MONKEYPOX DISEASE DETECTION FROM SKIN LESION IMAGES USING TRANSFER LEARNING

Yıl 2024, , 148 - 164, 30.04.2024

Hüseyin Fırat , Hüseyin Üzen

https://doi.org/10.54365/adyumbd.1411927

Cited By: 1

Öz

Monkeypox is a viral disease predominantly found in Central and West Africa, resulting from infection with the monkeypox virus. Its transmission occurs through close contact with infected individuals, manifesting as flu-like symptoms and skin rashes, often resembling chickenpox or measles, thus increasing the risk of misdiagnosis. Timely and precise diagnosis is crucial for effective medical intervention. Recently, deep learning-based transfer learning methods have emerged as a promising means to accurately differentiate monkeypox from similar diseases. This study leverages pre-trained convolutional neural networks, including VGG16, ResNet models, Xception, Inception models, DenseNet121, and DenseNet201, to create robust diagnostic models by extracting pertinent features from medical images. The "Monkeypox Skin Lesion Dataset" on Kaggle, comprising two classes (Monkeypox and others), was employed to assess these models. Experimental findings revealed that the DenseNet201 model achieved the highest classification accuracy, reaching 95.56%, highlighting its effectiveness when compared to existing literature.

Anahtar Kelimeler

Deep learning, Monkeypox disease, Transfer learning, Classification

TRANSFER ÖĞRENME KULLANILARAK DERİ LEZYON GÖRÜNTÜLERİNDEN MAYMUN ÇİÇEĞİ HASTALIĞININ TESPİTİ

Öz

Maymun çiçeği, ağırlıklı olarak Orta ve Batı Afrika'da bulunan ve maymun çiçeği virüsü enfeksiyonundan kaynaklanan viral bir hastalıktır. Bulaşma, enfeksiyon kapmış kişilerle yakın temas yoluyla meydana gelmektedir. Grip benzeri semptomlar ve deri döküntüleri şeklinde kendini göstermektedir. Çoğunlukla su çiçeği veya kızamığa benzer ve dolayısıyla yanlış teşhis riskini arttırmaktadır. Etkili tıbbi müdahale için zamanında ve kesin tanı çok önemlidir. Son zamanlarda, derin öğrenmeye dayalı transfer öğrenme yöntemleri, maymun çiçeğini benzer hastalıklardan doğru bir şekilde ayırt etmek için umut verici bir araç olarak ortaya çıkmıştır. Bu çalışma, tıbbi görüntülerden ilgili özellikleri çıkararak sağlam teşhis modelleri oluşturmak için VGG16, ResNet modelleri, Xception, Inception modelleri, DenseNet121 ve DenseNet201 dahil olmak üzere önceden eğitilmiş evrişimsel sinir ağlarından yararlanmaktadır. Bu modelleri değerlendirmek için Kaggle'daki iki sınıftan (MaymunÇiçeği ve diğerleri) oluşan "Maymun Çiçeği Cilt Lezyonu Veri Seti" kullanılmıştır. Deneysel bulgular, DenseNet201 modelinin %95.56'ya ulaşarak en yüksek sınıflandırma doğruluğuna ulaştığını ve mevcut literatürle karşılaştırıldığında etkinliğini öne çıkardığını ortaya koymaktadır.

