Cilt Kanseri Teşhisi için Konvolüsyonel Sinir Ağları Tabanlı Bilgisayar Destekli Tanıda (CNN-CAD) Dijital Görüntü Kalitesinin İyileştirilmesi

Cilt kanserini tespit edilmesi öncelikle bir dermatolog tarafından yapılan görsel muayeneye ve ardından daha doğru bir tanı için bir dizi teste dayanmaktadır. "Kanser doğal geçmişinde ne kadar erken tespit edilirse, tedavinin o kadar etkili olması muhtemeldir" kavramı cilt kanseri için de geçerlidir. Bu nedenle, gecikmiş veya kaçırılmış herhangi bir tanı daha ağır bir klinik aşamaya veya daha da kötüsü ölüme yol açabilir. Öte yandan, klinik kullanımda biyomarker eksikliği aşırı tanı ve gereksiz biyopsileri beraberinde getirmektedir. DL-CAD sistemleri tanısal doğruluğu artırmak ve gereksiz tedavileri azaltmak için mükemmel bir aday gibi görünmektedir. Bununla birlikte, geleneksel CAD sistemlerin büyük çoğunluğu, yüksek maliyetli ekipmanın yansıra işlenmesi zaman alan dermoskopik görüntüleri kullanır. Hassasiyet hususundaki zorluklara rağmen, modern DL-CAD sistemleri, dijital görüntüleri kullanarak bir yorumlama sağlar ve uygun maliyetli dermoskopik görüntü yakalama ve yorumlamada uzmanlık gerektirmez. Ön işleme yöntemleri bu sorunun çözümünde çok önemli bir rol oynamaktadır. Bu çalışma, önerilen CNN tabanlı ResNet50 derin öğrenme modeli için en yaygın 5 cilt kanseri türünün teşhisinde kullanılacak görüntülerin iyileştirilmesine yönelik ön işleme adımlarına ilişkin sonuçları sunmaktadır. Bildiğimiz kadarıyla, cilt kanseri tanısında ResNet50 derin öğrenme modeli ilk kez kullanılmıştır.

Anahtar Kelimeler:

Cilt kanseri, CNN-CAD sistemleri, Veri kümesi büyütme, Görüntü ön işleme, Medyan filtresi

Improving Digital Image Quality for Convolution Neural Network Based Computer-Aided Diagnosis (CNN-CAD) of Skin Cancer

The practice of detecting skin cancer is based primarily on a visual examination by a dermatologist, followed by a series of tests for a more accurate diagnosis. The concept “the earlier cancer is detected in its natural history, the more effective the treatment is likely to be" is also valid for skin cancer. Hence, any delayed or missed diagnosis can lead to a more severe clinical stage or, what's worse, death. On the other hand, the lack of biomarkers in clinical use brings about overdiagnosis and unnecessary biopsies. DL-CAD system seems to be an excellent candidate for improving diagnostic accuracy and reducing unnecessary treatments. However, the vast majority of conventional CADs manipulate dermoscopic images, which require not only costly equipment but also time-consuming processing. Despite the difficulties with precision, state-of-the-art DL-CAD systems provide an interpretation using digital images, requiring no expertise in cost-effective dermoscopic image capture and interpretation. Pre-processing methods play a crucial role in solving this problem. This study presents results with regard to pre-processing steps to improve the images to be used in the diagnosis of the 5 most common skin cancer types for the proposed CNN based ResNet50 deep learning model. To the best of our knowledge it is the first time that ResNet50 deep-learning model has been utilized in diagnosis of skin cancer.

Keywords:

Skin cancer, CNN-CAD systems, Dataset augmentation, Image pre-processing, Median filter,

