Deep learning model to predict visual field in central 10° from optical coherence tomography measurement in glaucoma

2020 ◽  
pp. bjophthalmol-2019-315600
Author(s):  
Yohei Hashimoto ◽  
Ryo Asaoka ◽  
Taichi Kiwaki ◽  
Hiroki Sugiura ◽  
Shotaro Asano ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Visual Field ◽  
Retinal Pigment ◽  
Prediction Performance ◽  
Support Vector ◽  
Inner Plexiform Layer ◽  
Optical Coherence ◽  
Data Set ◽  
Sd Oct

Background/AimTo train and validate the prediction performance of the deep learning (DL) model to predict visual field (VF) in central 10° from spectral domain optical coherence tomography (SD-OCT).MethodsThis multicentre, cross-sectional study included paired Humphrey field analyser (HFA) 10-2 VF and SD-OCT measurements from 591 eyes of 347 patients with open-angle glaucoma (OAG) or normal subjects for the training data set. We trained a convolutional neural network (CNN) for predicting VF threshold (TH) sensitivity values from the thickness of the three macular layers: retinal nerve fibre layer, ganglion cell layer+inner plexiform layer and outer segment+retinal pigment epithelium. We implemented pattern-based regularisation on top of CNN to avoid overfitting. Using an external testing data set of 160 eyes of 131 patients with OAG, the prediction performance (absolute error (AE) and R2 between predicted and actual TH values) was calculated for (1) mean TH in whole VF and (2) each TH of 68 points. For comparison, we trained support vector machine (SVM) and multiple linear regression (MLR).ResultsAE of whole VF with CNN was 2.84±2.98 (mean±SD) dB, significantly smaller than those with SVM (5.65±5.12 dB) and MLR (6.96±5.38 dB) (all, p<0.001). Mean of point-wise mean AE with CNN was 5.47±3.05 dB, significantly smaller than those with SVM (7.96±4.63 dB) and MLR (11.71±4.15 dB) (all, p<0.001). R2 with CNN was 0.74 for the mean TH of whole VF, and 0.44±0.24 for the overall 68 points.ConclusionDL model showed considerably accurate prediction of HFA 10-2 VF from SD-OCT.

scholarly journals Early Detection of Incipient Retinal Pigment Epithelium Atrophy Overlying Drusen with Fundus Autofluorescence vs. Spectral Domain Optical Coherence Tomography

2020 ◽  
Vol 2020 ◽  
pp. 1-8 ◽  
Author(s):  
Anabel Rodríguez ◽  
Marc Biarnés ◽  
Rosa M. Coco-Martin ◽  
Anna Sala-Puigdollers ◽  
Jordi Monés
Keyword(s):  
Optical Coherence Tomography ◽  
Retinal Pigment Epithelium ◽  
Median Time ◽  
Pigment Epithelium ◽  
Fundus Autofluorescence ◽  
Retinal Pigment ◽  
Geographic Atrophy ◽  
Optical Coherence ◽  
Rpe Atrophy ◽  
Sd Oct

Purpose. This study aims to find out which tool, fundus autofluorescence (FAF) or spectral domain optical coherence tomography (SD-OCT), is more sensitive in detecting retinal pigment epithelium (RPE) demise overlying drusen and can, therefore, help predict geographic atrophy (GA) appearance in Age-Related Macular Degeneration (AMD). Methods. A single-site, retrospective, observational, longitudinal study was conducted. Patients with intermediate AMD (iAMD) (large (>125 μm) or intermediate (63–125 μm) drusen with hyper/hypopigmentation) with a minimum follow-up of 18 months were included. Drusen with overlying incipient RPE atrophy were identified on SD-OCT defined as choroidal hypertransmission or nascent geographic atrophy (nGA). These selected drusen were, then, traced backwards in time to determine if incipient RPE atrophy overlying drusen was observed on FAF (well-demarcated region of absence of autofluorescence) before, simultaneously, or after having detected the first signs of incipient RPE atrophy on SD-OCT. The number of drusen in which signs of incipient RPE atrophy was detected earlier using FAF or SD-OCT was compared. The time elapsed from the identification with the more sensitive method to the other was recorded and analyzed. Results. One hundred and thirty-three drusen in 22 eyes of 22 patients were included. Of these, 112 (84.2%) drusen showed choroidal hypertransmission and 21(15.8%) nGA. Early signs of atrophy overlying drusen were found simultaneously on SD-OCT and FAF in 52 cases (39.1%, 95% CI 30.8–47.9%), earliest on FAF in 51 (38.3%, 95% CI 30.0–47.2%) and first on SD-OCT in 30 (22.6%, 95% CI 15.8–30.6%; p<0.05). Statistically significant differences were found between both techniques (p=0.005), with FAF detecting it earlier than SD-OCT. When RPE atrophy was found first on FAF, the median time to diagnosis with SD-OCT was 6.6 months (95% CI 5.5 to 8.6), while if detection occurred earlier on SD-OCT, the median time until identification with FAF was 12.6 months (95% CI 6.0 to 23.4; p=0.0003). Conclusions. In iAMD cases in which early atrophy overlying drusen is not detected simultaneously in FAF and SD-OCT, FAF was significantly more sensitive. Nevertheless, a multimodal approach is recommended and required to evaluate these patients.

