Koroner Arter Hastalığının İris Görüntülerinden Yerel İkili Örüntüler ve Yapay Sinir Ağı Kullanılarak Tahmini

Year 2023, , 665 - 679, 15.06.2023

Ferdi Özbilgin , Çetin Kurnaz

https://doi.org/10.31466/kfbd.1266996

Cited By: 1

Abstract

Koroner Arter Hastalığı (KAH), kalp kasını besleyen koroner arterlerin daralması veya tıkanması sonucunda oluşan bir kalp hastalığıdır. Dünya genelinde mortalite oranı yüksek bir sağlık sorunu olan KAH’ın erken tanısı çok önemlidir. Bu çalışmada, iridoloji ve görüntü işleme tekniklerinin kullanılarak KAH’ın tahmin edilmesi amaçlanmıştır. Mevcut çalışmalardan farklı olarak iridoloji ile birlikte gerçekleştirilen kalp hastalıkları tahmini çalışmalarında kullanılmamış Yerel İkili Örüntüler (YİÖ) öznitelik çıkarma yönteminin başarımı analiz edilmiştir. Önerilen yöntemde 94 KAH ve 104 Kontrol grubu olmak üzere toplamda 198 gönüllüye ait iris görüntülerinden YİÖ ile öznitelikler çıkarılmış ve Yapay Sinir Ağı (YSA) kullanılarak sınıflandırma gerçekleştirilmiştir. Görüntü içerisinden iris konumlarını bulmak için İntegral Diferansiyel Operatörü ve irisi dikdörtgen formata dönüştürmek için Rubber Sheet Normalizasyon yöntemleri kullanılmıştır. İridoloji haritası vasıtasıyla iriste yer alan kalp bölgesi analiz bölgesi olarak belirlenmiş ve bu bölgeden bir piksel ve sekiz komşulukla YİÖ ile 59 adet histogram temelli öznitelikler çıkarılmıştır. Çıkarılan özniteliklerin YSA ile sınıflandırması gerçekleştirilmiştir. Eğitim ve test olarak iki gruba ayrılan verilerde eğitim işlemi Ölçeklendirilmiş Konjuge Gradyan (Scaled Conjugate Gradient, SCG) algoritması ile gerçekleştirilmiştir. Performans ölçütü olarak belirlenen doğruluk, kesinlik, duyarlılık, özgüllük, F1 skor ve Eğri Altında Kalan Alan (Area Under the Curve, AUC) değerleri test verileri için sırasıyla %91,5, 0,9063, 0,9355, 0,8929, 0,92063 ve 0,9103 olarak bulunmuştur. Elde edilen bulgular doğrultusunda YİÖ temelli önerilen yöntemin KAH’ın tahmin edilmesinde başarılı olduğu söylenebilir.

Keywords

Koroner Arter Hastalığı, İris, İridoloji, Görüntü İşleme, Yerel İkili Örüntüler, Yapay Sinir Ağları

Supporting Institution

-

Project Number

-

Thanks

-

Prediction of Coronary Artery Disease from Iris Images Using Local Binary Patterns and Artificial Neural Network

Abstract

Coronary Artery Disease (CAD) is a heart disease caused by the narrowing or blockage of the coronary arteries that supply the heart muscle. Early diagnosis of CAD, a health problem with a high mortality rate worldwide, is very important. In this study, we aimed to predict CAD using iridology and image processing techniques. Unlike previous studies, the performance of the Local Binary Patterns (LBP) feature extraction method, which has not been utilized in iridology-based heart disease prediction studies, was analyzed. In the proposed method, features were extracted with LBP from iris images of a total of 198 volunteers (94 CAD and 104 Control group), and classification was performed using Artificial Neural Network (ANN). The Integral Differential Operator method was used to find the iris positions in the image, and Rubber Sheet Normalization was used to convert the iris into a rectangular format. Through the iridology map, the heart region in the iris was determined as the analysis region, and 59 histogram-based features were extracted from this region with one pixel and eight neighborhoods with the LBP. The classification was performed using ANN with the extracted features. The data were divided into two groups: training and test. The Scaled Conjugate Gradient (SCG) algorithm performed the training process. The accuracy, precision, sensitivity, specificity, F1 score and Area Under the Curve (AUC) values determined as performance criteria were 91.5%, 0.9063, 0.9355, 0.8929, 0.92063 and 0.9103 for the test data, respectively. Based on the findings, it can be said that the proposed method based on the LBP is successful in predicting CAD.

