Developing new automated alternation flicker using optic disc photography for the detection of glaucoma progression.
Ontology highlight
ABSTRACT:
SUBMITTER: Ahn J
PROVIDER: S-EPMC5233931 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectivesTo evaluate the performance of a deep learning based Artificial Intelligence (AI) software for detection of glaucoma from stereoscopic optic disc photographs, and to compare this performance to the performance of a large cohort of ophthalmologists and optometrists.MethodsA retrospective study evaluating the diagnostic performance of an AI software (Pegasus v1.0, Visulytix Ltd., London UK) and comparing it with that of 243 European ophthalmologists and 208 British optometrists, as determined in previous studies, for the detection of glaucomatous optic neuropathy from 94 scanned stereoscopic photographic slides scanned into digital format.ResultsPegasus was able to detect glaucomatous optic neuropathy with an accuracy of 83.4% (95% CI: 77.5-89.2). This is comparable to an average ophthalmologist accuracy of 80.5% (95% CI: 67.2-93.8) and average optometrist accuracy of 80% (95% CI: 67-88) on the same images. In addition, the AI system had an intra-observer agreement (Cohen's Kappa, κ) of 0.74 (95% CI: 0.63-0.85), compared with 0.70 (range: -0.13-1.00; 95% CI: 0.67-0.73) and 0.71 (range: 0.08-1.00) for ophthalmologists and optometrists, respectively. There was no statistically significant difference between the performance of the deep learning system and ophthalmologists or optometrists.ConclusionThe AI system obtained a diagnostic performance and repeatability comparable to that of the ophthalmologists and optometrists. We conclude that deep learning based AI systems, such as Pegasus, demonstrate significant promise in the assisted detection of glaucomatous optic neuropathy.
| S-EPMC7002599 | biostudies-literature
Project description:PurposeTo compare the diagnostic performance of automated imaging for glaucoma.DesignProspective, direct comparison study.ParticipantsAdults with suspected glaucoma or ocular hypertension referred to hospital eye services in the United Kingdom.MethodsWe evaluated 4 automated imaging test algorithms: the Heidelberg Retinal Tomography (HRT; Heidelberg Engineering, Heidelberg, Germany) glaucoma probability score (GPS), the HRT Moorfields regression analysis (MRA), scanning laser polarimetry (GDx enhanced corneal compensation; Glaucoma Diagnostics (GDx), Carl Zeiss Meditec, Dublin, CA) nerve fiber indicator (NFI), and Spectralis optical coherence tomography (OCT; Heidelberg Engineering) retinal nerve fiber layer (RNFL) classification. We defined abnormal tests as an automated classification of outside normal limits for HRT and OCT or NFI ≥ 56 (GDx). We conducted a sensitivity analysis, using borderline abnormal image classifications. The reference standard was clinical diagnosis by a masked glaucoma expert including standardized clinical assessment and automated perimetry. We analyzed 1 eye per patient (the one with more advanced disease). We also evaluated the performance according to severity and using a combination of 2 technologies.Main outcome measuresSensitivity and specificity, likelihood ratios, diagnostic, odds ratio, and proportion of indeterminate tests.ResultsWe recruited 955 participants, and 943 were included in the analysis. The average age was 60.5 years (standard deviation, 13.8 years); 51.1% were women. Glaucoma was diagnosed in at least 1 eye in 16.8%; 32% of participants had no glaucoma-related findings. The HRT MRA had the highest sensitivity (87.0%; 95% confidence interval [CI], 80.2%-92.1%), but lowest specificity (63.9%; 95% CI, 60.2%-67.4%); GDx had the lowest sensitivity (35.1%; 95% CI, 27.0%-43.8%), but the highest specificity (97.2%; 95% CI, 95.6%-98.3%). The HRT GPS sensitivity was 81.5% (95% CI, 73.9%-87.6%), and specificity was 67.7% (95% CI, 64.2%-71.2%); OCT sensitivity was 76.9% (95% CI, 69.2%-83.4%), and specificity was 78.5% (95% CI, 75.4%-81.4%). Including only eyes with severe glaucoma, sensitivity increased: HRT MRA, HRT GPS, and OCT would miss 5% of eyes, and GDx would miss 21% of eyes. A combination of 2 different tests did not improve the accuracy substantially.ConclusionsAutomated imaging technologies can aid clinicians in diagnosing glaucoma, but may not replace current strategies because they can miss some cases of severe glaucoma.
