Faculty Bibliography

Purpose : Current GPU memory limitations do not support the analysis of OCT scans at its original resolution, and previous techniques have downsampled the inputs considerably which resulted in a loss of detail. Here, we utilise a new memory management support framework that allows for the training of large deep learning networks and apply it to the detection of glaucoma in OCT scans at its original resolution. Methods : A total of 1110 SDOCT volumes (Cirrus, Zeiss, CA) were acquired from both eyes of 624 subjects (139 healthy and 485 glaucomatous patients (POAG)). A convolutional neural network (CNN) consisting of 8 3D-convolutional layers with a total of 600K parameters and was trained using a cross-entropy loss to differentiate between the healthy and glaucomatous scans. To avoid GPU memory constraints, the network was trained using a large model support library that automatically adds swap-in and swap-out nodes for transferring tensors from GPUs to the host and vice versa. This allowed for the OCT scans to be analysed at the original resolution of 200x200x1024. The performance of the network was gauged by computing the area under the receiver operating characteristic (AUC) curve. The performance of this network was also compared to a previously proposed network that ingested downsampled OCT scans (50x50x128), consisted of 5 3D-convolutional layers and had a total of 222K parameters; and a machine-learning technique (random forests) that relied on segmented features (peripapillary nerve fibre thicknesses). Class activation maps (CAM) were also generated for each of these networks to provide a qualitative view of the regions that the network deemed as important and relevant to the task. Results : The AUCs computed on the test set for the networks that analysed the volumes at the original and downsampled resolutions was found to be 0.92 and 0.91, respectively. The CAMs obtained using the high resolution images show more detail in comparison to the downsampled volume. The random forest technique showed an AUC of 0.85. Conclusions : The performance of the two networks was comparable for glaucoma detection but showed a vast improvement over the random forest that relied on segmented features. The ability to retain detail (as shown in the CAM) will likely allow for improvements in other tasks, such as spatial correspondences between visual field test locations and retinal structure

Purpose : Development and pre-clinical testing of glaucoma neurotherapeutics have been obfuscated by limited experimental models that provide chronic elevation of intraocular pressure (IOP) while preserving optical media clarity for structural and functional assessments over time. In this study, we developed an in vivo model system involving the use of non-invasive tonometry, optical coherence tomography (OCT) and optokinetics to characterize retinal integrity and visual behavior in a novel hydrogel-induced chronic IOP elevation model. Methods : Six adult C57BL/6J mice underwent unilateral intracameral injection of an optically clear, chemically cross-linked hydrogel composed of hyaluronic acid functionalized with vinyl sulfone and thiol groups. IOP was measured with a rebound tonometer at baseline and 1, 3, 7, 10 and 14 days after hydrogel injection. The optic nerve head (ONH) region was scanned for each eye using OCT at baseline and 2 weeks after injection, and total retinal thickness (TRT) was measured within a 0.26-0.36 mm radius ring centered on the ONH using custom-written software (Fig 1). Visual acuity (VA) was measured for each eye using an optokinetic virtual-reality system at baseline and 2 weeks after injection. Data are presented as mean+/-SEM. Results : Intracameral hydrogel injection resulted in mild-to-moderate IOP elevation throughout the 2-week experimental period (Fig 2a). TRT in the hydrogel-injected eye was 10.06+/-3.61% thinner at 2 weeks post-injection compared to baseline (p<0.01) (Fig 2b). IOP elevation also led to a decline in VA by 58.12+/-7.22% at 2 weeks post-injection compared to baseline (p<0.001) (Fig 2c). Interestingly, among the hydrogel-injected eyes, cumulative IOP measured from 0 to 14 days post-injection did not correlate with TRT or VA (p>0.05) (Fig 2d-e), whereas TRT was positively associated with VA at 2 weeks post-injection (r=0.824, p<0.05) (Fig 2f). No significant change in IOP, TRT or VA was found in the non-injected eye. Conclusions : An in vivo glaucoma model system was developed that showed a positive correlation between retinal thinning and visual behavioral deficits after chronic IOP elevation. The weak association between cumulative IOP and TRT or VA suggests additional factors apart from IOP level in contributing to glaucomatous damage after chronic IOP elevation