Discriminating glaucomatous and compressive optic neuropathy on spectral-domain optical coherence tomography with deep learning classifier

2020 ◽  
Vol 104 (12) ◽  
pp. 1717-1723 ◽  
Author(s):  
Jinho Lee ◽  
Jin-Soo Kim ◽  
Haeng Jin Lee ◽  
Seong-Joon Kim ◽  
Young Kook Kim ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Optic Neuropathy ◽  
Spectral Domain ◽  
Optical Coherence ◽  
Compressive Optic Neuropathy ◽  
Diagnostic Parameters ◽  
Learning Classifier ◽  
Oct Image ◽  
Sd Oct

Background/aimsTo assess the performance of a deep learning classifier for differentiation of glaucomatous optic neuropathy (GON) from compressive optic neuropathy (CON) based on ganglion cell–inner plexiform layer (GCIPL) and retinal nerve fibre layer (RNFL) spectral-domain optical coherence tomography (SD-OCT).MethodsEighty SD-OCT image sets from 80 eyes of 80 patients with GON along with 81 SD-OCT image sets from 54 eyes of 54 patients with CON were compiled for the study. The bottleneck features extracted from the GCIPL thickness map, GCIPL deviation map, RNFL thickness map and RNFL deviation map were used as predictors for the deep learning classifier. The area under the receiver operating characteristic curve (AUC) was calculated to validate the diagnostic performance. The AUC with the deep learning classifier was compared with those for conventional diagnostic parameters including temporal raphe sign, SD-OCT thickness profile and standard automated perimetry.ResultsThe deep learning system achieved an AUC of 0.990 (95% CI 0.982 to 0.999) with a sensitivity of 97.9% and a specificity of 92.6% in a fivefold cross-validation testing, which was significantly larger than the AUCs with the other parameters: 0.804 (95% CI 0.737 to 0.872) with temporal raphe sign, 0.815 (95% CI 0.734 to 0.896) with superonasal GCIPL and 0.776 (95% CI 0.691 to 0.860) with superior GCIPL thicknesses (all p<0.001).ConclusionThe deep learning classifier can outperform the conventional diagnostic parameters for discrimination of GON and CON on SD-OCT.

Evolution of retinal changes measured by optical coherence tomography in the assessment of hydroxychloroquine ocular safety in patients with systemic lupus erythematosus

Lupus ◽  
2019 ◽  
Vol 28 (4) ◽  
pp. 555-559 ◽  
Author(s):  
D Martín-Iglesias ◽  
J Artaraz ◽  
A Fonollosa ◽  
A Ugarte ◽  
A Arteagabeitia ◽  
...  
Keyword(s):  
Risk Factors ◽  
Optical Coherence Tomography ◽  
Lupus Erythematosus ◽  
Pigment Epithelium ◽  
Retinal Pigment ◽  
Optical Coherence ◽  
The Mean ◽  
Sd Oct