| S-EPMC4846823 | biostudies-literature
Project description:Optic-disc photography (ODP) has proven to be very useful for optic nerve evaluation in glaucoma. In real clinical practice, however, limited patient cooperation, small pupils, or media opacities can limit the performance of ODP. The purpose of this study was to propose a deep-learning approach for increased resolution and improved legibility of ODP by contrast, color, and brightness compensation. Each high-resolution original ODP was transformed into two counterparts: (1) down-scaled 'low-resolution ODPs', and (2) 'compensated high-resolution ODPs' produced via enhancement of the visibility of the optic disc margin and surrounding retinal vessels using a customized image post-processing algorithm. Then, the differences between these two counterparts were directly learned through a super-resolution generative adversarial network (SR-GAN). Finally, by inputting the high-resolution ODPs into SR-GAN, 4-times-up-scaled and overall-color-and-brightness-transformed 'enhanced ODPs' could be obtained. General ophthalmologists were instructed (1) to assess each ODP's image quality, and (2) to note any abnormal findings, at 1-month intervals. The image quality score for the enhanced ODPs was significantly higher than that for the original ODP, and the overall optic disc hemorrhage (DH)-detection accuracy was significantly higher with the enhanced ODPs. We expect that this novel deep-learning approach will be applied to various types of ophthalmic images.
| S-EPMC7529226 | biostudies-literature
Project description:PurposeTo present a digital image subtraction technique to alert clinicians to signs of glaucomatous optic disc progression.MethodsNinety-two glaucomatous eyes (65 patients) were included. Thirty-three eyes were identified as progressive and 59 as stable based on comparison of baseline and follow-up stereoscopic disc photographs by three masked glaucoma specialists. The disc images were aligned and converted to gray scale and underwent histogram matching to enhance contrast and account for illumination differences. The difference in image intensity between baseline and follow-up images was shown as a colormap superimposed on the grayscale follow-up image. A graded scale (1, no progression, to 5, definitive progression) was used by three masked glaucoma experts to score progression probability on the colormap images. Sensitivity, specificity, and accuracy of the classification were computed. Weighted κ statistics summarized agreement of categorical gradings.ResultsMedian time interval between two visits was 4.4 years (range: 1.0-16.8). Clinicians detected glaucoma deterioration in 25 to 27 of the progressive group and 8 to 10 of stable eyes based on subtraction maps. Sensitivities/specificities of the clinicians were 0.76 to 0.82 and 0.86 to 0.89, respectively. Classification accuracy ranged from 81.5% to 84.8%. Agreement among clinicians was good (weighted κ = 0.68; 95% confidence interval [CI]: 0.60-0.77) for progression grades (1-5 scales) and was substantial (weighted κ = 0.81; 95% CI: 0.74-0.85) for binary scores.ConclusionsThe proposed software provides a single static image that clinicians can use with other structural/functional tests to detect glaucoma progression.Translational relevanceProvision of a subtraction colormap in the setting of electronic medical records can improve monitoring of glaucoma by alerting clinicians to possible signs of progression.
| S-EPMC5661381 | biostudies-literature
Project description:To investigate optic disc hemorrhage (DH)'s clinical implications to subsequent progression of primary open-angle glaucoma (POAG) in cases of mild-to-moderate myopia.Retrospective comparative study.(1) Fifty-nine (59) myopic (26.5 mm > axial length [AXL] ? 24.0 mm) POAG patients with DH and (2) 59 age-, AXL-, and mean deviation (MD) of visual field (VF)-matched controls without DH were evaluated over the course of a minimum 3.5 years of follow up. For clear assessment of the effect of DH on progression of glaucoma, the patients selected for inclusion in the study were those with stable IOP (i.e., those showing an at least 20% reduction relative to the baseline IOP) whose IOP-lowering medication was not increased, supplemented or changed during the follow-up period.The patients' optic disc/retinal nerve fiber layer (RNFL) photographs were independently evaluated by three glaucoma specialists for structural progression of glaucoma. Event-based analysis with Guided Progression Analysis (GPA) software was used to determine their functional progression. The durations of structural and functional progression were compared by Kaplan-Meier life survival analyses.Optic disc/RNFL progression and VF progression.The mean follow-up periods between the DH and non-DH groups were not significantly different: in the DH group, 5.6±2.7 years; in the non-DH group, 5.4±2.6 years (P = 0.588). In the DH group, 30 (50.8%) of 59 eyes manifested optic disc/RNFL deterioration; in the non-DH group, however, only 17 (28.8%) of 59 eyes showed structural progression. For the DH group, the cumulative probability of structural glaucoma progression was significantly greater than for the non-DH group (P = 0.001; log rank test). Interestingly, the two groups did not significantly differ in the cumulative probability of functional progression (P = 0.79; log rank test): in the DH group, VF progression was observed in 14 eyes (23.7%); in the non-DH group, in 12 eyes (20.3%).DH was associated with a greater probability of structural progression in medically well-controlled-IOP POAG eyes with mild-to-moderate myopia. However, the relevance of DH to VF progression was not clear over the course of the average 5.5-year duration of the study.