Anahtar Kelimeler

Derin öğrenme, Maymun çiçeği hastalığı, Transfer öğrenimi, Sınıflandırma

Kaynakça

• Mileto D. New challenges in human monkeypox outside Africa: A review and case report from Italy. Travel Medicine and Infectious Disease 2022;49:102386.
• Thornhill JP. Monkeypox Virus Infection in Humans across 16 Countries — April–June 2022. The New England Journal of Medicine 2022;387:679–691.
• Sepehrinezhad A, Ashayeri Ahmadabad R, Sahab-Negah S. Monkeypox virus from neurological complications to neuroinvasive properties: current status and future perspectives. Journal of Neurology 2023;270:101–108.
• WHO. Monkeypox Outbreak 2022. 2022. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/monkeypox. [Accessed: 25-Oct-2023].
• Beeson MA. Mpox in Children and Adolescents: Epidemiology, Clinical Features, Diagnosis, and Management. Pediatrics 2023;151:e2022060179.
• Altindis M, Puca E, Shapo L. Diagnosis of monkeypox virus – An overview. Travel Medicine and Infectious Disease 2022;50:102459.
• Paniz-Mondolfi A. Evaluation and validation of an RT-PCR assay for specific detection of monkeypox virus (MPXV). Journal of Medical Virology 2023;95:1–12.
• Fomenko A. Assessing severe acute respiratory syndrome coronavirus 2 infectivity by reverse-transcription polymerase chain reaction: A systematic review and meta-analysis. Reviews in Medical Virology 2022;32:1–13.
• Nayak T. Deep learning based detection of monkeypox virus using skin lesion images. Medicine in Novel Technology and Devices 2023;18:100243.
• Nayak T. Detection of Monkeypox from skin lesion images using deep learning networks and explainable artificial intelligence. Applied Mathematics in Science and Engineering 2023;31.
• Chadaga K. Application of Artificial Intelligence Techniques for Monkeypox: A Systematic Review. Diagnostics 2023;13:1–16.
• Pramanik R, Banerjee B, Efimenko G, Kaplun D, Sarkar R. Monkeypox detection from skin lesion images using an amalgamation of CNN models aided with Beta function-based normalization scheme. PLoS One 2023;18:1–21.
• Almufareh MF, Tehsin S, Humayun M, Kausar S. A Transfer Learning Approach for Clinical Detection Support of Monkeypox Skin Lesions. Diagnostics 2023;13:1–16.
• Sitaula C and Shahi T B. Monkeypox Virus Detection Using Pre-trained Deep Learning-based Approaches. Journal of Medical Systems 2022;46.
• Ahsan MM, Uddin MR, Farjana M, Sakib AN, Al Momin K, Luna SA. Image Data collection and implementation of deep learning-based model in detecting Monkeypox disease using modified VGG16. 2022.
• Ali S N. Monkeypox Skin Lesion Detection Using Deep Learning Models: A Feasibility Study. 2022:2–5.
• Akın KD, Gürkan C, Budak A, Karataş H. Açıklanabilir Yapay Zeka Destekli Evrişimsel Sinir Ağları Kullanılarak Maymun Çiçeği Deri Lezyonunun Sınıflandırılması. European Journal of Science and Technology 2022;40:106–110.
• Bala D, MonkeyNet: A robust deep convolutional neural network for monkeypox disease detection and classification. Neural Networks 2023;161:757–775.
• Tensorkitty. Monkeypox Skin Lesion Dataset. [Online]. Available: https://www.kaggle.com/datasets/nafin59/monkeypox-skin-lesion-dataset/data. [Accessed: 15-Oct-2023].
• Simonyan K and Zisserman A. Very deep convolutional networks for large-scale image recognition. In 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings 2015.
• He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016: 770–778.
• Chollet F. Xception: Deep learning with depthwise separable convolutions. 30th IEEE Conference on Computer Vision and Pattern Recognition. 2017: 1800–1807.
• Szegedy C, Vanhoucke V, Ioffe S, Shlens J, and Wojna Z. Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE conference on computer vision and pattern Recognition 2016: 2818–2826.
• Szegedy C, Ioffe S, Vanhoucke V, Alemi AA. Inception-v4, inception-ResNet and the impact of residual connections on learning. AAAI-17: Thirty-First AAAI Conference on Artificial Intelligence 2017:4278–4284.
• Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. Conference on Computer Vision and Pattern Recognition (CVPR) 2017: 2261–2269.
• Sahin V H, Oztel I, Yolcu Oztel G. Human Monkeypox Classification from Skin Lesion Images with Deep Pre-trained Network using Mobile Application. Journal of Medical Systems 2022; 46.