Deep Learning-Based Melanoma Classification Using Hybrid DCNN-LSTM and DCNN-BiLSTM Architectures
DOI:
https://doi.org/10.22399/ijcesen.5251Keywords:
Skin Cancer, Melanoma, Early Detection, DCNN, LSTM, BiLSTMAbstract
Recent advancements in dermatology have improved the diagnosis and treatment of skin cancer. Early detection is particularly important, especially for melanoma, which is highly aggressive and can metastasize rapidly. However, diagnosing melanoma early is challenging due to its resemblance to atypical moles. While dermatologists assess lesions visually, microscopic examination is required for uncertain cases. The ABCD criteria are commonly used but may miss some melanomas. Dermoscopy offers greater accuracy and is preferred for reliable detection. AI and deep learning are revolutionizing dermatology, particularly in malignant melanoma diagnosis. This paper presents an AI system designed for accurate melanoma detection by incorporating a Deep Conventional Neural Network with transfer learning, data augmentation, and hybrid DCNN-LSTM and CNN-BiLSTM models. These techniques improve the performance of melanoma classification models. Experimental results demonstrate that the proposed methods surpass CNN approaches in accuracy, reaching 97.43%, specificity 99.6%, and, most importantly, sensitivity. This last metric, which represents the number of correctly identified malignant images, reaches 97.4% with the MobileNetV2-BiLSTM model.
References
[1] A. Alani, M. Sadlier, A. Uddin, C. Hackett, B. Ramsay, and K. Ahmad, “An analysis of inpatient dermatologic consultations at University Hospital Limerick: Inadequate infrastructure leads to acute skin failure,” Irish Journal of Medical Science, vol. 186, no. 2, pp. 305–307, 2014. https://doi.org/10.1007/s11845-016-1424-8
[2] L. C. Parish, “Dermatologic therapy for the 21st Century,” Clinics in Dermatology, vol. 18, no. 2, pp. 147, 2000. https://doi.org/10.1016/S0738-081X(00)00117-6
[3] E. M. Miró and N. P. Sánchez, “Cutaneous manifestations of infectious diseases,” in Atlas of Dermatology in Internal Medicine, New York: Springer, 2011, pp. 77–119. https://doi.org/10.1007/978-1-4614-0688-4_7
[4] National Institute of Arthritis and Musculoskeletal and Skin Diseases, “Skin Diseases,” National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIAMS), [Online]. Available: https://www.niams.nih.gov/health-topics/skin-diseases. [Accessed: Feb. 01, 2025].
[5] D. S. Rigel, R. J. Friedman, L. M. Dzubow, D. S. Reintgen, J.-C. Bystryn, and R. Marks, Cancer of the Skin, 2nd ed. Philadelphia, USA: Elsevier Saunders, 2005.
[6] C. Karimkhani, L. N. Boyers, R. P. Dellavalle, and M. A. Weinstock, “It’s time for ‘keratinocyte carcinoma’ to replace the term ‘nonmelanoma skin cancer’,” Journal of the American Academy of Dermatology, vol. 72, no. 1, pp. 186–187, 2015. https://doi.org/10.1016/j.jaad.2014.09.036
[7] M. Ernst and A. Giubellino, “The current state of treatment and future directions in cutaneous malignant melanoma,” Biomedicines, vol. 10, no. 4, pp. 822, 2022. https://doi.org/ 10.3390/biomedicines10040822
[8] C. M. Balch, A. C. Buzaid, S. J. Soong, et al., “Final version of the American Joint Committee on Cancer Staging System for cutaneous melanoma,” Journal of Clinical Oncology: Official Journal of the American Society of Clinical Oncology, vol. 19, no. 16, pp. 3635–3648, 2001. https://doi.org/10.1200/JCO.2001.19.16.3635
[9] C. Papageorgiou, D. Ioannides, Z. Apalla, E. Vakirlis, E. Lazaridou, E. Sotiriou, and A. Lallas, “Dermoscopy of difficult-to-diagnose melanomas,” Serbian Journal of Dermatology and Venereology, vol. 8, no. 3, pp. 121–127, 2016. https://doi.org/10.1515/sjdv-2016-0011
[10] C. Longo, R. Pampena, E. Moscarella, et al., “Dermoscopy of melanoma according to different body sites: Head and neck, trunk, limbs, nail, mucosal and acral,” Journal of the European Academy of Dermatology and Venereology, vol. 37, no. 9, pp. 1718–1730, 2023. https://doi.org/10.1111/jdv.19221
[11] P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Scientific Data, vol. 5, no. 1, pp. 1–9, 2018. https://doi.org/10.1038/sdata.2018.161
[12] C. Hernández-Pérez, M. Combalia, S. Podlipnik, et al., “BCN20000: Dermoscopic lesions in the wild,” Scientific Data, vol. 11, no. 1, pp. 641, 2024. https://doi.org/10.1038/s41597-024-03387-w
[13] N. Codella, V. Rotemberg, P. Tschandl, et al., “Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the International Skin Imaging Collaboration (ISIC),” arXiv preprint, 2019. https://arxiv.org/abs/1902.03368
[14] V. Rotemberg, N. Kurtansky, B. Betz-Stablein, et al., “A patient-centric dataset of images and metadata for identifying melanomas using clinical context,” Scientific Data, vol. 8, no. 1, pp. 34, 2021. https://doi.org/10.1038/s41597-021-00815-z