| S-EPMC5734762 | biostudies-literature
Project description:Visual field assessment is recognized as the important criterion of glaucomatous damage judgement; however, it can show large test-retest variability. We developed a deep learning (DL) algorithm that quantitatively predicts mean deviation (MD) of standard automated perimetry (SAP) from monoscopic optic disc photographs (ODPs). A total of 1200 image pairs (ODPs and SAP results) for 563 eyes of 327 participants were enrolled. A DL model was built by combining a pre-trained DL network and subsequently trained fully connected layers. The correlation coefficient and mean absolute error (MAE) between the predicted and measured MDs were calculated. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the detection ability for glaucomatous visual field (VF) loss. The data were split into training/validation (1000 images) and testing (200 images) sets to evaluate the performance of the algorithm. The predicted MD showed a strong correlation and good agreement with the actual MD (correlation coefficient = 0.755; R2 = 57.0%; MAE = 1.94 dB). The model also accurately predicted the presence of glaucomatous VF loss (AUC 0.953). The DL algorithm showed great feasibility for prediction of MD and detection of glaucomatous functional loss from ODPs.
| S-EPMC7712913 | biostudies-literature
Project description:PURPOSE:To evaluate the relationship between pattern electroretinogram (PERG) and optic disc morphology in glaucoma suspect and glaucoma. METHODS:Eighty-six eyes of glaucoma suspect and 145 eyes of manifest glaucoma subjects were included in this study. Average peripapillary retinal nerve fiber layer (RNFL) thickness was obtained with spectral-domain optical coherence tomography, and optic disc imaging was performed using the Heidelberg Retinal Tomograph (HRT). Visual function was evaluated with perimetry (SITA and frequency doubling technology) and PERG. Scatter plots and correlation coefficients were evaluated between visual function and RNFL thickness or optic disc structure. RESULTS:Scatter plots of PERG and perimetry according to RNFL thickness change showed that PERG started to decrease earlier than did perimetry. The differences between linear and logarithmic R2 were largest for the scatter plot of SITA 24-2 (linear R2 = 0.415; logarithmic R2 = 0.443) and the smallest for P50 amplitude of PERG (linear R2 = 0.136, logarithmic R2 = 0.138). In glaucoma suspect, HRT parameters such as cup shape measure (CSM) and linear cup-disc ratio (CDR) had significant correlations with PERG amplitudes (P = 0.016 for P50 and 0.049 for N95 in CSM, P = 0.012 for P50 in CDR). However, in glaucoma patients, mean RNFL thickness was associated with PERG amplitude (P = 0.011 for P50 and 0.002 for N95). CONCLUSIONS:PERG deterioration occurred earlier than did perimetry according to RNFL thickness decrease. PERG amplitudes were significantly correlated with disc morphology in glaucoma suspect. These results suggest that PERG can detect ganglion cell dysfunction before the cells die.
