Automated detection of a nonperfusion area caused by retinal vein occlusion in optical coherence tomography angiography images using deep learning

Abstract

We aimed to assess the ability of deep learning (DL) and support vector machine (SVM) to detect a nonperfusion area (NPA) caused by retinal vein occlusion (RVO) with optical coherence tomography angiography (OCTA) images. The study included 322 OCTA images (normal: 148; NPA owing to RVO: 174 [128 branch RVO images and 46 central RVO images]). Training to construct the DL model using deep convolutional neural network (DNN) algorithms was provided using OCTA images. The SVM used a scikit-learn library with a radial basis function kernel. The area under the curve (AUC), sensitivity and specificity for detecting an NPA were examined. We compared the diagnostic ability (sensitivity, specificity and average required time) between the DNN, SVM and seven ophthalmologists. Heat maps were generated. With regard to the DNN, the mean AUC, sensitivity, specificity and average required time for distinguishing RVO OCTA images with an NPA from normal OCTA images were 0.986, 93.7%, 97.3% and 176.9 s, respectively. With regard to SVM, the mean AUC, sensitivity, and specificity were 0.880, 79.3%, and 81.1%, respectively. With regard to the seven ophthalmologists, the mean AUC, sensitivity, specificity and average required time were 0.962, 90.8%, 89.2%, and 700.6 s, respectively. The DNN focused on the foveal avascular zone and NPA in heat maps. The performance of the DNN was significantly better than that of SVM in all parameters (p < 0.01, all) and that of the ophthalmologists in AUC and specificity (p < 0.01, all). The combination of DL and OCTA images had high accuracy for the detection of an NPA, and it might be useful in clinical practice and retinal screening.

Usefulness of Denoising Process to Depict Myopic Choroidal Neovascularisation Using a Single Optical Coherence Tomography Angiography Image

“…In ophthalmology, some researchers report that deep learning can support an automatic diagnosis of glaucomatous optic neuropathy, diabetic retinopathy, and central serous chorioretinopathy [20][21][22] . Furthermore, nonperfused areas could be automatically detected using deep learning 23 . In the present study, mCNV on single OCTA images could be depicted more clearly using an automatic denoising process that was accomplished by deep learning than by single OCTA images before the denoising process.…”

Machine learning in optical coherence tomography angiography

“…DR, 15,30,36,52,60 SCR, 19,20 and CRVO. 64 However, one limitation to these studies is the small dataset size. As a relatively new imaging modality, there is a limitation in the available datasets for OCTA.…”

Segmentation boosting with compensation methods in optical coherence tomography angiography images

“…RTVue XR 100 Avanti Edition [23], which is an OCTA machine, provides the scanned images from the retina by the reflections on different vessels, as shown in Although OCTA machine may provide a vessel density map [24][25][26][27], as shown in…”