Parçacık Sürüsü Optimizasyon Algoritması ile Optimize Edilmiş Evrişimsel Sinir Ağı Kullanılarak Dermoskopik Görüntülerden Cilt Kanserinin Sınıflandırılması

Yıl 2023, Cilt: 35 Sayı: 1, 261 - 273, 28.03.2023

Erdal Özbay , Feyza Altunbey Özbay

https://doi.org/10.35234/fumbd.1202580

Öz

Dermoskopik görüntülerden cilt lezyonlarını sınıflandırmak için güçlü bir tıbbi karar destek sistemi oluşturmak cilt kanserinin teşhisi için önemli bir adımdır. Laboratuvarlarda cilt kanseri teşhisi için gerçekleştirilen manuel araştırma, insan yorgunluğu, birlikte çalışabilirlik hataları vb. gibi belirli faktörler nedeniyle hatalara açıktır. Bununla birlikte, cilt lezyonlarının karmaşık morfolojik yapısından dolayı eğitimli verilerin kullanılmasında ciddi sorunlar yaşanmaktadır. Son yıllarda, Evrişimli Sinir Ağı (CNN) kullanılarak dermoskopik görüntülerden cilt kanseri türlerini tespit etmede önemli ilerlemeler kaydedilmiştir. Bu çalışmanın temel amacı, farklı sınıf sayılarına sahip cilt kanseri türlerini içeren dermoskopik görüntüleri yüksek doğrulukla otomatik olarak sınıflandırmak için CNN tabanlı bir model geliştirmektir. Çalışmada, evrimsel bir algoritmanın yanlış sınıflandırma oranını azaltmak üzere bir derin öğrenme modeline entegre edildiği bir metodoloji önerilmiştir. CNN hiper-parametreleri, cilt lezyonlarını dört farklı türde sınıflandırmada ağ performansını iyileştirmek için Parçacık Sürüsü Optimizasyon (PSO) algoritması kullanılarak optimize edilmiştir. Önerilen yöntem ile %99,33 doğruluk, %94,65 duyarlılık, %98,87 özgüllük ve 0,983 AUC sonuçlarına ulaşılarak birleştirilmiş ISIC-2019 ve Asian-dermoscopy veri kümeleri üzerinde test edilmiştir. Sonuçlar, Genetik Algoritmalar (GA), Diferansiyel Evrim (DE) ve Gri Kurt Optimizasyonu (GWO) algoritmaları gibi benzer kanıtlanmış algoritmalarla karşılaştırılmıştır. Deneysel sonuçlar, cilt kanseri sınıflandırması için CNN hiper-parametrelerini optimize etmede PSO’nun verimliliğini göstermiştir.

Anahtar Kelimeler

Cilt kanseri, CNN, Dermoskopik görüntü, Sınıflandırma, PSO

Classification of Skin Cancer from Dermoscopic Images using Convolutional Neural Network Optimized with Particle Swarm Optimization Algorithm

Öz

Creating a powerful medical decision support system to classify skin lesions from dermoscopic images is an important step for the diagnosis of skin cancer. Manual research for skin cancer diagnosis in laboratories, human fatigue, interoperability errors, etc. It is prone to errors due to certain factors such as However, there are serious problems in using educated data due to the complex morphological structure of skin lesions. In recent years, significant advances have been made in detecting types of skin cancer from dermoscopic images using the Convolutional Neural Network (CNN). The main aim of this study is to develop a CNN-based model to automatically classify dermoscopic images containing skin cancer types with different class numbers with high accuracy. In the study, a methodology is proposed in which an evolutionary algorithm is integrated into a deep learning model to reduce the misclassification rate. CNN hyper-parameters were optimized using the Particle Swarm Optimization (PSO) algorithm to improve network performance in classifying skin lesions into four different types. The proposed method was tested on the combined ISIC-2019 and Asian-dermoscopy datasets, achieving 99.33% accuracy, 94.65% sensitivity, 98.87% specificity, and 0.983 AUC results. The results are compared with similar proven algorithms such as Genetic Algorithms (GA), Differential Evolution (DE), and Gray Wolf Optimization (GWO) algorithms. Experimental results demonstrated the efficiency of PSO in optimizing CNN hyper-parameters for skin cancer classification.

