Ön Eğitimli Modeller ve Özellik Seçiminin Rolü: Diyabetik Retinopati Tanısında Yapay Zeka Tabanlı Yaklaşım

Year 2023, Volume: 18 Issue: 2, 511 - 517, 01.09.2023

Mehmet Kaan Kaya Burak Tasci

https://doi.org/10.55525/tjst.1342118

Abstract

Diyabetik retinopati, uzun süreli diyabet hastalığının bir sonucu olarak gözün retinasında meydana gelen ciddi bir komplikasyondur. Erken teşhis edilmediğinde görme kaybına neden olabilen bu durum, gelişmiş görüntü işleme teknikleri ve yapay zeka algoritmalarının kullanımıyla erken teşhis ve tedavi imkanlarını artırmıştır. Bu makalede, yapay zeka tabanlı diyabetik retinopati tespiti alanındaki güncel gelişmeler ve geleceğe yönelik ihtimaller ele alınmıştır. Makalemizin deneysel çalışmalarında, Kaggle Aptos 2019 veri seti kullanılmıştır. Bu verisetinde 5 sınıf bulunmaktadır ve toplamda 3662 görüntü içerir. Sınıf dağılımı şu şekildedir: DR (Diyabet Retinopatisi) yok: 1805, Hafif: 370, Orta: 999, Şiddetli: 193, Proliferatif DR: 295. Çalışma dört temel yapıdan oluşur. Bu aşamalar (1) VGG16 ve VGG19 ön eğitimli modellerinden özellik çıkarma, (2) Nca, relieff ve chi2 ile özellik seçimi,(3) destek vektör makinesi sınıflandırıcı ile Sınıflandırma,(4) yinelemeli çoğunluk oylama'dır. Önerilen yöntem kullanılarak %99.18'lik yüksek bir doğruluk elde edilmiştir. Ayrıca, Dr yok sınıfı için %100 hassasiyet, Orta sınıfı için %100 duyarlılık, Şiddetli sınıfı için %98.80 duyarlılık ve Dr yok sınıfı için %99.89 F1-Skoru elde edilmiştir. Bu çalışma, diyabetik retinopati tanısında makine öğrenimi yöntemlerinin kullanılmasının etkili bir yaklaşım olduğunu göstermektedir. Deney sonuçları, diyabetik retinopati hastalarının tanı ve tedavi süreçlerine önemli katkılar sağladığını ortaya koymaktadır.

Keywords

VGG16, VGG19, Komşuluk bileşenleri analizi, Relieff, Chi2

Pretrained Models and the Role of Feature Selection: An Artificial Intelligence-Based Approach in the Diagnosis of Diabetic Retinopathy

Abstract

Diabetic retinopathy is a significant complication occurring in the retina of the eye as a result of prolonged diabetes. When not detected early, this condition can lead to vision loss. Advanced image processing techniques and artificial intelligence algorithms have enhanced the possibilities of early diagnosis and treatment. This article discusses current advancements in artificial intelligence-based diabetic retinopathy detection and explores future possibilities in this field. In the experimental studies of the article, the Kaggle Aptos 2019 dataset was utilized. This dataset comprises 5 classes and a total of 3662 images. The class distribution is as follows: No DR (No Diabetic Retinopathy): 1805, Mild: 370, Moderate: 999, Severe: 193, Proliferative DR: 295. The study consists of four fundamental stages. These stages are (1) Feature extraction from VGG16 and VGG19 pretrained models, (2) Feature selection using NCA, Relieff, and Chi2, (3) Classification with Support Vector Machine classifier, (4) Iterative Majority Voting. Using the proposed method, a high accuracy of 99.18% is achieved. Furthermore, sensitivity of 100% for the No DR class, sensitivity of 100% for the Moderate class, sensitivity of 98.80% for the Severe class, and an F1-Score of 99.89% for the No DR class are obtained. This study demonstrates the effective utilization of machine learning methods in diabetic retinopathy diagnosis. The experimental results underscore the significant contributions of diabetic retinopathy patients' diagnosis and treatment processes.