Purpose : The presence of s zone peripapillary atrophy (PPA) has been associated with glaucoma. We performed a retrospective longitudinal study to evaluate s zone PPA area as a predictor for glaucomatous structural and functional progression. Methods : Subjects with glaucoma and >4 visits were included. Subjects had Humphrey visual field (Zeiss, Dublin, CA) testing, spectral-domain OCT (Cirrus HD-OCT; Zeiss) optic nerve head (ONH) and macula scans. s zone PPA was manually delineated on the baseline en face ONH scan as the area contiguous with the optic disc with the presence of hyper-and hyporeflectivity. Mixed effects linear models accounting for intra-subject correlation, follow-up time, scan's signal strength and ethnicity, were performed to determine if baseline PPA area was associated with glaucoma severity. Subsequent models incorporating the interaction term between time and baseline PPA area were performed to determine if baseline PPA area affected the rate of change in parameters of glaucoma over time. Results : 81 eyes (56 subjects) aged 62.8+/-14.1 years with an average follow-up time 3.9+/-1.3 years were analyzed. PPA was significantly associated with mean deviation (MD), visual field index (VFI), and inferior retinal nerve fiber layer (RNFL), (p=0.033, 0.038, and 0.034, respectively), but not with average RNFL, or macular ganglion cell inner plexiform layer (GCIPL) global and sectoral measurements and ONH parameters. No significant association was detected between s zone PPA area and the rate of progression for any parameter except for VFI (p =0.035). Conclusions : Although baseline s zone PPA area is associated with some indicators of glaucoma severity, it is not a significant predictor of the rate of glaucomatous progression (except for VFI)

Purpose : To compare the discrimination accuracy for glaucoma diagnosis using the OCT RNFL clock hours compared with average RNFL. Methods : In a large, ongoing, longitudinal cohort of healthy subjects and subjects with glaucoma, all subjects underwent visual field (VF) and OCT testing. Principal component (PC) analysis was used to reduce the dimensionality of clock hour measurements while maintaining maximum information variability for diagnostic performance. The first four PCs with linear regression were used as predictors of VF mean deviation (MD) and to classify glaucoma diagnosis. The prediction accuracy and discrimination power using cross validation were compared to the models using only average RNFL as a predictor. All models were adjusted for age, signal strength, and intra-subject correlation. Results : 1317 healthy and glaucomatous eyes (717 subjects) were included in the study. A PC analysis was built on the 9 clock hours while excluding non-informative sectors (clock hours 3, 4, and 9). The first PC explained 51% of the total variance, and the first four PCs explained 82% of the total variance and thus were used for subsequent regression models. A PC regression for glaucoma discrimination showed that clock hours 1, 5, 6, 7, 10, 11, 12 were significantly association with diagnosis. The PC showed better glaucoma diagnosis performance compared to average RNFL, with 10-fold cross-validation AUCs of 0.898 and 0.877, respectively (p<0.001). The PC regression for MD improved the model fit measured by R² by 9% compared to a regression using average RNFL. PC showed that clock hours 2, 5, 6, 7, 10, 11, 12 were significantly associated with MD. Conclusions : Using PCs with RNFL clock hours improved classification performance for glaucoma diagnosis and model fit for MD, compared to using average RNFL. This method improves discrimination performance by both considering all sectoral RNFL information and removing locations with low diagnostic yield

PURPOSE: Congenital retinal macrovessels are large aberrant retinal blood vessels that cross the horizontal raphe and can traverse the central macula. Using multimodal imaging and optical coherence tomography angiography, we describe 2 cases of congenital retinal macrovessel associated with macroaneurysms. METHODS: Two patients presented for evaluation and were found to have congenital retinal macrovessels associated with macroaneurysms. Color photography, optical coherence tomography, fundus autofluorescence fluorescein angiography, and optical coherence tomography angiography were performed and used to establish the diagnosis and monitor resolution at follow-up visits. RESULTS: The first patient presented with central vision loss in the right eye and was noted to have a ruptured macroaneurysm and scattered microaneurysms along the course of a venous macrovessel. After 3 months of observation, the patient's vision improved. The second patient presented for evaluation of a cataract in her left eye and was incidentally found to have an arterial macrovessel in her right eye with an associated macroaneurysm. Both cases demonstrated an intricate capillary network in the central macula best visualized on optical coherence tomography angiography. CONCLUSION: Macroaneurysms can occur on both arterial and venous macrovessels. After rupture of these lesions, hemorrhage and exudation can resolve with observation alone. Macrovessels can also present with microaneurysms. Optical coherence tomography angiography can effectively image the complex capillary network associated with these vascular anomalies.

