.2018.12.008.
Wainstein, A. J. and Belfort, F. A. (2004). Conduta para o melanoma cutâneo. Revista do Colégio Brasileiro de Cirurgiões, 31:204-214. DOI: 10.1590/S0100-69912004000300011.
Wang, H., Zhao, S., Qiang, Z., Xi, N., Qin, B., and Liu, T. (2024a). Beyond direct diagnosis: Llm-based multi-specialist agent consultation for automatic diagnosis. arXiv preprint arXiv:2401.16107. DOI: 10.48550/arXiv.2401.16107.
Wang, J., Yang, Z., Yao, Z., and Yu, H. (2024b). Jmlr: Joint medical llm and retrieval training for enhancing reasoning and professional question answering capability. arXiv preprint arXiv:2402.17887. DOI: 10.48550/arXiv.2402.17887.
Xiao, H., Li, L., Liu, Q., Zhu, X., and Zhang, Q. (2023). Transformers in medical image segmentation: A review. Biomedical Signal Processing and Control, 84:104791. DOI: 10.1016/j.bspc.2023.104791.
Xu, Y., Dos Santos, M. A., F. Souza, L. F., Marques, A. G., Zhang, L., da Costa Nascimento, J. J., de Albuquerque, V. H. C., and Rebouças Filho, P. P. (2022). New fully automatic approach for tissue identification in histopathological examinations using transfer learning. IET Image Processing, 16(11):2875-2889. DOI: 10.1049/ipr2.12449.
Yilmaz, A., Kalebasi, M., Samoylenko, Y., Guvenilir, M. E., and Uvet, H. (2021). Benchmarking of lightweight deep learning architectures for skin cancer classification using isic 2017 dataset. arXiv preprint arXiv:2110.12270. DOI: 10.48550/arXiv.2110.12270.
Zheng, Z., Xie, S., Dai, H., Chen, X., and Wang, H. (2017). An overview of blockchain technology: Architecture, consensus, and future trends. In 2017 IEEE International Congress on Big Data (BigData Congress), pages 557-564. DOI: 10.1109/BigDataCongress.2017.85.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Marcus Vinicius Candido de Figueiredo, Adriell Gomes Marques, Francisco Italo Guilherme Da Silva, José Jerovane Da Costa Nascimento, Cidcley Teixeira de Souza, Luís Fabrício de Freitas Souza
This work is licensed under a Creative Commons Attribution 4.0 International License.
