Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naïve proliferative diabetic retinopathy
作者： Toshihiko Nagasawa , Hitoshi Tabuchi , Hiroki Masumoto , Hiroki Enno , Masanori Niki
DOI: 10.1007/S10792-019-01074-Z
关键词: Ophthalmoscopy 、 Medicine 、 Ophthalmology 、 Therapy naive 、 Diabetic retinopathy 、 Convolutional neural network 、 Deep learning 、 Artificial intelligence 、 Fundus (eye)
摘要: We investigated using ultrawide-field fundus images with a deep convolutional neural network (DCNN), which is machine learning technology, to detect treatment-naive proliferative diabetic retinopathy (PDR). conducted training the DCNN 378 photographic (132 PDR and 246 non-PDR) constructed model. The area under curve (AUC), sensitivity, specificity were examined. model demonstrated high sensitivity of 94.7% 97.2%, an AUC 0.969. Our findings suggested that could be diagnosed wide-angle camera learning.
springer.com
sci-hub.se 参考文章(30)
Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, None, You Only Look Once: Unified, Real-Time Object Detection arXiv: Computer Vision and Pattern Recognition. ,(2015)
Dominik Scherer, Andreas Müller, Sven Behnke, None, Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition Artificial Neural Networks – ICANN 2010. pp. 92- 101 ,(2010) , 10.1007/978-3-642-15825-4_10
Paolo S Silva, Amanda J Dela Cruz, Migil G Ledesma, Jano van Hemert, Ajlan Radwan, Jerry D Cavallerano, Lloyd M Aiello, Jennifer K Sun, Lloyd Paul Aiello, Diabetic Retinopathy Severity and Peripheral Lesions Are Associated with Nonperfusion on Ultrawide Field Angiography Ophthalmology. ,vol. 122, pp. 2465- 2472 ,(2015) , 10.1016/J.OPHTHA.2015.07.034
Ron Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection international joint conference on artificial intelligence. ,vol. 2, pp. 1137- 1143 ,(1995)
Ning Qian, On the momentum term in gradient descent learning algorithms Neural Networks. ,vol. 12, pp. 145- 151 ,(1999) , 10.1016/S0893-6080(98)00116-6
Paolo S. Silva, Jerry D. Cavallerano, Nour Maya N. Haddad, Hanna Kwak, Kelli H. Dyer, Ahmed F. Omar, Hasanain Shikari, Lloyd M. Aiello, Jennifer K. Sun, Lloyd Paul Aiello, Peripheral Lesions Identified on Ultrawide Field Imaging Predict Increased Risk of Diabetic Retinopathy Progression over 4 Years Ophthalmology. ,vol. 122, pp. 949- 956 ,(2015) , 10.1016/J.OPHTHA.2015.01.008
Pradeep S. Prasad, Scott C.N. Oliver, Robert E. Coffee, Jean-Pierre Hubschman, Steven D. Schwartz, Ultra wide-field angiographic characteristics of branch retinal and hemicentral retinal vein occlusion. Ophthalmology. ,vol. 117, pp. 780- 784 ,(2010) , 10.1016/J.OPHTHA.2009.09.019
Anthony K Akobeng, Understanding diagnostic tests 3: receiver operating characteristic curves Acta Paediatrica. ,vol. 96, pp. 644- 647 ,(2007) , 10.1111/J.1651-2227.2006.00178.X
Shuntaro Ogura, Tsutomu Yasukawa, Aki Kato, Hideaki Usui, Yoshio Hirano, Munenori Yoshida, Yuichiro Ogura, Wide-field fundus autofluorescence imaging to evaluate retinal function in patients with retinitis pigmentosa. American Journal of Ophthalmology. ,vol. 158, pp. 1093- 1098 ,(2014) , 10.1016/J.AJO.2014.07.021
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei, ImageNet: A large-scale hierarchical image database computer vision and pattern recognition. pp. 248- 255 ,(2009) , 10.1109/CVPR.2009.5206848