Search

Purpose: We assessed the ability of deep learning (DL) models to distinguish between tear meniscus of lacrimal duct obstruction (LDO) patients and normal subjects using anterior segment optical coherence tomography (ASOCT) images. Methods: The study included 117 ASOCT images (19 men and 98 women; mean age, 66.6 ± 13.6 years) from 101 LDO patients and 113 ASOCT images (29 men and 84 women; mean age, 38.3 ± 19.9 years) from 71 normal subjects. We trained to construct 9 single and 502 ensemble DL models with 9 different network structures, and calculated the area under the curve (AUC), sensitivity, and specificity to compare the distinguishing abilities of these single and ensemble DL models. Results: For the highest single DL model (DenseNet169), the AUC, sensitivity, and specificity for distinguishing LDO were 0.778, 64.6%, and 72.1%, respectively. For the highest ensemble DL model (VGG16, ResNet50, DenseNet121, DenseNet169, InceptionResNetV2, InceptionV3, and Xception), the AUC, sensitivity, and specificity for distinguishing LDO were 0.824, 84.8%, and 58.8%, respectively. The heat maps indicated that these DL models placed their focus on the tear meniscus region of the ASOCT images. Conclusion: The combination of DL and ASOCT images could distinguish between tear meniscus of LDO patients and normal subjects with a high level of accuracy. These results suggest that DL might be useful for automatic screening of patients for LDO. [ABSTRACT FROM AUTHOR]

This study examined and compared outcomes of deep learning (DL) in identifying swept-source optical coherence tomography (OCT) images without myopic macular lesions [i.e., no high myopia (nHM) vs. high myopia (HM)], and OCT images with myopic macular lesions [e.g., myopic choroidal neovascularization (mCNV) and retinoschisis (RS)]. A total of 910 SS-OCT images were included in the study as follows and analyzed by k-fold cross-validation (k = 5) using DL's renowned model, Visual Geometry Group-16: nHM, 146 images; HM, 531 images; mCNV, 122 images; and RS, 111 images (n = 910). The binary classification of OCT images with or without myopic macular lesions; the binary classification of HM images and images with myopic macular lesions (i.e., mCNV and RS images); and the ternary classification of HM, mCNV, and RS images were examined. Additionally, sensitivity, specificity, and the area under the curve (AUC) for the binary classifications as well as the correct answer rate for ternary classification were examined. The classification results of OCT images with or without myopic macular lesions were as follows: AUC, 0.970; sensitivity, 90.6%; specificity, 94.2%. The classification results of HM images and images with myopic macular lesions were as follows: AUC, 1.000; sensitivity, 100.0%; specificity, 100.0%. The correct answer rate in the ternary classification of HM images, mCNV images, and RS images were as follows: HM images, 96.5%; mCNV images, 77.9%; and RS, 67.6% with mean, 88.9%.Using noninvasive, easy-to-obtain swept-source OCT images, the DL model was able to classify OCT images without myopic macular lesions and OCT images with myopic macular lesions such as mCNV and RS with high accuracy. The study results suggest the possibility of conducting highly accurate screening of ocular diseases using artificial intelligence, which may improve the prevention of blindness and reduce workloads for ophthalmologists. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Background: To determine the correlation between the optic nerve head (ONH) circulation determined by laser speckle flowgraphy and the best-corrected visual acuity or retinal sensitivity before and after intravitreal bevacizumab or ranibizumab for central retinal vein occlusion.Methods: Thirty-one eyes of 31 patients were treated with intravitreal bevacizumab or ranibizumab for macular edema due to a central retinal vein occlusion. The blood flow in the large vessels on the ONH, the best-corrected visual acuity, and retinal sensitivity were measured at the baseline, and at 1, 3, and 6 months after treatment. The arteriovenous passage time on fluorescein angiography was determined. The venous tortuosity index was calculated on color fundus photograph by dividing the length of the tortuous retinal vein by the chord length of the same segment. The blood flow was represented by the mean blur rate (MBR) determined by laser speckle flowgraphy. To exclude the influence of systemic circulation and blood flow in the ONH tissue, the corrected MBR was calculated as MBR of ONH vessel area - MBR of ONH tissue area in the affected eye divided by the vascular MBR - tissue MBR in the unaffected eye. Pearson's correlation tests were used to determine the significance of correlations between the MBR and the best-corrected visual acuity, retinal sensitivity, arteriovenous passage time, or venous tortuosity index.Results: At the baseline, the corrected MBR was significantly correlated with the arteriovenous passage time and venous tortuosity index (r = -0.807, P < 0.001; r = -0.716, P < 0.001; respectively). The corrected MBR was significantly correlated with the best-corrected visual acuity and retinal sensitivity at the baseline, and at 1, 3, and 6 months (all P < 0.050). The corrected MBR at the baseline was significantly correlated with the best-corrected visual acuity at 6 months (r = -0.651, P < 0.001) and retinal sensitivity at 6 months (r = 0.485, P = 0.005).Conclusions: The pre-treatment blood flow velocity of ONH can be used as a predictive factor for the best-corrected visual acuity and retinal sensitivity after anti-VEGF therapy for central retinal vein occlusion.Trial Registration: Trial Registration Number: UMIN000009072. Date of registration: 10/15/2012. [ABSTRACT FROM AUTHOR]