Öz
Glokom, göz iç basıncının anormal bir biçimde artmasına neden olan ve bu sebeple görme sinirlerinde kalıcı hasara yol açan bir hastalıktır. Göz rahatsızlıkları içerisinde en “sinsi” hastalık olarak bilinen hastalığın erken ve doğru teşhisi önemlidir. Bu çalışmada, açık kaynak bir veri tabanından alınan yüksek çözünürlüklü göz dibi (fundus) fotoğraflarından glokom tahmini uygulaması gerçekleştirilmiştir. Segmente edilmiş fotoğraflardan gri seviye eş oluşum matrisi kullanılarak korelasyon, enerji, homojenlik, kontrast ve entropi öznitelikleri çıkarılmıştır. Çıkarılan öznitelikler, ortalama değerleri alındıktan sonra %66 test ve %33 eğitim olarak ayrılmıştır. Verilere 3 kat çapraz doğrulama uygulanmış ve verilerin %66’sı kullanılarak geri beslemeli bir yapay sinir ağı, sınıflandırma ve regresyon ağaçları algoritması ve k en yakın komşuluk algoritması eğitilmiştir. %33 test verisi ile de sınıflandırma başarısı test edilmiştir. Sonuç olarak, k en yakın komşuluk algoritması ile ortalama %86,7 doğruluk, karar ağaçları ile ortalama %87,8 doğruluk ve yapay sinir ağı algoritması ile de ortalama %96,7 doğruluk ile glokom ve sağlıklı bireyler sınıflandırılmıştır. Elde edilen sonuçlara göre glokom rahatsızlığının gri seviye eş oluşum matrisi öznitelikleri ile glokom hastalığının yüksek doğrulukta tespit edilebildiği görülmüştür.
Anahtar Kelimeler
Yapay Sinir Ağı Göz Dibi Fotoğrafı Sınıflandırma ve Regresyon Ağacı Glokom Gri seviye Eş oluşum matrisi K-en yakın komşuluk. Artificial Neural Network Fundus Classification and Regression Tree Glaucoma Gray level Co-occurrence matrix K-nearest neighbor.
Kaynakça
- Abhishek et al. (2012). Proposing Efficient Neural Network Training Model for Kidney Stone Diagnosis. International Journal of Computer Science and Information Technologies, 3, No.3(11), 3900–3904.
- Balci, S. Y., Eraslan, M. ve Temel, A. (2015). Glokom, Parkinson hastalığı ve nörodejenerasyon. Marmara Medical Journal, 28(1), 8–12. doi:10.5472/MMJ.2015.03691.1
- Basheer, I. A. ve Hajmeer, M. (2000). Artificial neural networks: fundamentals, computing, design, and application. Journal of microbiological methods, 43(1), 3–31.
- Breiman, L., Friedman, J., Stone, C. J. ve Olshen, R. A. (1984). Classification and regression trees. CRC press. Budai, A., Bock, R., Maier, A., Hornegger, J. ve Michelson, G. (2013). Robust vessel segmentation in fundus images. International Journal of Biomedical Imaging, 2013, 1–22. doi:10.1155/2013/154860
- Cover T, M. ve Hart P, E. (1967). Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory, 1–12.
- Deconinck, E., Hancock, T., Coomans, D., Massart, D. L. ve Vander Heyden, Y. (2005). Classification of drugs in absorption classes using the classification and regression trees (CART) methodology. Journal of Pharmaceutical and Biomedical Analysis, 39(1–2), 91–103.
- Delican, Y., Özyilmaz, L. ve Yildirim, T. (2011). Evolutionary algorithms based RBF neural networks for Parkinson’s disease diagnosis. ELECO 2011 - 7th International Conference on Electrical and Electronics Engineering, (1), 1–4.
- Haralick, R. M., Shanmugam, K. ve Dinstein, I. H. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, (6), 610–621.
- İlkuçar, M. (2015). Kronik Böbrek Hastalarının Yapay Sinir Ağı ve Radyal Temelli Fonksiyon Ağı ile Teşhisi Diagnosis Chronic Kidney Disesa with Artificial Neural Network and Radial Basis Function Network, 6, 82–88.
- Kantardzic, M. (2011). Data Mining: Concepts, Models, Methods, and Algorithms: Second Edition. Data Mining: Concepts, Models, Methods, and Algorithms: Second Edition. doi:10.1002/9781118029145
- Nayak, J., Acharya U., R., Bhat, P. S., Shetty, N. ve Lim, T. C. (2009). Automated diagnosis of glaucoma using digital fundus images. Journal of Medical Systems, 33(5), 337–346. doi:10.1007/s10916-008-9195-z
- Ozkava, U., Ozturk, S., Akdemir, B., ve Sevfi, L. (2018). An efficient retinal blood vessel segmentation using morphological operations. 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 2018, 1-7. doi:10.1109/ISMSIT.2018.8567239
- Rouhani, M. ve Haghighi, M. M. (2009). The diagnosis of hepatitis diseases by support vector machines and artificial neural networks. 2009 International Association of Computer Science and Information Technology - Spring Conference, IACSIT-SC 2009, 456–458. doi:10.1109/IACSIT-SC.2009.25
- Rutkowski, L., Jaworski, M., Pietruczuk, L. ve Duda, P. (2014). The CART decision tree for mining data streams. Information Sciences, 266, 1–15. doi:10.1016/j.ins.2013.12.060
- Şatır, E. (2015). Veri İndirgeme ve Sınıflandırma Teknikleri ile Glokom Hastalığı Teşhisi. El-Cezeri Fen ve Mühendislik Dergisi, 2016(3), 485–497. doi:10.31202/ecjse.67172
- Tomar, D. ve Agarwal, S. (2015). Twin Support Vector Machine Approach for Diagnosing Breast Cancer , Hepatitis , and Diabetes. Hindawi, 2015. doi:10.1155/2015/265637
Öz
Glaucoma is a disease that causes an abnormal increase in intraocular pressure and therefore causes permanent damage to the optic nerves. Early and accurate diagnosis of the disease, known as the most "insidious" disease among eye diseases, is important. In this study, glaucoma prediction application was performed from high-resolution fundus photographs taken from an open-source database. Correlation, energy, homogeneity, contrast and entropy features were extracted from the segmented photographs using the gray-level co-occurrence matrix. Extracted features were divided into 66% test and 33% training after taking their average values. A 3-fold cross-validation was applied to the data and a feedback artificial neural network, classification and regression trees algorithm and k nearest neighbor algorithm were trained using 66% of the data. Classification success was also tested with 33% of test data. As a result, glaucoma and healthy individuals were classified with an average of 86.7% accuracy with the k nearest neighbor algorithm, an average of 87.8% accuracy with the decision trees, and an average of 96.7% accuracy with the artificial neural network algorithm. According to the results obtained, it was seen that glaucoma disease could be detected with high accuracy with the gray-level co-occurrence matrix features of glaucoma disease.