Kaynakça

• Karimkhani, C., Dellavalle, R. P., Coffeng, L. E., Flohr, C., Hay, R. J., Langan, S. M., ... & Naghavi, M. (2017). Global skin disease morbidity and mortality: an update from the global burden of disease study 2013. JAMA dermatology, 153(5), 406-412.
• Braun, R. P., Rabinovitz, H. S., Oliviero, M., Kopf, A. W., & Saurat, J. H. (2005). Dermoscopy of pigmented skin lesions. Journal of the American Academy of Dermatology, 52(1), 109-121.
• Argenziano, G., Soyer, H. P., 2Chimenti, S., Talamini, R., Corona, R., Sera, F., ... & Kopf, A. W. (2003). Dermoscopy of pigmented skin lesions: results of a consensus meeting via the Internet. Journal of the American Academy of Dermatology, 48(5), 679-693.
• Kittler, H., Pehamberger, H., Wolff, K., & Binder, M. J. T. I. O. (2002). Diagnostic accuracy of dermoscopy. The lancet oncology, 3(3), 159-165.
• Vestergaard, M. E., Macaskill, P. H. P. M., Holt, P. E., & Menzies, S. W. (2008). Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta‐analysis of studies performed in a clinical setting. British Journal of Dermatology, 159(3), 669-676.
• Prathiba, M., Jose, D., & Saranya, R. (2019, October). Automated melanoma recognition in dermoscopy images via very deep residual networks. In IOP Conference Series: Materials Science and Engineering (Vol. 561, No. 1, p. 012107). IOP Publishing.
• He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
• Özbay, E. (2022). An active deep learning method for diabetic retinopathy detection in segmented fundus images using artificial bee colony algorithm. Artificial Intelligence Review, 1-28. https://doi.org/10.1007/s10462-022-10231-3
• Harangi, B. (2018). Skin lesion classification with ensembles of deep convolutional neural networks. Journal of biomedical informatics, 86, 25-32.
• Almaraz-Damian, J. A., Ponomaryov, V., Sadovnychiy, S., & Castillejos-Fernandez, H. (2020). Melanoma and nevus skin lesion classification using handcraft and deep learning feature fusion via mutual information measures. Entropy, 22(4), 484.
• Ameri, A. (2020). A deep learning approach to skin cancer detection in dermoscopy images. Journal of Biomedical Physics and Engineering, 10(6), 801-806.
• Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.
• Moldovanu, S., Obreja, C. D., Biswas, K. C., & Moraru, L. (2021). Towards accurate diagnosis of skin lesions using feedforward back propagation neural networks. Diagnostics, 11(6), 936.
• Bakheet, S. (2017). An SVM framework for malignant melanoma detection based on optimized HOG features. Computation, 5(1), 4.
• Monisha, M., Suresh, A., Bapu, B. R., & Rashmi, M. R. (2019). Classification of malignant melanoma and benign skin lesion by using back propagation neural network and ABCD rule. Cluster Computing, 22(5), 12897-12907.
• Ge, Z., Demyanov, S., Bozorgtabar, B., Abedini, M., Chakravorty, R., Bowling, A., & Garnavi, R. (2017, April). Exploiting local and generic features for accurate skin lesions classification using clinical and dermoscopy imaging. In 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017) (pp. 986-990). IEEE.
• Moura, N., Veras, R., Aires, K., Machado, V., Silva, R., Araújo, F., & Claro, M. (2019). ABCD rule and pre-trained CNNs for melanoma diagnosis. Multimedia Tools and Applications, 78(6), 6869-6888.
• Khan, M. A., Sharif, M., Akram, T., Bukhari, S. A. C., & Nayak, R. S. (2020). Developed Newton-Raphson based deep features selection framework for skin lesion recognition. Pattern Recognition Letters, 129, 293-303.
• Naeem, A., Farooq, M. S., Khelifi, A., & Abid, A. (2020). Malignant melanoma classification using deep learning: datasets, performance measurements, challenges and opportunities. IEEE Access, 8, 110575-110597.
• Adegun, A., & Viriri, S. (2020, February). Deep convolutional network-based framework for melanoma lesion detection and segmentation. In International Conference on Advanced Concepts for Intelligent Vision Systems (pp. 51-62). Springer, Cham.
• Salih, O., & Viriri, S. (2020). Skin lesion segmentation using local binary convolution-deconvolution architecture. Image Analysis & Stereology, 39(3), 169-185.
• Ameri, A. (2020). A deep learning approach to skin cancer detection in dermoscopy images. Journal of Biomedical Physics and Engineering, 10(6), 801-806.
• Chaturvedi, S. S., Tembhurne, J. V., & Diwan, T. (2020). A multi-class skin Cancer classification using deep convolutional neural networks. Multimedia Tools and Applications, 79(39), 28477-28498.
• Lee, Y. C., Jung, S. H., & Won, H. H. (2018). WonDerM: Skin lesion classification with fine-tuned neural networks. arXiv preprint arXiv:1808.03426.
• Mahbod, A., Schaefer, G., Wang, C., Ecker, R., & Ellinge, I. (2019, May). Skin lesion classification using hybrid deep neural networks. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1229-1233). IEEE.
• Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
• Tschandl, P., Rosendahl, C., & Kittler, H. (2018). The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data, 5(1), 1-9.