PDF

___

1. World Health Organization. 2021. WHO Report on Cancer: Setting Priorities, Investing Wisely and Providing Care for All. (Second Edition), Geneva, Wiley.
2. Atlanta American Cancer Society, 2021, Cancer Facts Figures 2021. Atlanta, USA, 13-15.
3. Global Burden of Disease Cancer Collaboration and Others. 2019. 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 2017: a Systematic Analysis for the Global Burden of Disease Study. JAMA Oncology; 5, 1749-1768.
4. Khazaei, Z., Sohrabivafa, M., Mansori, K., Naemi, H., Goodarzi, E., 2019. Incidence and Mortality of Cervix Cancer and Their Relationship with the Human Development Index in 185 Countries in the World: An Ecology Study in 2018. Advances in Human Biology, 9(3), 222-227.
5. Avanaki, M.R.N., Hojjat, A., Podoleanu, A.G., 2009. Investigation of Computer-based Skin Cancer Detection Using Optical Coherence Tomography. Journal of Modern Optics, 56(13), 1536-1544.
6. Mohan, S.V., Chang, A.L.S., 2014. Advanced Basal Cell Carcinoma: Epidemiology and Therapeutic Innovations. Current Dermatology Reports, 3(1), 40-45.
7. Atlanta American Cancer Society. 2020. Cancer Facts Figures 2020. Atlanta, USA, 10-14.
8. MacFarlane, D., Shah, K., Wysong, A., Wortsman, X., Humphreys, T.R., 2017. The Role of Imaging in the Management of Patients with Nonmelanoma Skin Cancer: Diagnostic Modalities and Applications. Journal of the American Academy of Dermatolgy, 76(4), 579-588.
9. Rat, C., Hild, S., Serandour, J.R., Gaultier, A., Quereux, G., Dreno, B., Nguyen, J.M., 2018. Use of Smartphones for Early Detection of Melanoma: Systematic Review. Journal of Medical Internet Reseach, 20(4), 135-140.
10. Dinnes, J., Deeks, J.J., Grainge, M.J., Chuchu, N., Ferrante di Ruffano, L., Matin, R.N., Thomson, D.R., Wong, K.Y., Aldridge, R.B., Abbott, R., Fawzy, M., Bayliss, E.E., Takwoingi, Y., Davenport, C., Godfrey, K., Walter, F.M., Williams, H.C., Cochrane Skin Cancer Diagnostic Test Accuracy Group, 2018. Visual Inspection for Diagnosing Cutaneous Melanoma in Adults. Cochrane Database System Review, 12(12), 1689-1699.
11. Fujita, H., 2020. AI-based Computer-aided Diagnosis (AI-CAD): the Latest Review to Read First. Radiological Physics and Technology, 13(1), 6-19.
12. Cetinkaya, E., Kirac, M.F., 2020. Image Denoising Using Deep Convolutional Autoencoder with Feature Pyramids. Turkish Journal of Electrical Engineering & Computer Sciences, 28, 2096-2109. 1. Ebigbo, A., Mendel, R., Probst, A., Manzeneder, J., Souza Jr, L.A., Papa, J.P., Palm, C., Messmann, H., 2019. Computer-aided Diagnosis Using Deep Learning in the Evaluation of Early Oesophageal Adenocarcinoma. Gut, 68(7), 1143-1145.
13. Yanase, J., Triantaphyllou, E., 2019. A Systematic Survey of Computer-aided Diagnosis in Medicine: Past and Present Developments. Expert Systems with Applications, 138, 112-821.
14. Codella, N.C.F., Gutman, D., Celebi, M.E., Helba, B., Marchetti, M.A., Dusza, S.W., Kalloo, A., Liopyris, K., Mishra, N., Kittler, H., Halpern, A., 2018. 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). IEEE 15th International Symposium on Biomedical Imaging, Washington DC, USA, 168-172.
15. 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, 1-9.
16. Combalia, M., Codella, N.C.F., Rotemberg, V., Helba, B., Vilaplana, V., Reiter, O., Carrera, C., Barreiro, A., Halpern, A.C., Puig, S., Malvehy, J., 2019. Dermoscopic Lesions in the Wild, 1908.02288.
17. Vasconcelos, C.N., Vasconcelos, B.N., 2020. Experiments Using Deep Learning for Dermoscopy Image Analysis, Pattern Recognition Letters, 139, 95-103.
18. Steppan, J., Hanke, S., 2021. Analysis of Skin Lesion Images with Deep Learning. arXiv preprint arXiv:2101.03814. 2021, 06.06.2021.
19. Vocaturo, E., Zumpano, E., Veltri, P., 2018. Image Pre-processing in Computer Vision Systems for Melanoma Detection. 2018 IEEE International Conference on Bioinformatics and Biomedicine, Madrid, Spain, 2117-2124.
20. Zghal, N.S., Derbel, N., 2020. Melanoma Skin Cancer Detection Based on Image Processing. Current Medical Imaging Reviews, 16(1), 50-58.
21. Hoshyar, A.N., Al-Jumaily, A., Hoshyar, A.N., 2014. The Beneficial Techniques in Preprocessing Step of Skin Cancer Detection System Comparing. Procedia Journal of Computational Science, 42, 25-31.
22. Tan, T.Y., Zhang, L., Jiang, M., 2016. An Intelligent Decision Support System for Skin Cancer Detection from Dermoscopic Images. IEEE 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, Changsha, China, 2194-2199.
23. Sheha, M.A., Mabrouk, M.S., Sharawy, A., 2012. Automatic Detection of Melanoma Skin Cancer Using Texture Analysis. International Journal of Computer Mathematics, 42(20), 22-26.
24. Mishra, N.K., Celebi, M.E., 2016. An Overview of Melanoma Detection in Dermoscopy Images Using Image Processing and Machine Learning, arXiv preprint arXiv:1601.07843.
25. Rhee, K.H., 2017. Median Filtering Detection Based on Variations and Residuals in Image Forensics. Turkish Journal of Electrical Engineering & Computer Sciences, 25, 3811-3826.
26. Jana, E., Subban, R., Saraswathi, S., 2017. Research on Skin Cancer Cell Detection Using Image Processing. IEEE International Conference on Computational Intelligence and Computing Research, Tamil Nadu, India, 1-8.