Objective The objective of this report is to analyse retinal changes over a five-year period, assessed by spectral domain-optical coherence tomography (SD-OCT), in patients from the Lupus-Cruces cohort treated with hydroxychloroquine (HCQ). Methods SD-OCT screening was performed annually between 2012 and 2017. Average macular thickness (AMT), ganglion cell layer thickness (GCLT) and qualitative data of retinal pigment epithelium (RPE) and external retina (ExtR) were collected prospectively. We compared data from 2012 (first) and 2017 (second) SD-OCT. Results We studied 110 patients and 195 eyes. No cases of HCQ toxicity were detected. At the time of the second SD-OCT, 99% patients had taken a daily dose of HCQ ≤5 mg/kg/day. The median time on HCQ was 133 months. The mean AMT and GCLT were significantly lower in both eyes at the second SD-OCT; however, all the differences were clinically insignificant at less than 1%. Qualitative analysis of RPE and ExtR showed no significant changes. Similar results were found among patients with risk factors for retinopathy. The comparison of patients with and without risk factors showed no differences. Conclusions This study shows clinically irrelevant retinal changes in an SLE cohort on HCQ treatment over a five-year follow-up. Our findings support the safety of long-term HCQ at doses ≤5 mg/kg/day.

scholarly journals Relationship between visual field changes and optical coherence tomography measurements in advanced open-angle glaucoma

Folia Medica ◽  
2016 ◽  
Vol 58 (3) ◽  
pp. 174-181 ◽  
Author(s):  
Snezhina S. Kostianeva ◽  
Marieta I. Konareva-Kostianeva ◽  
Marin A. Atanassov
Keyword(s):  
Optical Coherence Tomography ◽  
Visual Field ◽  
Structural Changes ◽  
Open Angle Glaucoma ◽  
Mean Deviation ◽  
Ganglion Cell Complex ◽  
Automated Perimetry ◽  
Optical Coherence ◽  
Open Angle ◽  
Sd Oct

Abstract Aim: To assess relationships between functional changes in visual field and structural changes in advanced open-angle glaucoma (OAG) found using spectral-domain optical coherence tomography (SD-OCT). Methods: Thirty-one eyes of 25 patients with OAG were included in this study. Besides the routine ophthalmological exam the patients underwent standard automated perimetry (SAP) (Humphrey Field Analyzer) and SD-OCT (RTVue–100) performed within 6 months. The global perimetric indices in the study group were as follows: mean deviation (MD) 12.33±6.18 dB and pattern standard deviation (PSD) 9.17±3.41 dB. The relationship between OCT measurements and MD and PSD was evaluated by correlation analysis (Pearson’s correlation coefficient) and regression analysis (linear and nonlinear regression models). Results: Thickness measurements of the lower halves of ganglion cell complex (GCC) and retinal nerve fiber layer by two scanning protocols (ONH and 3.45) showed these to be thinner than the upper halves, but the difference failed to reach statistical significance. The correlations between global indices MD/PSD and most of the analysed quantitative OCT measurements were moderate (r in the range between 0.3 and 0.6). The correlation between MD and GCC showed nonlinear cubic regression (R2=0.417, P=0.004). Good correlation was found between MD and GLV (R2=0.383; P=0.008). Linear regression (P<0.05) was found only between MD and Cup area (R2=0.175, P=0.024) and between MD and RNFL by 3.45 protocol (R2=0.131, P=0.045). Conclusion: Nonlinear regressive models appear to be more appropriate in the assessment of the correlations between functional and structural changes in eyes with advanced glaucoma. The correlations we found were moderate.

scholarly journals Low-Reflectivity Drusen With Overlying RPE Damage Revealed by Spectral-Domain OCT: Hint for the Development of Age-Related Macular Degeneration

2021 ◽  
Vol 8 ◽  
Author(s):  
Shasha Yang ◽  
Zongyin Gao ◽  
Haijiang Qiu ◽  
Chengguo Zuo ◽  
Lan Mi ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Macular Degeneration ◽  
Retinal Pigment ◽  
Morphological Characteristics ◽  
Age Related Macular Degeneration ◽  
Spectral Domain ◽  
Optical Coherence ◽  
Age Related ◽  
Sd Oct