| S-EPMC6837750 | biostudies-literature
Project description:PurposeThe influence of myopia on glaucoma progression remains unknown, possibly because of the multifactorial nature of glaucoma and difficulty in assessing a solo contribution of myopia. The purpose of this study is to investigate the association of myopia with visual field (VF) progression in glaucoma using a paired-eye design to minimize the influence of confounding systemic factors that are diverse among individuals.MethodsThis retrospective study evaluated 144 eyes of 72 subjects with open-angle glaucoma, with similar intra-ocular pressure between paired eyes, spherical equivalent (SE) ≤ -2 diopter (D), and axial length ≥ 24 mm. Paired eyes with faster and slower VF progression were grouped separately, according to the global VF progression rate assessed by automated pointwise linear regression analysis. The SE, axial length, tilt ratio and torsion angle of optic discs, Bruch's membrane (BM) opening area, and gamma zone parapapillary atrophy (PPA) width were compared between the two groups. Factors associated with faster VF progression were determined by logistic regression analysis.ResultsThe mean follow-up duration was 8.9 ± 4.4 years. The mean value of SE and axial length were -6.31 ± 1.88 D and 26.05 ± 1.12 mm, respectively. The mean global visual field progression rate was -0.32 ± 0.38 dB/y. Tilt ratio, BM opening area, and gamma zone PPA width were significantly greater in the eyes with faster VF progression than those with slower progression. In multivariate analysis, these factors were significantly associated with faster VF progression (all P < 0.05), while SE and axial length were not associated with it.ConclusionIn myopic glaucoma subjects, tilt of the optic disc and temporal shifting and enlargement of the BM opening were associated with faster rate of VF progression between paired eyes. This suggests that myopia influences VF progression in glaucomatous eyes via optic disc deformations rather than via refractive error itself.
| S-EPMC5256995 | biostudies-literature
Project description:PURPOSE:To quantify the variability of 5 glaucoma specialists' optic disc margin (DM), rim margin (RM), and rim width (RW) estimates. DESIGN:Inter-observer reliability analysis. METHODS:Clinicians viewed stereo-photographs from 214 subjects with glaucoma or ocular hypertension and digitally marked the DM and RM. For each photograph, the centroid of each clinician's DM was calculated, and an averaged DMcentroid was determined. The axis between the DMcentroid and the fovea was used to establish 12 30-degree sectors. Measurements from the DMcentroid to each clinician's DM (DMradius) and RM (RMradius) were used to generate a RW (DMradius-RMradius) and cup-to-disc ratio (CDR) (RMradius/DMradius) by sector. Parameter means, standard deviations, and coefficient of variations (COVs) were calculated across all clinicians for each eye. Parameter means for each clinician, and intraclass correlation coefficients (ICC), were calculated across all eyes by sector. RESULTS:Among all eyes, the median COV by sector ranged from 3% to 5% for DMradius, 20% to 25% for RMradius, and 26% to 30% for RW. Sectoral ICCs for CDR ranged from 0.566 to 0.668. Sectors suspicious for rim thinning by 1 clinician were frequently overlooked by others. Among 1724 sectors in which at least 1 clinician was suspicious for rim thinning (CDR ≥ 0.7), all 5 clinicians' CDRs were ≥ 0.7 in only 499 (29%), and 2 of the 5 clinicians failed to detect rim thinning (CDR < 0.7) in 442 (26%). CONCLUSION:In this study, glaucoma specialist RM, DM, and RW discordance was frequent and substantial, even in sectors that were suspicious for rim thinning.
| S-EPMC6064671 | biostudies-literature
Project description:The Glaucoma Stereo Analysis Study (GSAS) is a multicenter collaborative study of the characteristics of glaucomatous optic disc morphology using a stereo fundus camera. This study evaluated the retinal vessel calibers and correlations using GSAS fundus photographs between retinal vessels and 38 optic nerve head (ONH) morphologic parameters comprehensively. In all 240 eyes, the mean central retinal arteriolar equivalent (CRAE) and central retinal venular equivalent (CRVE) were 138.4 and 216.5 μm, respectively; the CRAE correlated with age, visual field scores and 19 ONH parameters and CRVE correlated with age, intraocular pressure, visual field scores and 11 ONH parameters. Among the different optic disc appearances including focal ischemia (FI) (n = 53, 22%), generalized enlargement (GE) (n = 53, 22%), myopic glaucoma (MY) (n = 112, 47%), and senile sclerosis (SS) (n = 22, 9%), the CRAE did not differ significantly; CRVE was significantly narrower in SS than in FI and MY. In FI, GE, MY, and SS disc types, CRAE correlated with 3, 14, 9, and 2 ONH parameters, respectively, and CRVE corelated with 9, 0, 12, and 6 ONH parameters, respectively. We confirmed previous observations on the effect of retinal vessel narrowing on glaucomatous changes in the ONH and visual field. The associations between retinal vessel caliber and ONH morphologic parameters vary among different optic disc appearances, suggesting different effects of vascular changes in each disc type.
| S-EPMC8320981 | biostudies-literature