Keywords

Coronary Artery Disease, Iris, Iridology, Image Processing, Local Binary Patterns, Artificial Neural Networks

Project Number

-

References

• Alizadehsani, R., Zangooei, M. H., Hosseini, M. J., Habibi, J., Khosravi, A., Roshanzamir, M., Khozeimeh, F., Sarrafzadegan, N. ve Nahavandi, S. (2016). Coronary artery disease detection using computational intelligence methods. Knowledge-Based Systems, 109, 187-197.
• Daugman, J. (2009). How iris recognition works. The essential guide to image processing (s. 715-739): Elsevier.
• Fausett, L. V. (2006). Fundamentals of neural networks: architectures, algorithms and applications: Pearson Education India.
• Ghiasi, M. M., Zendehboudi, S. ve Mohsenipour, A. A. (2020). Decision tree-based diagnosis of coronary artery disease: CART model. Computer methods and programs in biomedicine, 192, 105400.
• Gunawan, V. A., Putra, L. S. A., Imansyah, F. ve Kusumawardhani, E. (2022). Identification of Coronary Heart Disease through Iris using Gray Level Co-occurrence Matrix and Support Vector Machine Classification. International Journal of Advanced Computer Science and Applications, 13(1).
• Jensen, B. (2012). Iridology simplified: Book Publishing Company.
• Kurnaz, Ç. ve Gül, B. K. (2018). Determination of the relationship between sodium ring width on iris and cholesterol level. Journal of the Faculty of Engineering and Architecture of Gazi University, 33(4), 1557-1568.
• Kusuma, F. D., Kusumaningtyas, E. M., Barakbah, A. R. ve Hermawan, A. A. (2018). Heart abnormalities detection through iris based on mobile. Paper presented at the 2018 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC).
• Ma, L., Zhang, D., Li, N., Cai, Y., Zuo, W. ve Wang, K. (2012). Iris-based medical analysis by geometric deformation features. IEEE journal of biomedical and health informatics, 17(1), 223-231.
• Malakar, A. K., Choudhury, D., Halder, B., Paul, P., Uddin, A. ve Chakraborty, S. (2019). A review on coronary artery disease, its risk factors, and therapeutics. Journal of cellular physiology, 234(10), 16812-16823.
• Muzamil, S., Hussain, T., Haider, A., Waraich, U., Ashiq, U. ve Ayguadé, E. (2020). An intelligent iris based chronic kidney identification system. Symmetry, 12(12), 2066.
• Ojala, T., Pietikainen, M. ve Maenpaa, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on pattern analysis and machine intelligence, 24(7), 971-987.
• Ozbilgin, F. ve Kurnaz, C. (2022). An alternative approach for determining the cholesterol level: Iris analysis. International Journal of Imaging Systems and Technology, 32(4), 1159-1171.
• Özbilgin, F. (2019). Sistemik hastalıkların iristeki belirtilerinin iris analizi yöntemi ile belirlenmesi. Yüksek Lisans Tezi, Ondokuz Mayıs Üniversitesi, Fen Bilimleri Enstitüsü, Samsun.
• Özbilgin, F., Kurnaz, Ç. ve Aydın, E. (2023). Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis. Diagnostics, 13(6), 1081.
• Permatasari, L. I., Novianty, A. ve Purboyo, T. W. (2016). Heart disorder detection based on computerized iridology using support vector machine. Paper presented at the 2016 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC).
• Putra, L. S. A., Isnanto, R. R., Triwiyatno, A. ve Gunawan, V. A. (2018). Identification of Heart Disease With Iridology Using Backpropagation Neural Network. Paper presented at the 2018 2nd Borneo International Conference on Applied Mathematics and Engineering (BICAME).
• Ramlee, R. ve Ranjit, S. (2009). Using iris recognition algorithm, detecting cholesterol presence. Paper presented at the 2009 International Conference on Information Management and Engineering.
• Rehman, M. U., Najam, S., Khalid, S., Shafique, A., Alqahtani, F., Baothman, F., Shah, S. Y., Abbasi, Q. H., Imran, M. A. ve Ahmad, J. (2021). Infrared sensing based non-invasive initial diagnosis of chronic liver disease using ensemble learning. IEEE Sensors Journal, 21(17), 19395-19406.
• Samant, P. ve Agarwal, R. (2018). Machine learning techniques for medical diagnosis of diabetes using iris images. Computer methods and programs in biomedicine, 157, 121-128.
• Sunnetci, K. M., ve Alkan, A., (2022). Biphasic majority voting-based comparative COVID-19 diagnosis using chest X-Ray images. Expert Systems with Applications, 119430.
• Sunnetci, K. M., Ulukaya, S., ve Alkan, A., (2022). Periodontal bone loss detection based on hybrid deep learning and machine learning models with a user-friendly application. Biomedical Signal Processing and Control, 77: 103844.
• TÜİK. (2019). Ölüm ve Ölüm Nedeni İstatistikleri, 2019. Erişim adresi Ölüm ve Ölüm Nedeni İstatistikleri, 2019
• Virani, S. S., Alonso, A., Benjamin, E. J., Bittencourt, M. S., Callaway, C. W., Carson, A. P., Chamberlain, A. M., Chang, A. R., Cheng, S. ve Delling, F. N. (2020). Heart disease and stroke statistics—2020 update: a report from the American Heart Association. Circulation, 141(9), e139-e596.
• Yegnanarayana, B., (2009). Artificial neural networks. PHI Learning Pvt. Ltd.