Advancing Skin Cancer Prediction: A Deep Dive into Hybrid PCA-Autoencoder
Keywords:
Skin cancer detection, Feature extraction, Principal Component Analysis (PCA), Autoencoders, Ensemble machine learning models, Dermatological imagesAbstract
Skin cancer, one of the most prevalent forms of cancer globally, necessitates early and accurate detection to improve patient outcomes. In this context, the integration of computational techniques with dermatological expertise offers promising avenues for diagnosis. This study introduces a comprehensive algorithm designed to detect skin cancer by harnessing the power of both automatic and manual feature extraction methodologies. At the heart of our approach lies the combination of Principal Component Analysis (PCA) and Autoencoders. These techniques are employed to effectively reduce the dimensionality of the features, ensuring that only the most pertinent information is retained. By analyzing dermatological images, meticulously extract colour intensity features, including the primary RGB (red, green, blue) channels. Beyond these primary channels, the proposed algorithm is fine-tuned to discern specific shades crucial for skin cancer diagnosis, such as pink, brown, red, and black intensities. Once these features are extracted and processed, they form the input for an ensemble of state-of-the-art machine learning models. Ensemble includes a diverse set of models: XGBoost, Logistic Regression, Long Short-Term Memory (LSTM), CatBoost, Multi-Layer Perceptron (MLP), Bayesian Model Averaging (BMA), and Bayesian Model Combination (BMC). Each model offers unique strengths, and their combined power aims to provide a holistic and robust diagnostic tool. Through extensive validation and testing, this research not only ascertains the efficacy of each model but also evaluates the collective strength of the ensemble. The goal is to present a tool that seamlessly integrates into clinical workflows, aiding dermatologists in the early detection and subsequent treatment of skin cancer, thereby significantly enhancing patient care.
Downloads
References
Fernandes, S. L., Chakraborty, B., Gurupur, V. P., & Prabhu G, A. (2016). Early skin cancer detection using computer aided diagnosis techniques. Journal of Integrated Design and Process Science, 20(1), 33-43.
Majumder, S., & Ullah, M. A. (2019). Feature extraction from dermoscopy images for melanoma diagnosis. SN Applied Sciences, 1(7), 753.
Kausar, N., Hameed, A., Sattar, M., Ashraf, R., Imran, A. S., & Ali, A. (2021). Multiclass skin cancer classification using ensemble of fine-tuned deep learning models. Applied Sciences, 11(22), 10593.
Thanh, D. N., Prasath, V. S., Hieu, L. M., & Hien, N. N. (2020). Melanoma skin cancer detection method based on adaptive principal curvature, colour normalisation and feature extraction with the ABCD rule. Journal of Digital Imaging, 33, 574-585.
Ceballos-Arroyo, A. M., Robles-Serrano, S., & Sanchez-Torres, G. (2020). A morphological convolutional Autoencoder for segmenting pigmented skin lesions. Engineering Letters, 28(3), 855-866.
Thurnhofer-Hemsi, K., & Domínguez, E. (2021). A convolutional neural network framework for accurate skin cancer detection. Neural Processing Letters, 53(5), 3073-3093.
Heibel, H. D., Hooey, L., & Cockerell, C. J. (2020). A review of noninvasive techniques for skin cancer detection in dermatology. American journal of clinical dermatology, 21, 513-524.
Pacheco, A. G., & Krohling, R. A. (2020). The impact of patient clinical information on automated skin cancer detection. Computers in biology and medicine, 116, 103545.
Zghal, N. S., & Derbel, N. (2020). Melanoma skin cancer detection based on image processing. Current Medical Imaging, 16(1), 50-58.
Dubal, P., Bhatt, S., Joglekar, C., & Patil, S. (2017, November). Skin cancer detection and classification. In 2017 6th international conference on electrical engineering and informatics (ICEEI) (pp. 1-6). IEEE.
Ameri, A. (2020). A deep learning approach to skin cancer detection in dermoscopy images. Journal of biomedical physics & engineering, 10(6), 801.
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, 1-24.
Alfed, N., & Khelifi, F. (2017). Bagged textural and color features for melanoma skin cancer detection in dermoscopic and standard images. Expert Systems with Applications, 90, 101-110.
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.
Brinker, Titus Josef, Achim Hekler, Jochen Sven Utikal, Niels Grabe, Dirk Schadendorf, Joachim Klode, Carola Berking, Theresa Steeb, Alexander H. Enk, and Christof Von Kalle. "Skin cancer classification using convolutional neural networks: systematic review." Journal of medical Internet research 20, no. 10 (2018): e11936.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
