scholarly journals RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shounak Datta ◽  
Eduardo B. Mariottoni ◽  
David Dov ◽  
Alessandro A. Jammal ◽  
Lawrence Carin ◽  
...  
Keyword(s):  
Visual Field ◽  
Optic Disc ◽  
Severe Disease ◽  
Nerve Fibers ◽  
Mean Deviation ◽  
Automated Perimetry ◽  
Standard Automated Perimetry ◽  
Fiber Layer ◽  
Floor Effect ◽  
Trade Offs

AbstractGlaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is most frequently used to detect visual loss due to glaucoma. Due to the SAP test’s innate difficulty and its high test-retest variability, we propose the RetiNerveNet, a deep convolutional recursive neural network for obtaining estimates of the SAP visual field. RetiNerveNet uses information from the more objective Spectral-Domain Optical Coherence Tomography (SDOCT). RetiNerveNet attempts to trace-back the arcuate convergence of the retinal nerve fibers, starting from the Retinal Nerve Fiber Layer (RNFL) thickness around the optic disc, to estimate individual age-corrected 24-2 SAP values. Recursive passes through the proposed network sequentially yield estimates of the visual locations progressively farther from the optic disc. While all the methods used for our experiments exhibit lower performance for the advanced disease group (possibly due to the “floor effect” for the SDOCT test), the proposed network is observed to be more accurate than all the baselines for estimating the individual visual field values. We further augment the proposed network to additionally predict the SAP Mean Deviation values and also facilitate the assignment of higher weightage to the underrepresented groups in the data. We then study the resulting performance trade-offs of the RetiNerveNet on the early, moderate and severe disease groups.

scholarly journals Estimating visual field loss from monoscopic optic disc photography using deep learning model

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Jinho Lee ◽  
Yong Woo Kim ◽  
Ahnul Ha ◽  
Young Kook Kim ◽  
Ki Ho Park ◽  
...  
Keyword(s):  
Deep Learning ◽  
Visual Field ◽  
Optic Disc ◽  
Correlation Coefficient ◽  
Characteristic Curve ◽  
Visual Field Loss ◽  
Absolute Error ◽  
Mean Deviation ◽  
Automated Perimetry ◽  
Standard Automated Perimetry

AbstractVisual 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.

scholarly journals Association between visual field damage and corneal structural parameters

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Alexandru Lavric ◽  
Valentin Popa ◽  
Hidenori Takahashi ◽  
Rossen M. Hazarbassanov ◽  
Siamak Yousefi
Keyword(s):  
Machine Learning ◽  
Visual Field ◽  
Structural Parameters ◽  
Corneal Thickness ◽  
Anterior Segment ◽  
Mean Deviation ◽  
Automated Perimetry ◽  
Standard Automated Perimetry ◽  
Visual Field Damage ◽  
Corneal Shape

AbstractThe main goal of this study is to identify the association between corneal shape, elevation, and thickness parameters and visual field damage using machine learning. A total of 676 eyes from 568 patients from the Jichi Medical University in Japan were included in this study. Corneal topography, pachymetry, and elevation images were obtained using anterior segment optical coherence tomography (OCT) and visual field tests were collected using standard automated perimetry with 24-2 Swedish Interactive Threshold Algorithm. The association between corneal structural parameters and visual field damage was investigated using machine learning and evaluated through tenfold cross-validation of the area under the receiver operating characteristic curves (AUC). The average mean deviation was − 8.0 dB and the average central corneal thickness (CCT) was 513.1 µm. Using ensemble machine learning bagged trees classifiers, we detected visual field abnormality from corneal parameters with an AUC of 0.83. Using a tree-based machine learning classifier, we detected four visual field severity levels from corneal parameters with an AUC of 0.74. Although CCT and corneal hysteresis have long been accepted as predictors of glaucoma development and future visual field loss, corneal shape and elevation parameters may also predict glaucoma-induced visual functional loss.

scholarly journals Topographic Quadrant Analysis of Peripapillary Superficial Microvasculature in Optic Disc Drusen