[15] H. Mahmoud, O. A. Omer, S. Ragab, H. Esmaiel, and M. Abdel-Nasser, “Classifying melanoma in ISIC dermoscopic images using efficient convolutional neural networks and deep transfer learning,” Traitement du Signal, vol. 41, no. 2, pp. 679–691, 2024. https://doi.org/10.18280/ts.410211
[16] A. Fuchs and E. Marmur, “The kinetics of skin cancer: Progression of actinic keratosis to squamous cell carcinoma,” Dermatologic Surgery, vol. 33, no. 9, pp. 1099–1101, 2007. https://doi.org /10.1111/j.1524-4725.2007.33224.x
[17] R. Pilarczyk and W. Skarbek, “On intra-class variance for deep learning of classifiers,” Foundations of Computing and Decision Sciences, vol. 44, no. 3, pp. 285–301, 2019. https://doi.org/10.2478/fcds-2019-0015
[18] S. I. Abir, S. Shoha, M. M. Hossain, et al., “Deep learning-based classification of skin lesions: Enhancing melanoma detection through automated preprocessing and data augmentation,” Journal of Computer Science and Technology Studies, vol. 6, no. 5, pp. 152–167, 2024. https://doi.org/10.32996/jcsts.2024.6.5.13
[19] S. Q. Gilani, T. Syed, M. Umair, and O. Marques, “Skin cancer classification using deep spiking neural network,” Journal of Digital Imaging, vol. 36, no. 3, pp. 1137–1147, 2023. https://doi.org/10.1007/s10278-023-00776-2
[20] Y. Ingle and N. F. Shaikh, “Deep learning for skin cancer classification: A comparative study of CNN and VGG16 on HAM10000 dataset,” Communications on Applied Nonlinear Analysis, vol. 31, no. 4s, pp. 490–499, 2024. http://dx.doi.org/10.2139/ssrn.4787463
[21] T. Imran, A. S. Alghamdi, and M. S. Alkatheiri, “Enhanced skin cancer classification using deep learning and nature-based feature optimization,” Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12702–12710, 2024. https://doi.org/10.48084/etasr.6604
[22] R. Kaur, H. GholamHosseini, R. Sinha, and M. Lindén, “Melanoma classification using a novel deep convolutional neural network with dermoscopic images,” Sensors, vol. 22, no. 3, pp. 1134, 2022. https://doi.org/10.3390/s22031134
[23] A. Atta, M. A. Khan, M. Asif, G. F. Issa, R. A. Said, and T. Faiz, “Classification of skin cancer empowered with a convolutional neural network,” in Proc. International Conference on Cyber Resilience (ICCR), Dubai, United Arab Emirates, 2022. https://doi.org/ 10.1109/ICCR56254.2022.9995928
[24] M. M’hamedi, M. Merzoug, M. Hadjila, and A. Bekkouche, “Enhancing melanoma skin cancer classification through data augmentation,” TELKOMNIKA (Telecommunication Computing Electronics and Control), vol. 22, no. 5, pp. 1209, 2024. http://doi.org /10.12928/telkomnika.v22i5.26106
[25] TensorFlow Core, “Load and preprocess images,” [Online]. Available: https://www.tensorflow.org /tutorials/load_data/images. [Accessed: Feb. 05, 2025].
[26] TensorFlow Core, “Data augmentation,” [Online]. Available: https://www.tensorflow.org /tutorials/images/data_augmentation. [Accessed: Feb. 05, 2025].
[27] C. Sun, A. Shrivastava, S. Singh, and A. Gupta, “Revisiting unreasonable effectiveness of data in deep learning era,” in Proc. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017. https://doi.org/10.1109/iccv.2017.97
[28] R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The unreasonable effectiveness of deep features as a perceptual metric,” in Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018. https://doi.org/10.1109/CVPR.2018.00068
[29] M. Aziz, U. Rehman, M. U. Danish, and K. Grolinger, “Global-Local Image Perceptual Score (GLIPS): Evaluating photorealistic quality of AI-generated images,” IEEE Transactions on Human-Machine Systems, vol. 55, no. 2, pp. 223–233, 2025. https://doi.org /10.36227/techrxiv.173933251. 15884096/v1
[30] M. A. Farooq, A. Abaid, I. Ullah, and P. Corcoran, “A comparative study on diffusion sampling methods across diverse medical imaging modalities,” In Proc. Asian Conference on Computer Vision (ACCV), 2024, Hanoi, Vietnam. https://doi.org/10.1007/978-981-96-2641-0_13
[31] U. Muhammad, W. Wang, S. P. Chattha, and S. Ali, “Pre-trained VGGNet architecture for remote-sensing image scene classification,” In Proc. 24th International Conference on Pattern Recognition (ICPR), IEEE, 2018, Beijing, China. https://doi.org/10.1109/ICPR.2018.8545591
[32] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, Salt Lake City, USA. https://doi.org/ 10.1109/CVPR.2018.00474
[32] M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Information Processing & Management, vol. 45, no. 4, pp. 427–437, 2009. https://doi.org /10.1016/j.ipm.2009.03.002
[33] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, USA: MIT Press, 2016.
[34] K. P. Murphy, Machine Learning: A Probabilistic Perspective. London, United Kingdom: The MIT Press, 2012.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
