Dermatolojik Görüntü Analizi için Derin Öğrenme Modellerinin Karşılaştırılması: EfficientNet Zirvede

Yıl 2024, Cilt: 40 Sayı: 2, 383 - 392, 31.08.2024

Rukiye Nur Kaçmaz , Refika Sultan Doğan

Öz

Hızlı yayılan ve ölümcül olan cilt kanserine melanom denir. Cilt kanserinin erken
evrelerinde tedavi edilmezse ölüm oranı çok yüksektir ancak erken evrelerinde
doğru bir şekilde tanımlandığında hastaların hayatları kurtarılabilir. Doğru ve hızlı
bir teşhis ile hastanın hayatta kalma şansı artabilir. Bilgisayar destekli bir tanı
destek sisteminin oluşturulmasını gerekir.. Bu çalışmada Dense201, DarkNet19,
EfficientNet melanom sınıflandırması için 3 farklı derin transfer öğrenme modeli
sunmaktadır. Buna ek olarak, transfer öğrenmesinde kullanılan filtre boyutu
açısından ablasyon çalışması yapılmıştır. Filtre boyutunun etkisine bakmak için her
bir modelde farklı sayıda filtre boyutu oluşturulup sonuç alınmıştır. Çalışmada 1792
iyi huylu ve 1464 kötü huylu görüntü içeren ISIC veri seti kullanılmıştır. Bu
çalışmaya göre, DenseNet201, boyutlarına bakılmaksızın farklı filtre boyutlarında
doğru ve güvenilir sonuçlar sağlamıştır. Bu nedenle, cilt lezyonlarının
sınıflandırılmasını içeren çalışmalarda DenseNet201 kullanımının seçilmesi
önerilir.