Purpose : To develop a method for monitoring the functional deterioration of glaucoma patents using structural surrogates, we used machine learning algorithms to estimate visual field index (VFI) from OCT scans, and evaluated the accuracy of the progression rates calculated from the estimated VFI. Methods : Macular and ONH SDOCT scans (Cirrus HD-OCT, Zeiss, Dublin, CA; 200x200x1024 samplings over 6x6x2mm, downsampled to 64x64x128 voxels) were acquired from both eyes of 1,678 healthy participants, glaucoma suspects, and glaucoma patients over multiple visits (range: 1-14, median=3), forming a dataset of 10,172 pairs of macular+ONH scans. Automated perimetry (Humphrey visual field, SITA 24-2) tests were administered at each visit. Two models were trained to estimate the measured VFI from a pair of macular and ONH scans: the first ("classic model") was a non-linear regression model (multi-layer perceptron) based on 47 thickness measures of retinal layers, while the other ("CNN") was a 5-layer convolutional neural network, trained to learn 3D features in the OCT scans. For both models, MSE was minimized in 5-fold cross-validation, using 80%:10%:10% of the dataset as training, validation and test sets. Data from the same participant were not split across the three sets. For data in the test sets, VFI's for eyes with more than N=3,4,5 visits were estimated for individual visits, and the slopes were calculated using linear regression across N consecutive visits. Median absolute error (MAE) was used to quantify estimation accuracy. Results : For estimating VFI at single visits, the CNN achieved significant lower MAE (2.6+/-0.28; mean and s.d.) than the classic model (2.9+/-0.45). For estimating slopes across 5 visits, the MAE of the CNN (0.73+/-0.12/year) was also lower than the classic model (0.82+/-0.23/year). The errors depended on the measured VFI of the first visit, and on the true slope (Fig. 1). Increasing the number of visits decreased the errors (N=3.6, MAE=1.38/yr, 0.99/yr, 0.73/yr, and 0.63yr) Conclusions : The feature-agnostic CNN was better at estimating VFI and visual field progression rates than the regression method based on thickness measures. Structure-tofunction estimation using neural networks is a promising method for monitoring the visual functions of glaucoma patients

Purpose : Oxygen concentration in retinal blood vessels (sO ) can be critical biomarkers for diabetic retinopathy and glaucoma, leading causes of blindness worldwide. We previously demonstrated sO2measurements in rodent and human retinas with spectroscopic visible-light optical coherence tomography (vis-OCT). However, reliable measurements of sO2in a clinical setting remains an open challenge due to constraints on light exposure, imaging time, patient motion, and variation in eye geometry. Spectral calibration to optimize sO2measurements under these non-ideal imaging conditions is needed. Here, we investigate, develop, and implement such calibration. Methods : We developed vis-OCT processing software to optimize sO2measurements in humans. First, we identified an optimal spectral range for spectral measurement in which sO2was most stable. Next, we developed methods to account for alterations induced by the imaging system and eye optics. Specifically, we accounted for depth-dependent variations in the measured spectrum, such as absorption contrast, spectrally-dependent roll-off, chromatic aberrations, and eye morphology. We then imaged the retinas of 12 healthy subjects aged 22 to 60 at Northwestern Medical Hospital in Chicago, IL, and Langone Medical Center in New York, NY. All imaging was approved by the respective IRBs and strictly adhered to the Declaration of Helsinki. Light exposure in the eye was no higher than 250 muW and imaging time was no longer than 5 s. We extracted sO2from vessels larger than 50 mum in diameter using an automated version of our vis-OCT processing software. Results : We measured the sO2in 89 vessels (53 arteries and 36 veins). We found the mean sO2in arteries was 97.70 +/-4.75 % in arteries and mean sO2in veins was 53.11 +/-6.85 %. Conclusions : We developed analytical methods for depth-dependent alterations to the measured spectrum in vis-OCT retinal oximetry. Our measurements yielded spectra that are highly consistent with those reported in literature, despite variations in imaging conditions. Our results indicate a clear path forward for clinical adoption of vis-OCT