Purpose: To observe the relationship between the characteristic changes in the drusen morphology revealed by the spectral-domain optical coherence tomography (SD-OCT) and the progression of age-related macular degeneration (AMD).Methods: A total of 380 drusen in 45 eyes in 35 patients with the intermediate drusen were longitudinally followed up every 6 months by SD-OCT for a period of 24 months. The drusen were divided into the dynamic group and stable group according to the following parameters: number, volume, concurrent retinal pigment epithelium (RPE)/ellipsoid zone (EZ) damage, and the development of advanced AMD. The morphological characteristics of the progressive or stable drusen were further analyzed. Odds ratios (ORs) and the risk for the drusen progression were calculated.Results: The level of interobserver and intraobserver agreement for each drusen tomographic morphological parameters ranged from 82.7 to 90%. At the end of an average follow-up of 15.92 ± 6.99 months, six patients developed choroidal neovascularization and no patients developed geographic atrophy. Finally, 139 drusen changed and 241 drusen remained stable. The drusen with low reflectivity (p &lt; 0.001; OR: 5.26; 95% CI: 2.24–12.36), non-homogeneity without a core (p &lt; 0.001; OR: 4.31; 95% CI: 2.08–8.92), RPE damage (p &lt; 0.001; OR: 28.12; 95% CI: 9.43–83.85), and the EZ damage (p &lt; 0.001; OR: 14.01; 95% CI: 5.28–37.18) were significantly associated with active change; the drusen with low reflectivity (p = 0.01; OR: 2.95; 95% CI: 1.29–6.75) and decreased overlying RPE reflectivity (p &lt; 0.001; OR: 21.67; 95% CI: 9.20–51.02) were the independent predictors for progression. The drusen with high reflectivity were significantly associated with stabilization (p = 0.03; OR: 0.17; 95% CI: 0.04–0.84).Conclusion: Spectral-domain optical coherence tomography is an optimized, accurate, and efficient method to follow-up the drusen. The intermediate non-exudative AMD prognosis of the patient was most strongly correlated with the drusen reflectivity and disruption of the overlying RPE layer. The drusen with low reflectivity and overlying RPE damage were more likely to progress and required frequent follow-up.

scholarly journals Early Detection of Mold-Contaminated Peanuts Using Machine Learning and Deep Features Based on Optical Coherence Tomography

2021 ◽  
Vol 3 (3) ◽  
pp. 703-715
Author(s):  
Edwin Manhando ◽  
Yang Zhou ◽  
Fenglin Wang
Keyword(s):  
Optical Coherence Tomography ◽  
Early Stage ◽  
Support Vector ◽  
Optical Coherence ◽  
Data Set ◽  
New Approach ◽  
Svm Model ◽  
Incubation Periods ◽  
Output Code ◽  
Oct Imaging

Fungal infection is a pre-harvest and post-harvest crisis for farmers of peanuts. In environments with temperatures around 28 °C to 30 °C or relative humidity of approximately 90%, mold-contaminated peanuts have a considerable likelihood to be infected with Aflatoxins. Aflatoxins are known to be highly carcinogenic, posing danger to humans and livestock. In this work, we proposed a new approach for detection of mold-contaminated peanuts at an early stage. The approach employs the optical coherence tomography (OCT) imaging technique and an error-correcting output code (ECOC) based Support Vector Machine (SVM) trained on features extracted using a pre-trained Deep Convolutional Neural Network (DCNN). To this end, mold-contaminated and uncontaminated peanuts were scanned to create a data set of OCT images used for training and evaluation of the ECOC-SVM model. Results showed that the proposed approach is capable of detecting mold-contaminated peanuts with respective accuracies of approximately 85% and 96% after incubation periods of 48 and 96 h.

Inner macular layer thickness by spectral domain optical coherence tomography in children and adults: a hospital-based study

2019 ◽  
Vol 103 (11) ◽  
pp. 1576-1583 ◽  
Author(s):  
Yung Ju Yoo ◽  
Jeong-Min Hwang ◽  
Hee Kyung Yang
Keyword(s):  
Optical Coherence Tomography ◽  
Layer Thickness ◽  
Male Gender ◽  
Spectral Domain ◽  
Retinal Layer ◽  
Inner Plexiform Layer ◽  
Optical Coherence ◽  
Korean Children ◽  
Factors Associated ◽  
Sd Oct

