A Deep Learning-Based Method for Skin Cancer Detection
DOI:
https://doi.org/10.58916/jhas.v10i4.954الكلمات المفتاحية:
Discrete Wavelet Transform، Principal Component Analysis، Recurrent Neural Networksالملخص
Skin cancer is a common and potentially fatal disease, necessitating accurate and early detection methods. This study leverages the power of deep learning to address the challenge of classifying skin lesions into benign or malignant categories. An integrated framework is proposed, combining Discrete Wavelet Transform (DWT) for spatial and frequency-based feature extraction, Principal Component Analysis (PCA) for dimensionality reduction, and Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM) layers for classification. The system processes lesion images by decomposing them using DWT to extract salient low-frequency features, followed by PCA to eliminate redundancy and enhance computational efficiency. These refined features are then analyzed through an RNN architecture capable of modeling complex dependencies within the data.
The results demonstrate strong generalization performance, with the model achieving an average accuracy of 96.33% and an F1-score of 0.9803 across folds. The synergy between DWT, PCA, and RNN contributes to a highly efficient and accurate diagnostic system, underscoring its potential for real-world applications in medical image analysis and early detection of skin cancer.
التنزيلات
المراجع
American Cancer Society. (2023). Skin Cancer.
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.
Mitchell, T. M. (1997). Machine Learning. McGraw-Hill Education.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by backpropagating errors. Nature.
Mallat, S. (1999). A Wavelet Tour of Signal Processing: The Sparse Way. Academic Press.
Esteva, A., et al. (2017). Skin Cancer Detection using Deep Learning. IEEE Conference Publication.
El-Khatib, H., Popescu, D., & Ichim, L. (2020). Deep Learning–Based Methods for Automatic Diagnosis of Skin Lesions. Journal of Medical Imaging, vol. 27, no. 4, pp. 123-135.
Kim, C.-I., Hwang, S.-M., Park, E.-B., Won, C.-H., & Lee, J.-H. (2021). Computer-Aided Diagnosis Algorithm for Classification of Malignant Melanoma Using Deep Neural Networks. Sensors, 21(16), 5551. https://doi.org/10.3390/s21165551
Jain, S., Singhania, U., Tripathy, B., Nasr, E. A., Aboudaif, M. K., & Kamrani, A. K. (2021). Deep Learning-Based Transfer Learning for Classification of Skin Cancer. Sensors, 21(23), 8142. https://doi.org/10.3390/s21238142
Hussain, S. I., et al. (2022). Melanoma Identification Through X-ray Modality Using Inception-v3 Based Convolutional Neural Network. IEEE Transactions on Medical Imaging, vol. 41, no. 5, pp. 1234–1242.
Hussain, S. I., et al. (2024). Skin Cancer Detection and Classification Using Neural Network Algorithms. MDPI Sensors, vol. 24, no. 7, pp. 567–579.
Bhatti, Z. I., et al. (2023). Skin Cancer Detection and Classification Using Deep Neural Networks. Springer Lecture Notes in Computer Science, vol. 13692, pp. 89–101.
Ansari, M., et al. (2023). Skin Cancer Detection Using Deep Neural Networks Based on ResNet and Inception Architectures. MDPI Applied Sciences, vol. 13, no. 15, pp. 3561.
Tembhurne, J. V., Hebbar, N., Patil, H. Y., & Diwan, T. (2023). Skin cancer detection using ensemble of machine learning and deep learning techniques. Multimedia Tools and Applications, 82, 27501–27524.
Claret, S. P. A., Dharmian, J. P., & Manokar, A. M. (2024). Artificial intelligence-driven enhanced skin cancer diagnosis: leveraging convolutional neural networks with discrete wavelet transformation. Egyptian Journal of Medical Human Genetics, 25, Article number: 50.
Azizi, S., Biyabani, S. R., Yan, P., Tahmasbi, A., Kwak, J. T., Xu, S., Turkbey, B., Choyke, P. L., Pinto, P. A., Wood, B. J., Mousavi, P., & Abolmaesumi, P. (2018). Deep Recurrent Neural Networks for Prostate Cancer Detection: Analysis of Temporal Enhanced Ultrasound. PubMed Central.
Ganguli, R., Lad, R., Lin, A., & Yu, X. (2023). Novel Generative Recurrent Neural Network Framework to Produce Accurate, Applicable, and Deidentified Synthetic Medical Data for Patients With Metastatic Cancer. JCO Clinical Cancer Informatics. PubMed Central.
Zareen, S. S., Sun, G., Kundi, M., Qadri, S. F., Qadri, S., 2024. Enhancing Skin Cancer Diagnosis with Deep Learning: A Hybrid CNN-RNN Approach. Computers, Materials & Continua 74, pp. 1245-1258.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder. Empirical Methods in Natural Language Processing (EMNLP), 1724-1734.
Olah, C. (2015). Understanding LSTM Networks. Colah's Blog. Retrieved from http://colah.github.io/posts/2015-08-Understanding-LSTMs/
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation. MIT Press.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research. MIT Press.
Ioffe, S., & Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv preprint. arXiv.
Mallat, S. (1989). A Theory for Multiresolution Signal Decomposition: The Wavelet Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence. IEEE.
Almarimi, A. F., & Salem, A. M. (2025). Machine Learning using Simple Linear Regression. Bani Waleed University Journal of Humanities and Applied Sciences, 10(3), 178-184.
Jolliffe, I. T. (2002). Principal Component Analysis. Springer Series in Statistics. Springer.
Shlens, J. (2014). A Tutorial on Principal Component Analysis. arXiv preprint arXiv:1404.1100. Retrieved from https://arxiv.org/abs/1404.1100.
Codella, N., Rotemberg, V., Tschandl, P., et al. (2019). The ISIC Skin Image Analysis Collaboration: 2018–2019 Challenge Datasets and Techniques. arXiv preprint arXiv:1902.03368. Retrieved from https://arxiv.org/abs/1902.03368.
Soglia, S. (2025). Artificial Intelligence-Based Integrated Approach for Skin Cancer Recognition. PhD thesis, University of Brescia.
Hosseinzadeh, M., Hussain, D., Mahmood, F. M. Z., Alenizi, F. A., Noroozi Varzeghani, A., Asghari, P., Darwesh, A., Malik, M. H., & Lee, S. W. (2025). A model for skin cancer using combination of ensemble learning and deep learning. PLOS ONE, 20(4), e0301275. https://doi.org/10.1371/journal.pone.0301275
التنزيلات
منشور
إصدار
القسم
كيفية الاقتباس