Purpose: The purpose of the present study was to quantify test-retest reproducibili-ty of measurements of stiffness of the human trabecular meshwork (HTM) by atomic force microscopy (AFM).
Method(s): Eleven 40 mum radial limbal cryostat sections from a fresh human donor rim were mounted on charged slides and rehydrated at room temperature. Stiffness at four TM locations (anterior to posterior along Schlemm's canal) was measured by AFM. At each location, a 6 x 6 grid was sampled. Indentation points were evenly distributed over a 20 mum x 20 mum area, with a rate of one load/unload cycle per second. Measurements were then repeated for calculation of test-retest variability.
Result(s): The test-retest coefficients of variation for the four measurement locations (anterior to posterior) were 24.39, 25.28, 12.74, and 14.26%, respectively, with a notable drop in the two posterior locations compared to the anterior. The test-retest coefficient for the sections was 19.17%. For the entire eye, the test-retest coefficient of variation for the measurement of the TM stiffness was 17.13%. Young's moduli consistently decreased from anterior to posterior location.
Conclusion(s): Wide regional variation suggests that single value does little to fully describe the complex array of TM stiffness levels within the eye, and future studies of TM stiffness assessed by AFM should include multiple tissue samples from each eye, with documentation of the anterior-posterior location of each measurement.
Copyright

Purpose : In mild glaucoma, RNFL thinning and visual field (VF) loss are often localized, but structure-function modeling is impeded by variability due to individual eye anatomy. We perform high-resolution spatial correlations of RNFLT maps for each VF location to identify relevant areas and study further improvements by geometrically aligning RNFLT maps based on artery trajectories. Methods : In 419 SITA Standard 24-2 Humphrey VFs with at most mild glaucoma (mean deviation >=-3dB) with accompanying circumpapillary Cirrus HD-OCT RNFLT maps, we computed pixel-wise correlations (52 VF locations x 40401 pixels). We then performed an alignment operation, ensuring that the two major retinal arteries follow the same lines in all scans. We piecewise linearly approximated the trajectories of the arteries on 4 concentric circles around ONH (Fig. 1a), determined the necessary rotation for each pixel, and morphed the images accordingly (Fig. 1b). Results : For the pre-alignment RNFLT (correlation maps Fig. 2 top) we observed: (1) relatively high correlations (max 0.29); (2) most of the high-correlation regions are highly localized around the median trajectories of the major arteries at most VF locations, possibly due to the stacked character of the fiber bundles close to ONH, which impedes precise spatial mapping to the VF. This observation suggests general retinal vulnerability zones rather than highly VF location-specific areas as assumed by many previous structure-function models. Accordingly, morphing the RNFLT maps by aligning the eyespecific artery locations increased the maximal correlations on 25 of the 52 VF locations (Fig. 2 bottom, marked in green), particularly in nasal and inferior VF, with improvements of up to 0.1 (inferior arcuate region of VF). At many locations, aligned vulnerability areas become substantially more conspicuous (e.g. the location enlarged on the top left) and might have been missed without aligning. Conclusions : High-resolution structure-function correlations reveal retinal vulnerability zones in mild glaucoma. At many VF locations, these zones become better correlated with VF regions when RNFLT maps are aligned along the arteries. Specific attention to RNFL thinning in these zones in glaucoma suspects may improve the detection of initial VF loss glaucoma

Purpose : Predicting progression of primary open angle glaucoma (POAG) continues to be a challenge. Recent studies have shown that macular parameters may predict glaucoma progression and disease onset equally as well or even better than the traditionally used optic nerve head (ONH) retinal nerve fiber layer (RNFL) thickness. We performed a retrospective longitudinal study to identify structural parameters which best predicted visual field (VF) loss. Methods : Subjects with POAG with at least 5 qualified Cirrus OCT (Zeiss, Dublin, CA) macular and optic nerve head (ONH) scans and 5 qualified 24-2 Humphrey VF tests (Zeiss) were enrolled to this study. All parameters from the OCT's report of the macula and ONH scans were used in the analysis. We identified subjects who were OCT ONH progressors or VF progressors using both event and trend based definitions of progression based on the Guided Progression Analyses. Students t-test was used to assess differences in baseline characteristics between groups, and mixed-effects model was used in longitudinal analysis to compare the rate of parameter change between groups. Results : 263 eyes (180 subjects) with a mean follow-up time of 2.4+/-1.8 years were included in the study. Twenty-three eyes were identified as ONH progressors, 25 eyes were identified as VF progressors, and of these, 6 eyes were both VF and ONH progressors. At baseline, only macular average RNFL and macular inferior RNFL were significantly thinner in ONH progressors compared to non-progressors. Between the VF progressors and non-progressor groups, all OCT parameters were significantly thinner at baseline in the progressors except for four focal macular measurements and disc area. Mixed-effects modeling showed that both focal macular and ONH parameters thinned at a significantly greater rate in VF progressors compared to non-progressors (Table 1). Conclusions : Focal macular retinal segmentations and focal ONH parameters thin significantly more per year in VF progressors, and VF progressors tend to have thinner baseline structural parameters