Anahtar Kelimeler
Artificial Neural Network Fundus Classification and Regression Tree Glaucoma Gray level Co-occurrence matrix K-nearest neighbor.
Kaynakça
- Abhishek et al. (2012). Proposing Efficient Neural Network Training Model for Kidney Stone Diagnosis. International Journal of Computer Science and Information Technologies, 3, No.3(11), 3900–3904.
- Balci, S. Y., Eraslan, M. ve Temel, A. (2015). Glokom, Parkinson hastalığı ve nörodejenerasyon. Marmara Medical Journal, 28(1), 8–12. doi:10.5472/MMJ.2015.03691.1
- Basheer, I. A. ve Hajmeer, M. (2000). Artificial neural networks: fundamentals, computing, design, and application. Journal of microbiological methods, 43(1), 3–31.
- Breiman, L., Friedman, J., Stone, C. J. ve Olshen, R. A. (1984). Classification and regression trees. CRC press. Budai, A., Bock, R., Maier, A., Hornegger, J. ve Michelson, G. (2013). Robust vessel segmentation in fundus images. International Journal of Biomedical Imaging, 2013, 1–22. doi:10.1155/2013/154860
- Cover T, M. ve Hart P, E. (1967). Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory, 1–12.
- Deconinck, E., Hancock, T., Coomans, D., Massart, D. L. ve Vander Heyden, Y. (2005). Classification of drugs in absorption classes using the classification and regression trees (CART) methodology. Journal of Pharmaceutical and Biomedical Analysis, 39(1–2), 91–103.
- Delican, Y., Özyilmaz, L. ve Yildirim, T. (2011). Evolutionary algorithms based RBF neural networks for Parkinson’s disease diagnosis. ELECO 2011 - 7th International Conference on Electrical and Electronics Engineering, (1), 1–4.
- Haralick, R. M., Shanmugam, K. ve Dinstein, I. H. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, (6), 610–621.
- İlkuçar, M. (2015). Kronik Böbrek Hastalarının Yapay Sinir Ağı ve Radyal Temelli Fonksiyon Ağı ile Teşhisi Diagnosis Chronic Kidney Disesa with Artificial Neural Network and Radial Basis Function Network, 6, 82–88.
- Kantardzic, M. (2011). Data Mining: Concepts, Models, Methods, and Algorithms: Second Edition. Data Mining: Concepts, Models, Methods, and Algorithms: Second Edition. doi:10.1002/9781118029145
- Nayak, J., Acharya U., R., Bhat, P. S., Shetty, N. ve Lim, T. C. (2009). Automated diagnosis of glaucoma using digital fundus images. Journal of Medical Systems, 33(5), 337–346. doi:10.1007/s10916-008-9195-z
- Ozkava, U., Ozturk, S., Akdemir, B., ve Sevfi, L. (2018). An efficient retinal blood vessel segmentation using morphological operations. 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 2018, 1-7. doi:10.1109/ISMSIT.2018.8567239
- Rouhani, M. ve Haghighi, M. M. (2009). The diagnosis of hepatitis diseases by support vector machines and artificial neural networks. 2009 International Association of Computer Science and Information Technology - Spring Conference, IACSIT-SC 2009, 456–458. doi:10.1109/IACSIT-SC.2009.25
- Rutkowski, L., Jaworski, M., Pietruczuk, L. ve Duda, P. (2014). The CART decision tree for mining data streams. Information Sciences, 266, 1–15. doi:10.1016/j.ins.2013.12.060
- Şatır, E. (2015). Veri İndirgeme ve Sınıflandırma Teknikleri ile Glokom Hastalığı Teşhisi. El-Cezeri Fen ve Mühendislik Dergisi, 2016(3), 485–497. doi:10.31202/ecjse.67172
- Tomar, D. ve Agarwal, S. (2015). Twin Support Vector Machine Approach for Diagnosing Breast Cancer , Hepatitis , and Diabetes. Hindawi, 2015. doi:10.1155/2015/265637
Ayrıntılar
| Birincil Dil | İngilizce |
|---|---|
| Konular | Mühendislik |
| Bölüm | Makaleler |
| Yazarlar | |
| Erken Görünüm Tarihi | 25 Kasım 2022 |
| Yayımlanma Tarihi | 30 Kasım 2022 |
| Yayımlandığı Sayı | Yıl 2022 Sayı: 43 |
- Makale Dosyaları