2021 ◽  
Vol 12 ◽  
Author(s):  
Yan Yan ◽  
Xiao Zhou ◽  
Zhongdi Chu ◽  
Laurel Stell ◽  
Mohammad Ali Shariati ◽  
...  
Keyword(s):  
Visual Field ◽  
Optic Disc ◽  
Function Analysis ◽  
Nerve Fibers ◽  
Quadrant Analysis ◽  
Mean Deviation ◽  
Structure Comparison ◽  
Parallel Change ◽  
Optic Disc Drusen ◽  
Temporal Quadrant

Background: Limited information is known about the topographic effect of optic disc drusen (ODD) on peripapillary retinal nerve fibers and microvasculature.Objective: This study aims to understand the structural and functional impact of ODD in different quadrants of the optic disc.Methods: We performed a retrospective case-control study of 22 ODD patients (34 eyes) and 26 controls (33 eyes) to compare optical coherence tomography (OCT) retinal nerve fiber layer (RNFL), OCT angiography (OCTA), and corresponding static perimetry mean deviation (MD) calculated using the modified Garway-Heath map in different quadrants of the optic disc. OCTA was analyzed using custom MATLAB script to measure six parameters in a peripapillary annulus with large vessel removal: vessel area density (VAD), vessel skeleton density (VSD), vessel perimeter index (VPI), vessel complexity index (VCI), flux, and vessel diameter index (VDI).Results: Quadrant analysis revealed that OCTA VAD and VCI were significantly decreased in superior, nasal, and inferior but not temporal quadrant. RNFL, VSD, and VPI were significantly impacted only in the superior and nasal quadrants. Corresponding visual field MDs in all ODD eyes were not different in the four quadrants, although eyes with MD equal or worse than −5 dB (32%) had worst visual field corresponding to the superior quadrant of the optic disc (inferior arcuate visual field). Structure-structure comparison of OCT and OCTA showed high correlation of RNFL with multiple OCTA measurements in the superior, nasal, and inferior quadrants but not temporal quadrant. Structure-function analysis revealed significant correlation of VAD and VCI and visual field MD in every quadrant, but RNFL was only significantly correlated in the superior and inferior quadrants.Conclusions: Peripapillary VAD and VCI are decreased in more quadrants than RNFL, supporting the clinical utility of performing OCTA in addition to OCT. Consistent with the most common locations of ODD, five OCT/OCTA measurements (VAD, VCI, RNFL, VSD, VPI) are decreased in the superior and nasal quadrants. OCT/OCTA measurements were significantly impacted in contrast to the relatively mild effect on corresponding visual field MD, consistent with the idea that a decrease in objective structural and vascular measurements occurs without parallel change in subjective visual function in ODD.

scholarly journals Estimating Rates of Progression and Predicting Future Visual Fields in Glaucoma Using a Deep Variational Autoencoder

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Samuel I. Berchuck ◽  
Sayan Mukherjee ◽  
Felipe A. Medeiros
Keyword(s):  
Visual Field ◽  
Learning Algorithm ◽  
Visual Fields ◽  
Visual Field Loss ◽  
Absolute Error ◽  
Rate Of Change ◽  
Mean Deviation ◽  
Automated Perimetry ◽  
Standard Automated Perimetry ◽  
Deep Learning Algorithm

AbstractIn this manuscript we develop a deep learning algorithm to improve estimation of rates of progression and prediction of future patterns of visual field loss in glaucoma. A generalized variational auto-encoder (VAE) was trained to learn a low-dimensional representation of standard automated perimetry (SAP) visual fields using 29,161 fields from 3,832 patients. The VAE was trained on a 90% sample of the data, with randomization at the patient level. Using the remaining 10%, rates of progression and predictions were generated, with comparisons to SAP mean deviation (MD) rates and point-wise (PW) regression predictions, respectively. The longitudinal rate of change through the VAE latent space (e.g., with eight dimensions) detected a significantly higher proportion of progression than MD at two (25% vs. 9%) and four (35% vs 15%) years from baseline. Early on, VAE improved prediction over PW, with significantly smaller mean absolute error in predicting the 4th, 6th and 8th visits from the first three (e.g., visit eight: VAE8: 5.14 dB vs. PW: 8.07 dB; P < 0.001). A deep VAE can be used for assessing both rates and trajectories of progression in glaucoma, with the additional benefit of being a generative technique capable of predicting future patterns of visual field damage.

