TY - JOUR
T1 - Glaucoma Diagnosis with Machine Learning Based on Optical Coherence Tomography and Color Fundus Images
AU - An, Guangzhou
AU - Omodaka, Kazuko
AU - Hashimoto, Kazuki
AU - Tsuda, Satoru
AU - Shiga, Yukihiro
AU - Takada, Naoko
AU - Kikawa, Tsutomu
AU - Yokota, Hideo
AU - Akiba, Masahiro
AU - Nakazawa, Toru
N1 - Funding Information:
-is manuscript was supported in part by a JST grant from JSPS KAKENHI Grants-in-Aid for Scientific Research (B) (T.N. 26293372), the JST Center for Revitalization Promotion and KAKENHI Grants-in-Aid for Young Scientists (B) (K.O. 17K16957), and the Public Trust Suda Memorial Fund for
PY - 2019
Y1 - 2019
N2 - This study aimed to develop a machine learning-based algorithm for glaucoma diagnosis in patients with open-Angle glaucoma, based on three-dimensional optical coherence tomography (OCT) data and color fundus images. In this study, 208 glaucomatous and 149 healthy eyes were enrolled, and color fundus images and volumetric OCT data from the optic disc and macular area of these eyes were captured with a spectral-domain OCT (3D OCT-2000, Topcon). Thickness and deviation maps were created with a segmentation algorithm. Transfer learning of convolutional neural network (CNN) was used with the following types of input images: (1) fundus image of optic disc in grayscale format, (2) disc retinal nerve fiber layer (RNFL) thickness map, (3) macular ganglion cell complex (GCC) thickness map, (4) disc RNFL deviation map, and (5) macular GCC deviation map. Data augmentation and dropout were performed to train the CNN. For combining the results from each CNN model, a random forest (RF) was trained to classify the disc fundus images of healthy and glaucomatous eyes using feature vector representation of each input image, removing the second fully connected layer. The area under receiver operating characteristic curve (AUC) of a 10-fold cross validation (CV) was used to evaluate the models. The 10-fold CV AUCs of the CNNs were 0.940 for color fundus images, 0.942 for RNFL thickness maps, 0.944 for macular GCC thickness maps, 0.949 for disc RNFL deviation maps, and 0.952 for macular GCC deviation maps. The RF combining the five separate CNN models improved the 10-fold CV AUC to 0.963. Therefore, the machine learning system described here can accurately differentiate between healthy and glaucomatous subjects based on their extracted images from OCT data and color fundus images. This system should help to improve the diagnostic accuracy in glaucoma.
AB - This study aimed to develop a machine learning-based algorithm for glaucoma diagnosis in patients with open-Angle glaucoma, based on three-dimensional optical coherence tomography (OCT) data and color fundus images. In this study, 208 glaucomatous and 149 healthy eyes were enrolled, and color fundus images and volumetric OCT data from the optic disc and macular area of these eyes were captured with a spectral-domain OCT (3D OCT-2000, Topcon). Thickness and deviation maps were created with a segmentation algorithm. Transfer learning of convolutional neural network (CNN) was used with the following types of input images: (1) fundus image of optic disc in grayscale format, (2) disc retinal nerve fiber layer (RNFL) thickness map, (3) macular ganglion cell complex (GCC) thickness map, (4) disc RNFL deviation map, and (5) macular GCC deviation map. Data augmentation and dropout were performed to train the CNN. For combining the results from each CNN model, a random forest (RF) was trained to classify the disc fundus images of healthy and glaucomatous eyes using feature vector representation of each input image, removing the second fully connected layer. The area under receiver operating characteristic curve (AUC) of a 10-fold cross validation (CV) was used to evaluate the models. The 10-fold CV AUCs of the CNNs were 0.940 for color fundus images, 0.942 for RNFL thickness maps, 0.944 for macular GCC thickness maps, 0.949 for disc RNFL deviation maps, and 0.952 for macular GCC deviation maps. The RF combining the five separate CNN models improved the 10-fold CV AUC to 0.963. Therefore, the machine learning system described here can accurately differentiate between healthy and glaucomatous subjects based on their extracted images from OCT data and color fundus images. This system should help to improve the diagnostic accuracy in glaucoma.
UR - http://www.scopus.com/inward/record.url?scp=85062590664&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062590664&partnerID=8YFLogxK
U2 - 10.1155/2019/4061313
DO - 10.1155/2019/4061313
M3 - Article
C2 - 30911364
AN - SCOPUS:85062590664
VL - 2019
JO - Journal of Healthcare Engineering
JF - Journal of Healthcare Engineering
SN - 2040-2295
M1 - 4061313
ER -