Keywords

VGG16, VGG19, Neighborhood Component Analysis, Relieff, Chi2

References

• Da Rocha Fernandes J, Ogurtsova K, Linnenkamp U, Guariguata L, Seuring T, Zhang P, et al. IDF Diabetes Atlas estimates of 2014 global health expenditures on diabetes. Diabetes Res. Clin. Pract.. 2016;117:48-54.
• Saeedi P, Petersohn I, Salpea P, Malanda B, Karuranga S, Unwin N, et al. Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas. Diabetes Res. Clin. Pract.. 2019;157:107843.
• Klein R, Klein BE, Moss SE, Davis MD, DeMets DL. The Wisconsin epidemiologic study of diabetic retinopathy: IV. Diabetic macular edema. Ophthalmology. 1984;91:1464-74.
• Kobrin Klein BE. Overview of epidemiologic studies of diabetic retinopathy. Ophthalmic Epidemiol. 2007;14:179-83.
• Özçelik YB, Altan A. Diyabetik retinopati teşhisi için fundus görüntülerinin derin öğrenme tabanlı sınıflandırılması. Avr. Bilim Teknol. Derg. 2021:156-67.
• Secinaro S, Calandra D, Secinaro A, Muthurangu V, Biancone P. The role of artificial intelligence in healthcare: a structured literature review. BMC Med. Inform. Decis. Mak.. 2021;21:1-23.
• Hosny A, Parmar C, Quackenbush J, Schwartz L. HJ and Aerts. Artificial intelligence in radiology, Nat. Rev. Cancer. 2018;18:500-10.
• Hipwell J, Strachan F, Olson J, McHardy K, Sharp P, Forrester J. Automated detection of microaneurysms in digital red‐free photographs: a diabetic retinopathy screening tool. Diabet. Med. 2000;17:588-94.
• Tasci B, Tasci I. Deep feature extraction based brain image classification model using preprocessed images: PDRNet. Biomed. Signal Process. Control. 2022;78:103948.
• Macin G, Tasci B, Tasci I, Faust O, Barua PD, Dogan S, et al. An accurate multiple sclerosis detection model based on exemplar multiple parameters local phase quantization: ExMPLPQ. Appl. Sci. 2022;12:4920.
• Kaya D, Gurbuz S, Yildirim IO, Akbal E, Dogan S, Tuncer T. Swin-PHOG-LPQ: An accurate computed tomography images classification model using Swin architecture with handcrafted features. Biomed. Signal Process. Control. 2023;86:105183.
• Math L, Fatima R. Adaptive machine learning classification for diabetic retinopathy. Multimed. Tools Appl. 2021;80:5173-86.
• Mahmoud MH, Alamery S, Fouad H, Altinawi A, Youssef AE. An automatic detection system of diabetic retinopathy using a hybrid inductive machine learning algorithm. Pers. Ubiquit. Comput. 2021:1-15.
• Ali A, Qadri S, Khan Mashwani W, Kumam W, Kumam P, Naeem S, et al. Machine learning based automated segmentation and hybrid feature analysis for diabetic retinopathy classification using fundus image. Entropy. 2020;22:567.
• Yildirim H, Çeliker Ü, Kobat Sg, Dogan S, Bayğin M, Yaman O, et al. An automated diabetic retinopathy disorders detection model based on pretrained MobileNetv2 and nested patch division using fundus images. J. Health Sci. Med.. 2022;5:1741-6.
• Kobat SG, Baygin N, Yusufoglu E, Baygin M, Barua PD, Dogan S, et al. Automated diabetic retinopathy detection using horizontal and vertical patch division-based pre-trained DenseNET with digital fundus images. Diagnostics. 2022;12:1975.
• Tang Y, Gao X, Wang W, Dan Y, Zhou L, Su S, et al. Automated detection of epiretinal membranes in oct images using deep learning. Ophthalmic Res.. 2023;66:238-46.
• Pramil V, de Sisternes L, Omlor L, Lewis W, Sheikh H, Chu Z, et al. A deep learning model for automated segmentation of geographic atrophy imaged using swept-source OCT. Ophthalmol. Retina. 2023;7:127-41.
• Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556. 2014.
• APTOS Dataset. https://www.kaggle.com/c/aptos2019-blindness-detection/data.
• Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 2017;40:834-48.
• Goldberger J, Hinton GE, Roweis S, Salakhutdinov RR. Neighbourhood components analysis. Adv. Neural Inf. Process. Syst. 2004;17.
• Robnik-Šikonja M, Kononenko I. Theoretical and empirical analysis of ReliefF and RReliefF. Mach. Learn. 2003;53:23-69.
• Liu H, Setiono R. Chi2: Feature selection and discretization of numeric attributes. Proceedings of 7th IEEE international conference on tools with artificial intelligence: Ieee; 1995. p. 388-91.
• Noble WS. What is a support vector machine? Nat. Biotechnol. 2006;24:1565-7.
• Dogan S, Baygin M, Tasci B, Loh HW, Barua PD, Tuncer T, et al. Primate brain pattern-based automated Alzheimer's disease detection model using EEG signals. Cogn. Neurodyn. 2023;17:647-59.
• Gangwar AK, Ravi V. Diabetic retinopathy detection using transfer learning and deep learning. Evolution in Computational Intelligence: Front. Intell. Comput. Theory Appl. (FICTA 2020), Volume 1: Springer; 2021. p. 679-89.
• Kassani SH, Kassani PH, Khazaeinezhad R, Wesolowski MJ, Schneider KA, Deters R. Diabetic retinopathy classification using a modified xception architecture. 2019 IEEE international symposium on signal processing and information technology (ISSPIT): IEEE; 2019. p. 1-6.
• Alyoubi WL, Abulkhair MF, Shalash WM. Diabetic retinopathy fundus image classification and lesions localization system using deep learning. Sensors. 2021;21:3704.