scholarly journals Comparison of multifocal visual evoked potential, standard automated perimetry and optical coherence tomography in assessing visual pathway in multiple sclerosis patients

2010 ◽  
Vol 16 (4) ◽  
pp. 412-426 ◽  
Author(s):  
Michal Laron ◽  
Han Cheng ◽  
Bin Zhang ◽  
Jade S Schiffman ◽  
Rosa A Tang ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Optical Coherence Tomography ◽  
Mean Deviation ◽  
Automated Perimetry ◽  
Optical Coherence ◽  
Standard Automated Perimetry ◽  
Fiber Layer ◽  
Field Of Vision ◽  
Multiple Sclerosis Patients ◽  
Visual Evoked

Background: Multifocal visual evoked potentials (mfVEP) measure local response amplitude and latency in the field of vision. Objective: To compare the sensitivity of mfVEP, Humphrey visual field (HVF) and optical coherence tomography (OCT) in detecting visual abnormality in multiple sclerosis (MS) patients. Methods: mfVEP, HVF, and OCT (retinal nerve fiber layer [RNFL]) were performed in 47 MS-ON eyes (last optic neuritis [ON] attack ≥6 months prior) and 65 MS-no-ON eyes without ON history. Criteria to define an eye as abnormal were: (1) mfVEP amplitude/latency — either amplitude or latency probability plots meeting cluster criteria with 95% specificity; (2) mfVEP amplitude or latency alone (specificity: 97% and 98%, respectively); and (3) HVF and OCT, mean deviation and RNFL thickness meeting p < 0.05, respectively. Results: MfVEP (amplitude/latency) identified more abnormality in MS-ON eyes (89%) than HVF (72%), OCT (62%), mfVEP amplitude (66%) or latency (67%) alone. Eighteen percent of MS-no-ON eyes were abnormal for both mfVEP (amplitude/latency) and HVF compared with 8% with OCT. Agreement between tests ranged from 60% to 79%. mfVEP (amplitude/latency) categorized an additional 15% of MS-ON eyes as abnormal compared with HVF and OCT combined. Conclusions: mfVEP, which detects both demyelination (increased latency) and neural degeneration (reduced amplitude), revealed more abnormality than HVF or OCT in MS patients.

scholarly journals Glaucoma home-monitoring using a tablet-based visual field test (Eyecatcher): An assessment of accuracy and adherence over six months

2020 ◽  
Author(s):  
Pete R. Jones ◽  
Peter Campbell ◽  
Tamsin Callaghan ◽  
Lee Jones ◽  
Daniel S. Asfaw ◽  
...  
Keyword(s):  
Visual Field ◽  
Home Monitoring ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Mean Deviation ◽  
Test Duration ◽  
Automated Perimetry ◽  
Standard Automated Perimetry ◽  
Measurement Variability ◽  
Prospective Longitudinal

AbstractPurposeTo assess accuracy and adherence of visual field (VF) home-monitoring in a pilot sample of glaucoma patients.DesignProspective longitudinal observation.MethodsTwenty adults (median 71 years) with an established diagnosis of glaucoma were issued a tablet-perimeter (Eyecatcher), and were asked to perform one VF home-assessment per eye, per month, for 6 months (12 tests total). Before and after home-monitoring, two VF assessments were performed in-clinic using Standard Automated Perimetry (SAP; 4 tests total, per eye).ResultsAll 20 participants could perform monthly home-monitoring, though one participant stopped after 4 months (Adherence: 98%). There was good concordance between VFs measured at home and in the clinic (r = 0.94, P < 0.001). In 21 of 236 tests (9%) Mean Deviation deviated by more than ±3dB from the median. Many of these anomalous tests could be identified by applying machine learning techniques to recordings from the tablets’ front-facing camera (Area Under the ROC Curve = 0.78). Adding home-monitoring data to 2 SAP tests made 6 months apart reduced measurement error (between-test measurement variability) in 97% of eyes, with mean absolute error more than halving in 90% of eyes. Median test duration was 4.5mins (Quartiles: 3.9−5.2mins). Substantial variations in ambient illumination had no observable effect on VF measurements (r = 0.07, P = 0.320).ConclusionsHome-monitoring of VFs is viable for some patients, and may provide clinically useful data.