PurposeTo establish the normative ranges of macular ganglion cell layer (mGCL) and macular inner plexiform layer (mIPL) thickness using Spectralis spectral domain optical coherence tomography (SD-OCT) (Heidelberg Engineering, Inc., Heidelberg, Germany) in both Korean children and adults, and to determine factors associated with mGCL and mIPL thickness.MethodsWe conducted a retrospective, observational study of 573 healthy subjects (5–70 years old) who underwent comprehensive ophthalmic examinations in a single institution. Each inner retinal layer thickness was measured using SD-OCT and automatic segmentation software. Cross-sectional analysis was used to evaluate the effect of gender, age and ocular parameters on mGCL and mIPL thickness. Normative ranges of mGCL and mIPL thickness according to age, gender and factors associated with mGCL and mIPL thickness were measured.ResultsThe mean mGCL and mIPL thickness were 40.6±2.8 and 33.8±2.0 µm, respectively. Determinants of inner sector mGCL thickness were circumpapillary retinal nerve fibre layer (cpRNFL) thickness (β=1.172, p<0.001), age (β=−0.019, p=0.021) and male gender (β=1.452, p<0.001). Determinants of inner sector mIPL thickness were cpRNFL (β=0.952, p<0.001) and male gender (β=1.163, p<0.001). The inner sector mGCL and mIPL thickness increased significantly with age in children (β=0.174, p=0.009 and β=0.115, p=0.013), and then decreased in adults (β=−0.070, p<0.001 and β=−0.024, p=0.032). In the case of outer sectors, mGCL and mIPL thickness were not significantly related to age and gender.ConclusionsThis study ensured a normative range of the mGCL and mIPL thickness using Spectralis OCT. Gender, age and cpRNFL thickness significantly correlated with mGCL and mIPL thickness. This information should be considered in the interpretation of SD-OCT data.

scholarly journals Optical Coherence Tomography Angiography (OCT-A) in a Patient with Occult Retinal Dysfunction

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Juliana Wons ◽  
Jana Dinges ◽  
Matthias D. Becker ◽  
Stephan Michels
Keyword(s):  
Optical Coherence Tomography ◽  
Visual Field ◽  
Near Infrared ◽  
Infrared Imaging ◽  
Imaging Techniques ◽  
Visual Field Defects ◽  
Retinal Layer ◽  
Optical Coherence ◽  
Large Area ◽  
Sd Oct

Multimodal imaging techniques were performed in a patient with a newly emerged visual field defect; a missing retinal lesion on fundus examination made the diagnosis challenging but infrared imaging showed a larger area of retinal abnormality temporal to the fovea. Indocyanine green angiography (IA) showed late hypofluorescence and there was mild hyperautofluorescence which is known from acute zonal occult outer retinopathy (AZOOR). Despite normal fluorescein angiography (FA) results, a perfusion loss in the outer retinal layer was detected by OCT-A. Similar OCT-A findings were recently described in patients with acute macular neuroretinopathy (AMN). Methods. The methods included FA and IA, spectral domain optical coherence tomography (SD-OCT), near infrared imaging, and autofluorescence imaging (AF), as well as OCT-A. Patient. A 36-year-old patient who suffered from acute symptoms of photopsia and scotoma on her left eye. She had an influenza-like illness two weeks earlier. The scotoma could be verified by visual field testing. Results. The affected retinal zone showed mild fading of external limiting membrane (ELM) and a disorganisation of the ellipsoid zone (EZ) on SD-OCT. OCT-A revealed a large area of reduced perfusion in the outer retinal vascular layer. Conclusion. OCT-A can help to detect reduced capillary network in patients with visual field defects and no visible fundus changes. This case seems to have features of different occult retinal disorders such as AZOOR and AMN.

Deep Learning Estimation of 10-2 and 24-2 Visual Field Metrics based on Thickness Maps from Macula Optical Coherence Tomography

Ophthalmology ◽  
2021 ◽  
Author(s):  
Mark Christopher ◽  
Christopher Bowd ◽  
James A. Proudfoot ◽  
Akram Belghith ◽  
Michael H. Goldbaum ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Visual Field ◽  
Optical Coherence
Sign in / Sign up

Export Citation Format

Share Document