• Codella, N. C., Gutman, D., Celebi, M. E., Helba, B., Marchetti, M. A., Dusza, S. W., ... & Halpern, A. (2018, April). Skin lesion analysis toward melanoma detection: A challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). In 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018) (pp. 168-172). IEEE.
• Combalia, M., Codella, N. C., Rotemberg, V., Helba, B., Vilaplana, V., Reiter, O., ... & Malvehy, J. (2019). Bcn20000: Dermoscopic lesions in the wild. arXiv preprint arXiv:1908.02288.
• Zhang, Y., Qiu, Z., Yao, T., Liu, D., & Mei, T. (2018). Fully convolutional adaptation networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 6810-6818).
• Johnson, J. M., & Khoshgoftaar, T. M. (2019). Survey on deep learning with class imbalance. Journal of Big Data, 6(1), 1-54.
• LeCun, Y., Kavukcuoglu, K., & Farabet, C. (2010, May). Convolutional networks and applications in vision. In Proceedings of 2010 IEEE international symposium on circuits and systems (pp. 253-256). IEEE.
• Hijazi, S., Kumar, R., & Rowen, C. (2015). Using convolutional neural networks for image recognition. Cadence Design Systems Inc.: San Jose, CA, USA, 9.
• Shi, Y. (2001, May). Particle swarm optimization: developments, applications and resources. In Proceedings of the 2001 congress on evolutionary computation (IEEE Cat. No. 01TH8546) (Vol. 1, pp. 81-86). IEEE.
• Eberhart, R. C., & Shi, Y. (2000, July). Comparing inertia weights and constriction factors in particle swarm optimization. In Proceedings of the 2000 congress on evolutionary computation. CEC00 (Cat. No. 00TH8512) (Vol. 1, pp. 84-88). IEEE.
• García, S., Fernández, A., Luengo, J., & Herrera, F. (2009). A study of statistical techniques and performance measures for genetics-based machine learning: accuracy and interpretability. Soft Computing, 13(10), 959-977.
• Cai, X., Cui, Z., Zeng, J., & Tan, Y. (2009). Individual parameter selection strategy for particle swarm optimization. Particle swarm optimization, 978-953.
• Rubinstein, R. Y., & Kroese, D. P. (2004). The cross-entropy method: a unified approach to combinatorial optimization, Monte-Carlo simulation, and machine learning (Vol. 133). New York: Springer.
• Özbay, E., & Özbay, F. A. (2021). A CNN Framework for Classification of Melanoma and Benign Lesions on Dermatoscopic Skin Images. International Journal of Advanced Networking and Applications, 13(2), 4874-4883.
• Li, J., Cheng, J. H., Shi, J. Y., & Huang, F. (2012). Brief introduction of back propagation (BP) neural network algorithm and its improvement. In Advances in computer science and information engineering (pp. 553-558). Springer, Berlin, Heidelberg.
• Refaeilzadeh, P., Tang, L., & Liu, H. (2009). Cross-validation. Encyclopedia of database systems, 5, 532-538.
• Balasubramanian, K., & Ananthamoorthy, N. P. (2021). Improved adaptive neuro-fuzzy inference system based on modified glowworm swarm and differential evolution optimization algorithm for medical diagnosis. Neural Computing and Applications, 33(13), 7649-7660.
• Xie, F., Yang, J., Liu, J., Jiang, Z., Zheng, Y., & Wang, Y. (2020). Skin lesion segmentation using high-resolution convolutional neural network. Computer methods and programs in biomedicine, 186, 105241.
• Shahin, A. H., Kamal, A., & Elattar, M. A. (2018, December). Deep ensemble learning for skin lesion classification from dermoscopic images. In 2018 9th Cairo International Biomedical Engineering Conference (CIBEC) (pp. 150-153). IEEE.
• Khan, M. A., Javed, M. Y., Sharif, M., Saba, T., & Rehman, A. (2019, April). Multi-model deep neural network based features extraction and optimal selection approach for skin lesion classification. In 2019 international conference on computer and information sciences (ICCIS) (pp. 1-7). IEEE.
• Liu, L., Mou, L., Zhu, X. X., & Mandal, M. (2020). Automatic skin lesion classification based on mid-level feature learning. Computerized Medical Imaging and Graphics, 84, 101765.
• Pour, M. P., & Seker, H. (2020). Transform domain representation-driven convolutional neural networks for skin lesion segmentation. Expert Systems with Applications, 144, 113129.
• Al-Masni, M. A., Al-Antari, M. A., Choi, M. T., Han, S. M., & Kim, T. S. (2018). Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks. Computer methods and programs in biomedicine, 162, 221-231.
• Serte, S., & Demirel, H. (2019). Gabor wavelet-based deep learning for skin lesion classification. Computers in biology and medicine, 113, 103423.
• Dash, M., Londhe, N. D., Ghosh, S., Semwal, A., & Sonawane, R. S. (2019). PsLSNet: Automated psoriasis skin lesion segmentation using modified U-Net-based fully convolutional network. Biomedical Signal Processing and Control, 52, 226-237.
• Li, W., Raj, A. N. J., Tjahjadi, T., & Zhuang, Z. (2021). Digital hair removal by deep learning for skin lesion segmentation. Pattern Recognition, 117, 107994.
• Cengil, E., Çinar, A., & Yildirim, M. (2021). Hybrid Convolutional Neural Network Architectures For Skin Cancer Classification. Avrupa Bilim Ve Teknoloji Dergisi, (28), 694-701.
• Yildirim, M., & Çinar, A. (2021). Classification Of Skin Cancer Images With Convolutional Neural Network Architectures. Turkish Journal Of Science And Technology, 16(2), 187-195.