Anahtar Kelimeler

cilt kanseri, ablasyon, trasnfer öğrenme

Kaynakça

• R. L. Siegel, A. N. Giaquinto, and A. Jemal, ‘Cancer statistics, 2024’, CA Cancer J Clin, vol. 74, no. 1, pp. 12–49, Jan. 2024, doi: 10.3322/CAAC.21820.
• M. P. Purdue et al., ‘Etiologic and other factors predicting nevus-associated cutaneous malignant melanoma’, Cancer Epidemiology Biomarkers and Prevention, vol. 14, no. 8, pp. 2015–2022, Aug. 2005, doi: 10.1158/1055- 9965.EPI-05-0097.
• N. J. Petrelli et al., ‘Clinical cancer advances 2009: Major research advances in cancer treatment, prevention, and screening -A report from the American Society of Clinical Oncology’, Journal of Clinical Oncology, vol. 27, no. 35, pp. 6052–6069, Dec. 2009, doi: 10.1200/JCO.2009.26.6171.
• R. L. Siegel Mph, A. N. Giaquinto, | Ahmedin, J. Dvm, and R. L. Siegel, ‘Cancer statistics, 2024’, CA Cancer J Clin, vol. 74, no. 1, pp. 12–49, Jan. 2024, doi: 10.3322/CAAC.21820.
• F. Morgese et al., ‘Gender Differences and Outcomes in Melanoma Patients’, Oncol Ther, vol. 8, no. 1, p. 103, Jun. 2020, doi: 10.1007/S40487-020-00109-1.
• L. De Ann, R. I. Vogel, M. A. Weinstock, H. H. Nelson, R. L. Ahmed, and M. Berwick, ‘Association between indoor tanning and melanoma in younger men and women’, JAMA Dermatol, vol. 152, no. 3, p. 268, Mar. 2016, doi: 10.1001/JAMADERMATOL.2015.2938.
• J. J. Nordlund and A. B. Lerner, ‘On the causes of melanomas.’, Am J Pathol, vol. 89, no. 2, p. 443, 1977, Accessed: Jul. 29, 2024. [Online]. Available: /pmc/articles/PMC2032245/?report=abstract
• G. P. Guy, Z. Berkowitz, D. M. Holman, and A. M. Hartman, ‘Recent Changes in the Prevalence of and Factors Associated With Frequency of Indoor Tanning Among US Adults’, JAMA Dermatol, vol. 151, no. 11, p. 1256, Nov. 2015, doi: 10.1001/JAMADERMATOL.2015.1568.
• G. P. Guy, Y. Zhang, D. U. Ekwueme, S. H. Rim, and M. Watson, ‘The potential impact of reducing indoor tanning on melanoma prevention and treatment costs in the United States: An economic analysis’, J Am Acad Dermatol, vol. 76, no. 2, pp. 226–233, Feb. 2017, doi: 10.1016/J.JAAD.2016.09.029.
• B. Ahmed, M. I. Qadir, and S. Ghafoor, ‘Malignant melanoma: Skin cancer—diagnosis, prevention, and treatment’, Crit Rev Eukaryot Gene Expr, vol. 30, no. 4, pp. 291–297, 2020, doi: 10.1615/CRITREVEUKARYOTGENEEXPR.2020028454.
• PDQ Cancer Genetics Editorial Board, ‘Genetics of Skin Cancer (PDQ®): Health Professional Version’, PDQ Cancer Information Summaries, 2002, Accessed: Jul. 30, 2024. [Online]. Available: http://www.ncbi.nlm.nih.gov/pubmed/26389333
• S. R. Jartarkar et al., ‘Artificial intelligence in Dermatopathology’, J Cosmet Dermatol, vol. 22, no. 4, pp. 1163– 1167, Apr. 2023, doi: 10.1111/JOCD.15565.
• G. H. Dagnaw, M. El Mouhtadi, and M. Mustapha, ‘Skin cancer classification using vision transformers and explainable artificial intelligence’, J Med Artif Intell, vol. 7, no. 0, pp. 14–14, Jun. 2024, doi: 10.21037/JMAI-24-6.
• B. C. R. S. Furriel et al., ‘Artificial intelligence for skin cancer detection and classification for clinical environment: a systematic review’, Front Med (Lausanne), vol. 10, p. 1305954, Jan. 2023, doi: 10.3389/FMED.2023.1305954/BIBTEX.
• C. Xin et al., ‘An improved transformer network for skin cancer classification’, Comput Biol Med, vol. 149, Oct. 2022, doi: 10.1016/J.COMPBIOMED.2022.105939.
• C. Flosdorf, J. Engelker, I. Keller, and N. Mohr, ‘Skin Cancer Detection utilizing Deep Learning: Classification of Skin Lesion Images using a Vision Transformer’, Jul. 2024, Accessed: Jul. 30, 2024. [Online]. Available: https://arxiv.org/abs/2407.18554v1
• D. Wen et al., ‘Characteristics of publicly available skin cancer image datasets: a systematic review’,
• Lancet Digit Health, vol. 4, no. 1, pp. e64–e74, Jan. 2022, doi: 10.1016/S2589-7500(21)00252-1.