scholarly journals Influence of implantations of extended depth-of-focus on standard automated perimetry

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Jinhee Lee ◽  
Yosai Mori ◽  
Ryohei Nejima ◽  
Keiichiro Minami ◽  
Kazunori Miyata
Keyword(s):  
Visual Field ◽  
Cataract Surgery ◽  
Mean Deviation ◽  
Automated Perimetry ◽  
Depth Of Focus ◽  
Standard Automated Perimetry ◽  
Multifocal Iol ◽  
Reliability Indices ◽  
Extended Depth Of Focus ◽  
Foveal Sensitivity

AbstractThis prospective study aimed to investigate the influence of an extended depth-of-focus intraocular lens (EDOF IOL) on standard automated perimetry. Ninety eyes of 90 patients who had undergone cataract surgery from February 2018 to December 2018 were included. No patients had any diseases that might affect the visual field. ZMB00 (+ 4.00 D add), ZXR00V (+ 1.75 D add), and ZCB00V (Johnson & Johnson Surgical Vision, Santa Ana, CA, USA) were used as multifocal, EDOF, and monofocal IOLs, respectively. Humphrey Visual Field 10–2 testing was performed 2–3 months after cataract surgery, acceptable reliability indices were measured, and mean deviation (MD), pattern standard deviation (PSD), foveal sensitivity and mean sensitivity (MS) were compared. Seventy-one eyes (ZXR00V: 24 eyes, ZMB00: 25 eyes, ZCB00V: 22 eyes) were used for the analyses. The MD and MS of the EDOF and monofocal groups were significantly higher than those of the multifocal group (P < 0.0051). However, the MD and MS of the EDOF and monofocal groups were not different (P > 0.23). The PSD and foveal sensitivity were not different among the groups. In non-glaucomatous patients, the MD and MS of the EDOF IOL were comparable to those of the monofocal IOL and better than those of the multifocal IOL.

scholarly journals Factors Associated with Midterm Visual Field Variability in Patients with Stable Glaucoma

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Maria Emília V. Guimarães ◽  
Carolina P. B. Gracitelli ◽  
Syril Dorairaj ◽  
Fábio N. Kanadani ◽  
Tiago S. Prata
Keyword(s):  
Visual Field ◽  
Corneal Thickness ◽  
Mean Deviation ◽  
Eye Drops ◽  
Automated Perimetry ◽  
Standard Automated Perimetry ◽  
Factors Associated ◽  
Equivalent Number ◽  
Group 2 ◽  
Test Variability

Purpose. To evaluate factors associated with midterm visual field (VF) variability in stable glaucoma patients in Brazil. Methods. This retrospective observational study included 59 eyes of 39 stable glaucoma patients. Baseline data assessed were age, gender, educational level, intraocular pressure (IOP), central corneal thickness, best-corrected visual acuity, spherical equivalent, number of hypotensive eye drops, type of glaucoma, number of VFs performed, follow-up in years, lens status, visual field index (VFI) values from the last 5 VF (standard automated perimetry (SAP)) tests, the presence or absence of central scotoma in the VF test, and the level of glaucomatous damage according to the VF mean deviation (MD) index of the last VFs. The 5 latest VFI scores were used to calculate the mean, the standard deviation (SD), and the coefficient of variation (CV). We divided the eyes into 2 groups, being group 1 comprised by the 29 eyes presenting the lowest CV values and group 2 comprised by the 30 eyes presenting the highest CV values. GEE models were used to compare the CV and demographic and clinical parameters of all participants. Results. Mean age of all subjects was 65.8 ± 10.1 years. 54.0% were women. Average SAP MD values for groups 1 and 2 were −2.8 ± 3.1 dB and −6.2 ± 4.1 dB, respectively (P=0.006). Average SAP VFI values for groups 1 and 2 were 95.6 ± 5.9% and 85.9 ± 11.3%, respectively (P=0.002). There was a statistically significant association between CV and SAP MD values (P=0.006). A worse SAP MD and VFI were associated with a higher CV. In addition, even adjusting for potential confounding factors (age and level of education), the association between CV and the SAP MD and between CV and VFI remained significant (P≤0.010). Conclusion. Glaucomatous patients with worse VF sensitivity scores (both MD and VFI indices) present higher VF test variability.

scholarly journals Can Variability of Pattern ERG Signal Help to Detect Retinal Ganglion Cells Dysfunction in Glaucomatous Eyes?

