Derin Öğrenme ile Optik Koherens Tomografi Görüntülerinin Sınıflandırılması

Year 2021, Volume: 33 Issue: 2, 607 - 615, 15.09.2021

Numan Halit Güldemir , Ahmet Alkan

https://doi.org/10.35234/fumbd.900079

Cited By: 1

Abstract

Bu makalede, dünyada görme bozukluklarının %8.7’sinin sebebi olan yaşa bağlı makula dejenerasyonu hastalığının tespit edilmesi için otomatik bir sistem sunulmuştur. Hastalığın teşhisi için, son zamanlarda görüntüden özellik tanısı çıkarma işlemlerinde sıklıkla kullanılan evrişimsel sinir ağı mimarisinden faydalanılmıştır. Çalışmada, yaşa bağlı makula dejenerasyonu hastalığının sınıflandırılması için evrişimsel sinir ağı, etiketli 28031 adet OCT görüntüsü ile eğitilmiştir. Eğitilen evrişimsel sinir ağı 6900 adet OCT görüntüsü ile test edilmiştir. Eğitim ve test için Xception, VGG16, InceptionV3 ve Resnet50 derin öğrenme ağları kullanılmıştır. Eğitilen ağlar karşılaştırılıp OCT veri seti için ağların performansları değerlendirilmiştir. Derin öğrenme ağlarının test edilmesi sonucunda Resnet50 ağı 0.95, VGG16 ağı 0.95, InceptionV3 ağı 0.97 ve Xception ağı 0.98 doğruluk oranı OCT veri setini sınıflandırmıştır. 0.96 değerindeki F1 skoruyla Xception ağı kullanılan OCT veri seti üzerindeki en başarılı sınıflandırmayı elde etmiştir.

Keywords

Yaşa bağlı makula dejenerasyonu, derin öğrenme, evrişimsel sinir ağları

Classification of OCT Images via Deep Learning

Abstract

In this article, an automatic system is presented to detect age-related macular degeneration, which is the cause of 8.7% of visual impairment in the world. For the diagnosis of the disease convolutional neural network, which has recently been used in feature extraction from the image, has been utilized. In the study, the convolutional neural network was trained with 28031 labeled OCT images to classify age-related macular degeneration. The trained convolutional neural network was tested with 6900 OCT images. Xception, VGG16, Inception V3 and Resnet50 deep learning networks were used for training and testing. The trained networks were compared and the performance of the networks was evaluated for the OCT dataset. Classification of OCT images using Resnet50 network achieved 0.95, VGG16 network achieved 0.95, InceptionV3 network achieved 0.97 and Xception network achieved accuracy of 0.98. Xception network achieved F1 score of 0.96 which is highest rate of classification on the OCT dataset.

Keywords

Age-related macular degeneration, deep learning, convolutional neural network

References

• Rodríguez, Ignacio R., and Ignacio M. Larrayoz. "Cholesterol oxidation in the retina: implications of 7KCh formation in chronic inflammation and age-related macular degeneration." Journal of lipid research 51.10 (2010): 2847-2862.
• Fine, Stuart L., et al. "Age-related macular degeneration." New England Journal of Medicine 342.7 (2000): 483-492.
• Wong, Wan Ling, et al. "Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis." The Lancet Global Health 2.2 (2014): e106-e116.
• Al Gwairi, Othman, et al. "Cellular and molecular pathology of age-related macular degeneration: potential role for proteoglycans." Journal of ophthalmology 2016 (2016).
• Sibel, İ. N. A. N. "Retina anatomisi." Kocatepe Tıp Dergisi 15.3 (2014): 355-359.
• Nowak, Jerzy Z. "Age-related macular degeneration (AMD): pathogenesis and therapy." Pharmacological Reports 58.3 (2006): 353.
• Age-Related Eye Disease Study Research Group. "The Age-Related Eye Disease Study system for classifying age-related macular degeneration from stereoscopic color fundus photographs: the Age-Related Eye Disease Study Report Number 6." American journal of ophthalmology 132.5 (2001): 668-681.
• ImageNet Veri Seti. http://www.image-net.org
• Image Classification on ImageNet. https://paperswithcode.com/sota/image-classification-on-imagenet
• Retinal OCT Images. https://www.kaggle.com/paultimothymooney/kermany2018
• Chollet, François. "Xception: Deep learning with depthwise separable convolutions." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
• He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep residual learning for image recognition." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778. 2016.
• Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
• Szegedy, Christian, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. "Rethinking the inception architecture for computer vision." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818-2826. 2016.