Automatic Diagnosis of Diabetic Retinopathy Stage Focusing Exclusively on Retinal Hemorrhage.

Background and Objectives: The present study evaluated the detection of diabetic retinopathy (DR) using an automated fundus camera focusing exclusively on retinal hemorrhage (RH) using a deep convolutional neural network, which is a machine-learning technology. Materials and Methods: This investigation was conducted via a prospective and observational study. The study included 89 fundus ophthalmoscopy images. Seventy images passed an image quality review and were graded as showing no apparent DR (n = 51), mild nonproliferative DR (NPDR; n = 16), moderate NPDR (n = 1), severe NPDR (n = 1), and proliferative DR (n = 1) by three retinal experts according to the International Clinical Diabetic Retinopathy Severity scale. The RH numbers and areas were automatically detected and the results of two tests-the detection of mild-or-worse NPDR and the detection of moderate-or-worse NPDR-were examined. Results: The detection of mild-or-worse DR showed a sensitivity of 0.812 (95% confidence interval: 0.680-0.945), specificity of 0.888, and area under the curve (AUC) of 0.884, whereas the detection of moderate-or-worse DR showed a sensitivity of 1.0, specificity of 1.0, and AUC of 1.0. Conclusions: Automated diagnosis using artificial intelligence focusing exclusively on RH could be used to diagnose DR requiring ophthalmologist intervention.

Accuracy of Diabetic Retinopathy Staging with a Deep Convolutional Neural Network Using Ultra-Wide-Field Fundus Ophthalmoscopy and Optical Coherence Tomography Angiography.

PURPOSE: The present study aimed to compare the accuracy of diabetic retinopathy (DR) staging with a deep convolutional neural network (DCNN) using two different types of fundus cameras and composite images. METHOD: The study included 491 ultra-wide-field fundus ophthalmoscopy and optical coherence tomography angiography (OCTA) images that passed an image-quality review and were graded as no apparent DR (NDR; 169 images), mild nonproliferative DR (NPDR; 76 images), moderate NPDR (54 images), severe NPDR (90 images), and proliferative DR (PDR; 102 images) by three retinal experts by the International Clinical Diabetic Retinopathy Severity Scale. The findings of tests 1 and 2 to identify no apparent diabetic retinopathy (NDR) and PDR, respectively, were then assessed. For each verification, Optos, OCTA, and Optos OCTA imaging scans with DCNN were performed. RESULT: The Optos, OCTA, and Optos OCTA imaging test results for comparison between NDR and DR showed mean areas under the curve (AUC) of 0.79, 0.883, and 0.847; sensitivity rates of 80.9%, 83.9%, and 78.6%; and specificity rates of 55%, 71.6%, and 69.8%, respectively. Meanwhile, the Optos, OCTA, and Optos OCTA imaging test results for comparison between NDR and PDR showed mean AUC of 0.981, 0.928, and 0.964; sensitivity rates of 90.2%, 74.5%, and 80.4%; and specificity rates of 97%, 97%, and 96.4%, respectively. CONCLUSION: The combination of Optos and OCTA imaging with DCNN could detect DR at desirable levels of accuracy and may be useful in clinical practice and retinal screening. Although the combination of multiple imaging techniques might overcome their individual weaknesses and provide comprehensive imaging, artificial intelligence in classifying multimodal images has not always produced accurate results.

Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naïve proliferative diabetic retinopathy.

PURPOSE: We investigated using ultrawide-field fundus images with a deep convolutional neural network (DCNN), which is a machine learning technology, to detect treatment-naïve proliferative diabetic retinopathy (PDR). METHODS: We conducted training with the DCNN using 378 photographic images (132 PDR and 246 non-PDR) and constructed a deep learning model. The area under the curve (AUC), sensitivity, and specificity were examined. RESULT: The constructed deep learning model demonstrated a high sensitivity of 94.7% and a high specificity of 97.2%, with an AUC of 0.969. CONCLUSION: Our findings suggested that PDR could be diagnosed using wide-angle camera images and deep learning.

Effects of kallidinogenase in patients undergoing vitrectomy for diabetic macular edema.

PURPOSE: To evaluate the effectiveness of the combination of vitrectomy with kallidinogenase for diabetic macular edema (DME). METHODS: This study was designed as a prospective, randomized, multicenter study comparing 19 eyes of 19 patients who received 150 units of kallidinogenase administered a day for 52 weeks from the day after vitrectomy (study group) with 20 eyes of 20 patients who received no kallidinogenase (control group). The main outcome measurements included logMAR visual acuity and central foveal thickness (CFT) before surgery and at 3, 6, 9, and 12 months after vitrectomy. RESULTS: During follow-up, 11 patients dropped out (six in the study group and five in the control group), leaving 28 eyes in 28 patients for analysis (13 in the study group and 15 in the control group). Visual acuity improved significantly at 12 months in both groups compared with before surgery. The degree of improvement did not differ significantly between the groups. At 12 months, the mean CFT decreased significantly in both groups, with no significant difference in the rate of change between the two groups. In the study group, the visual acuity and CFT significantly improved from 3 to 12 months and from 6 to 12 months, whereas these parameters did not continue to improve in the control group after 6 months (for visual acuity) or 3 months (for CFT). CONCLUSION: After vitrectomy for DME, visual acuity and CFT improved significantly in both groups, but only patients treated with kallidinogenase continued to have significant improvement throughout the study period.

Changes in choroidal thickness in patients with diabetic retinopathy.

PURPOSE: To investigate the changes in choroidal thickness (ChT) following panretinal photocoagulation (PRP) for diabetic retinopathy (DR) and compare ChT in relation to DR severity. METHODS: Thirty-two eyes [19 eyes with proliferative DR (PDR) and 13 eyes with severe nonproliferative DR (NPDR)] for which PRP was necessary were analyzed. ChT was measured before PRP and at 1, 3, and 6 months after PRP using the swept-source optical coherence tomography. ChT of the 61 eyes matched with the PDR patients for the mean age and axial length was also measured and statistically compared in relation to severity. RESULTS: The central field ChT before PRP treatment was 268.6 ± 104.5 µm (mean ± standard deviation) and was significantly decreased at 1, 3, and 6 months after PRP (254.5 ± 105.3, 254.2 ± 108.2, and 248.1 ± 101.8 µm, respectively, P < 0.0001). The central field ChT of severe NPDR (323.2 ± 61.3 µm) was significantly thicker than that of normal (248.3 ± 70.7 µm) and mild to moderate NPDR (230.0 ± 70.3 µm, P = 0.0455 and 0.0099, respectively). Moreover, the central field ChT of PDR (307.3 ± 84.1 µm) was significantly thicker than of mild to moderate NPDR (P = 0.0169). CONCLUSION: ChT significantly decreased after PRP, which continued for at least 6 months after treatment. ChT of severe NPDR and PDR was significantly thicker than that of mild to moderate NPDR. ChT of patients with DR was changed according to the treatment and severity of DR.

Correlation between optic nerve head circulation and visual function before and after anti-VEGF therapy for central retinal vein occlusion: prospective, interventional case series.

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 NUMBER: UMIN000009072. Date of registration: 10/15/2012.