Cilt Kanseri Teşhisi için Hibrit Derin Öğrenme ve Makine Öğrenmesi Yaklaşımı

Year 2024, , 339 - 347, 31.10.2024

Yahya Doğan , Cüneyt Özdemir

https://doi.org/10.17671/gazibtd.1484037

Abstract

Cilt kanseri, cilt hücrelerinin kontrolsüz çoğalması sonucu ortaya çıkan ve genellikle lezyonlar veya yeni büyümeler olarak kendini gösteren bir hastalıktır. Erken teşhis, tedavi sonuçlarını iyileştirmek için kritik bir rol oynamaktadır. Bu çalışmada, modern derin öğrenme modelleri ile geleneksel makine öğrenimi algoritmalarını birleştirerek cilt kanseri teşhisinde yenilikçi bir yöntem sunulmaktadır. Üç aşamalı bir metodoloji geliştirilmiştir. İlk aşamada, cilt lezyonlarının görüntülerinden anlamlı özellikler çıkarılmış ve bu amaçla Xception, VGG16, ResNet152V2, InceptionV3, InceptionResNetV2, MobileNetV2, EfficientNetB2 ve DenseNet201 gibi çeşitli transfer öğrenme modelleri değerlendirilmiştir. İkinci aşamada, Temel Bileşen Analizi (PCA) ile özellik boyutlarının azaltılması sağlanmış ve üçüncü aşamada ise bu indirgenmiş özellikler, K-En Yakın Komşular (KNN) ve Rastgele Orman (RF) algoritmaları ile sınıflandırılmıştır. Yapılan deneyler sonucunda en yüksek doğruluk %91.28 ile DenseNet201 modelinden elde edilen özelliklerin PCA ile boyutlarının azaltılarak RF algoritması ile sınıflandırılmasıyla elde edilmiştir. Bu bulgular, transfer öğrenme modelleri ile yapılan özellik çıkarma işlemlerinin, PCA ile boyut azaltmanın ve makine öğrenmesi algoritmalarının cilt kanseri teşhisinde yüksek performans sağladığını göstermektedir.

Keywords

cilt kanseri teşhisi, öznitelik seçimi, boyut azaltma, transfer öğrenme, makine öğrenmesi

Enhancing Skin Cancer Diagnosis through the Integration of Deep Learning and Machine Learning Approaches

Abstract

Skin cancer is a disease characterized by the uncontrolled proliferation of skin cells, typically manifesting as lesions or abnormal growths. Early diagnosis is critical for improving treatment outcomes. This study proposes an innovative approach to skin cancer diagnosis by integrating modern deep learning models with traditional machine learning algorithms. A three-phase methodology was developed. In the first phase, meaningful features were extracted from skin lesion images using various transfer learning models, including Xception, VGG16, ResNet152V2, InceptionV3, InceptionResNetV2, MobileNetV2, EfficientNetB2, and DenseNet201. In the second phase, dimensionality reduction was performed using Principal Component Analysis (PCA). In the final phase, the reduced feature sets were classified using K-Nearest Neighbors (KNN) and Random Forest (RF) algorithms. Experimental results demonstrated that the highest accuracy of 91.28% was achieved through the combination of DenseNet201 for feature extraction, PCA for dimensionality reduction, and Random Forest for classification. These findings highlight the effectiveness of integrating transfer learning models, dimensionality reduction techniques, and machine learning algorithms in enhancing the accuracy of skin cancer diagnosis.

Keywords

skin cancer diagnosis, feature selection, dimensionality reduction, transfer learning, machine learning