• R. A. Mehr and A. Ameri, ‘Skin Cancer Detection Based on Deep Learning’, J Biomed Phys Eng, vol. 12, no. 6, p. 559, Dec. 2022, doi: 10.31661/JBPE.V0I0.2207-1517.
• A. G. C. Pacheco and R. A. Krohling, ‘Recent advances in deep learning applied to skin cancer detection’, Dec. 2019, Accessed: Jul. 30, 2024. [Online]. Available: https://arxiv.org/abs/1912.03280v1
• R. Ali, R. C. Hardie, B. N. Narayanan, and S. De Silva, ‘Deep Learning Ensemble Methods for Skin Lesion Analysis towards Melanoma Detection’, Proceedings of the IEEE National Aerospace Electronics Conference, NAECON, vol. 2019-July, pp. 311–316, Jul. 2019, doi: 10.1109/NAECON46414.2019.9058245.
• M. A. Khan, T. Akram, M. Sharif, S. Kadry, and Y. Nam, ‘Computer Decision Support System for Skin Cancer Localization and Classification’, Computers, Materials & Continua, vol. 68, no. 1, pp. 1041– 1064, Mar. 2021, doi: 10.32604/CMC.2021.016307.
• K. Thurnhofer-Hemsi and E. Domínguez, ‘A Convolutional Neural Network Framework for Accurate Skin Cancer Detection’, Neural Process Lett, vol. 53, no. 5, pp. 3073–3093, Oct. 2021, doi: 10.1007/S11063-020- 10364-Y/TABLES/9.
• H. Hussein, A. Magdy, R. F. Abdel-Kader, and K. A. El Salam, ‘Binary Classification of Skin Cancer Images Using Pre-trained Networks with I-GWO’, Inteligencia Artificial, vol. 27, no. 74, pp. 102–116, Dec. 2024, doi: 10.4114/INTARTIF.VOL27ISS74PP102-116.
• M. Naqvi, S. Q. Gilani, T. Syed, O. Marques, and H. C. Kim, ‘Skin Cancer Detection Using Deep Learning—A Review’, Diagnostics 2023, Vol. 13, Page 1911, vol. 13, no. 11, p. 1911, May 2023, doi: 10.3390/DIAGNOSTICS13111911.
• S. Benyahia, B. Meftah, and O. Lézoray, ‘Multi-features extraction based on deep learning for skin lesion classification’, Tissue Cell, vol. 74, p. 101701, Feb. 2022, doi: 10.1016/J.TICE.2021.101701.
• S. Alzahrani, B. Al-Bander, and W. Al-Nuaimy, ‘A Comprehensive Evaluation and Benchmarking of Convolutional Neural Networks for Melanoma Diagnosis’, Cancers 2021, Vol. 13, Page 4494, vol. 13, no. 17, p. 4494, Sep. 2021, doi: 10.3390/CANCERS13174494.
• D. ; Popescu et al., ‘New Trends in Melanoma Detection Using Neural Networks: A Systematic Review’,
• Sensors 2022, Vol. 22, Page 496, vol. 22, no. 2, p. 496, Jan. 2022, doi: 10.3390/S22020496.
• ‘Transfer Learning - MATLAB & Simulink’. Accessed: Jul. 31, 2024. [Online]. Available:
• https://www.mathworks.com/discovery/transfer-learning.html
• J. Redmon and A. Farhadi, ‘YOLO9000: Better, faster, stronger’, Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 6517–6525, Nov. 2017, doi: 10.1109/CVPR.2017.690.
• M. Tan and Q. V Le, ‘EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks’, May 24, 2019, PMLR. Accessed: Jul. 30, 2024. [Online]. Available: https://proceedings.mlr.press/v97/tan19a.html
• G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, ‘Densely Connected Convolutional Networks’, Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 2261–2269, Aug. 2016, doi: 10.1109/CVPR.2017.243.
• A. F. Agarap, ‘Deep Learning using Rectified Linear Units (ReLU)’, Mar. 2018, Accessed: Jul. 31, 2024.
• [Online]. Available: http://arxiv.org/abs/1803.08375
• K. Tang, W. Liu, Y. Zhang, and X. Chen, ‘Acceleration of stochastic gradient descent with momentum by averaging: finite-sample rates and asymptotic normality’, May 2023, Accessed: Jul. 31, 2024. [Online]. Available: https://arxiv.org/abs/2305.17665v2
• A. Biswas et al., ‘Generative Adversarial Networks for Data Augmentation’, Data Driven Approaches on Medical Imaging, pp. 159–177, Jun. 2023, doi: 10.1007/978-3-031-47772-0_8.
• A. Antoniou, A. Storkey, and H. Edwards, ‘Data Augmentation Generative Adversarial Networks’, J Phys A Math Theor, vol. 44, no. 44, pp. 1–13, Nov. 2017, Accessed: Jul. 31, 2024. [Online]. Available: https://arxiv.org/abs/1711.04340v3