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Alberto Mavilio ◽  
Francesca Scrimieri ◽  
Donato Errico
Keyword(s):  
Retinal Ganglion Cells ◽  
Ganglion Cells ◽  
Second Harmonic ◽  
Pattern Electroretinogram ◽  
Mean Deviation ◽  
Automated Perimetry ◽  
Pattern Erg ◽  
Retinal Ganglion ◽  
Standard Automated Perimetry ◽  
Fiber Layer

Objective. To evaluate variability of steady-state pattern electroretinogram (SS-PERG) signal in normal, suspected, and glaucomatous eyes.Methods. Twenty-one subjects with suspected glaucoma due to disc abnormalities (GS), 37 patients with early glaucoma (EG), and 24 normal control (NC) were tested with spectral-domain optical coherence tomography (SD-OCT), standard automated perimetry (SAP), and SS-PERG. Mean deviation (MD), pattern standard deviation (PSD), retinal nerve fiber layer (RNFL), and ganglionar complex cells (GCC) were evaluated. The SS-PERG was recorded five consecutive times and the amplitude and phase of second harmonic were measured. PERG amplitude and coefficient of variation of phase (CVphase) were recorded, and correlation with structural and functional parameters of disease, by means of one-way ANOVA and Pearson’s correlation, was analysed.Results. PERG amplitude was reduced, as expression of retinal ganglion cells (RGCs) dysfunction, in EG patients and GS subjects compared to NC patients (P<0.0001). CVphase was significantly increased in EG patients and GS subjects, compared to healthy (P<0.0001), and it was also correlated with PSD (P=0.0009), GCC (P=0.028), and RNFL (P=0.0078) only in EG patients.Conclusions. Increased intrasession variability of phase in suspected glaucomatous eyes may be a sign of RGCs dysfunction.

scholarly journals Standard automated perimetry using size III and size V stimuli in advanced stage glaucoma: an observational cross-sectional comparative study

BMJ Open ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. e046124
Author(s):  
Devindra Sood ◽  
Gabriela Czanner ◽  
Tobi Somerville ◽  
Ishaana Sood ◽  
Fiona J Rowe
Keyword(s):  
Visual Field ◽  
Mean Deviation ◽  
Test Duration ◽  
Automated Perimetry ◽  
Advanced Stage ◽  
Standard Automated Perimetry ◽  
Cross Sectional ◽  
Dynamic Strategy ◽  
Mean Sensitivity ◽  
Loss Variance

ObjectivesIn this study, we sought to evaluate the extent of further visual field that could be assessed when using stimulus size V in standard automated perimetry compared with size III in advanced stage glaucoma and whether cut-off values could be determined for when to switch from size III to size V.DesignProspective cross-sectional study.SettingSingle-centre outpatient eye clinic in India (New Delhi).ParticipantsAdvanced stage glaucoma defined as stages 3–4.InterventionCentral static perimetry with Octopus 900 G programme (size III stimulus dynamic strategy) and low vision central programme (size V stimulus dynamic strategy).Primary and secondary outcome measuresVisual field assessment for right and left eyes with both sizes III and V were undertaken within one clinic visit.ResultsWe recruited 126 patients (170 eyes). Mean patient age at assessment was 55.86 years (SD 15.15). Means (SD) for size III versus size V, respectively, were 6.94 dB (5.58) and 12.98 dB (7.77) for mean sensitivity, 20.02 dB (5.67) and 19.22 dB (7.74) for mean deviation, 5.89 dB (2.29) and 7.69 dB (2.78) for standard loss variance and 3.32 min (1.07) and 6.40 min (1.43) for test duration. All except mean deviation were significantly different between size III and V tests.ConclusionUseful visual field information was obtained with size V stimuli which allowed continued monitoring of these patients that was not possible with size III. Increased test duration, standard loss variance and mean sensitivity were found with size V, as expected, given that more visual responses were obtained with the increased target size. A switch from size III to V may be considered when mean sensitivity reaches 10 dB and/or mean deviation reaches 18 dB.

Sign in / Sign up

Export Citation Format

Share Document