References

• Alam, T. M., Khan, M. M. A., Iqbal, M. A., Abdul, W., & Mushtaq, M. (2019). Cervical cancer prediction through different screening methods using data mining. IJACSA) International Journal of Advanced Computer Science and Applications, 10(2).
• Rognoni, E., & Watt, F. M. (2018). Skin cell heterogeneity in development, wound healing, and cancer. Trends in cell biology, 28(9), 709-722.
• Fitzmaurice C, Akinyemiju TF, Al Lami FH, Alam T, Alizadeh-Navaei R, Allen C, et al. (2018) Global, regional, and national cancer incidence, mortality, years of life lost, years lived with disability, and disability-adjusted life-years for 29 cancer groups, 1990 to 2016: a systematic analysis for the global burden of disease study. JAMA Oncol.;4(11):1553–68
• Dinehart, S. M. (2000). The treatment of actinic keratoses. Journal of the American Academy of Dermatology, 42(1), S25-S28
• Flohr, C., and Hay, R. 2021. Putting the burden of skin diseases on the global map. *British Journal of Dermatology*, 184(2): 189-190.
• Skin Cancer Facts & Statistics [Internet]. 2021. Available from: https://www.skincancer.org/skin-cancer information/skin-cancer-facts/
• Ergün, E., & Kılıç, K. (2021). Derin öğrenme ile artırılmış görüntü seti üzerinden cilt kanseri tespiti. Black Sea Journal of Engineering and Science, 4(4), 192-200.
• Andrew, T. W., Alrawi, M., & Lovat, P. (2021). Reduction in skin cancer diagnoses in the UK during the COVID‐19 pandemic. Clinical and Experimental Dermatology, 46(1),145-146.
• Lukaviciute, L., Ganceviciene, R., Navickas, P., Navickas, A., Grigaitiene, J., and Zouboulis, C. C. 2020. Anxiety, depression, and suicidal ideation amongst patients with facial dermatoses (acne, rosacea, perioral dermatitis, and folliculitis) in Lithuania. *Dermatology*, 236(4): 314-322.
• Arnold, J. D., Yoon, S., and Kirkorian, A. Y. 2019. The national burden of inpatient dermatology in adults. *Journal of the American Academy of Dermatology*, 80(2): 425-432.
• Feng, H., Berk-Krauss, J., Feng, P. W., and Stein, J. A. 2018. Comparison of dermatologist density between urban and rural counties in the United States. *JAMA Dermatology*, 154(11): 1265-1271.
• Assiri, A., et al. 2013. Hospital outbreak of Middle East respiratory syndrome coronavirus. *The New England Journal of Medicine*, 369(5): 407-416.
• W. Yue, Z. Wang, H. Chen, A. Payne, & X. Liu, "Machine learning with applications in breast cancer diagnosis and prognosis", *Designs*, vol. 2, no. 2, p. 13, 2018.
• Z. Han, B. Wei, Y. Zheng, Y. Yin, K. Li, & S. Li, "Breast cancer multi-classification from histopathological images with structured deep learning model", *Scientific Reports*, vol. 7, no. 1, 2017.
• C. AKYEL and N. Arici, "A new approach to hair noise cleansing and lesion segmentation in images of skin cancer", Politeknik Dergisi, vol. 23, no. 3, p. 821-828, 2020. DOI: 10.2339/politeknik.645395
• A. Karli, "Cilt kanseri görüntüleri kullanılarak eğitilen efficientnet-b3 mimarisinde hiperparametre seçiminin sınıflandırma performansına etkisinin i̇ncelenmesi", Fırat Üniversitesi Mühendislik Bilimleri Dergisi, vol. 36, no. 1, p. 499-507, 2024. DOI: 10.35234/fumbd.1426044
• N. Kausar, A. Hameed, M. Sattar, R. Ashraf, A. Imran, M. Abidinet al., "Multiclass skin cancer classification using ensemble of fine-tuned deep learning models", Applied Sciences, vol. 11, no. 22, p. 10593, 2021. DOI: 10.3390/app112210593
• A. Mahbod, G. Schaefer, C. Wang, G. Dorffner, R. Ecker, & I. Ellinger, "Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification", Computer Methods and Programs in Biomedicine, vol. 193, p. 105475, 2020. DOI: 10.1016/j.cmpb.2020.105475
• Sivakumar, M. S., Leo, L. M., Gurumekala, T., Sindhu, V., & Priyadharshini, A. S. (2024). Deep learning in skin lesion analysis for malignant melanoma cancer identification. Multimedia Tools and Applications, 83(6), 17833-17853.
• Gajera, H. K., Nayak, D. R., & Zaveri, M. A. (2023). A comprehensive analysis of dermoscopy images for melanoma detection via deep CNN features. Biomedical Signal Processing and Control, 79, 104186.
• Manimurugan, S. (2023). Hybrid high performance intelligent computing approach of CACNN and RNN for skin cancer image grading. Soft Computing, 27(1), 579-589.
• Pham, T.C., Luong, C.M., Visani, M. and Hoang, V.D., 2018, March. Deep CNN and data augmentation for skin lesion classification. In Asian Conference on Intelligent Information and Database Systems (pp. 573-582). Springer, Cham.
• Remya, S., Anjali, T., & Sugumaran, V. (2024). A Novel Transfer Learning Framework for Multimodal Skin Lesion Analysis. IEEE Access.
• Fahad, N. M., Sakib, S., Raiaan, M. A. K., & Mukta, M. S. H. (2023, February). Skinnet-8: An efficient cnn architecture for classifying skin cancer on an imbalanced dataset. In 2023 International conference on electrical, computer and communication engineering (ECCE) (pp. 1-6). IEEE.