Faculty Bibliography

Optical coherence tomography (OCT) images of the retina are a powerful tool for diagnosing and monitoring eye disease. However, they are plagued by speckle noise, which reduces image quality and reliability of assessment. This paper introduces a novel speckle reduction method inspired by the recent successes of deep learning in medical imaging. We present two versions of the network to reflect the needs and preferences of different end-users. Specifically, we train a convolution neural network to denoise cross-sections from OCT volumes of healthy eyes using either (1) mean-squared error, or (2) a generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. We then interrogate the success of both methods with extensive quantitative and qualitative metrics on cross-sections from both healthy and glaucomatous eyes. The results show that the former approach provides state-of-the-art improvement in quantitative metrics such as PSNR and SSIM, and aids layer segmentation. However, the latter approach, which puts more weight on visual perception, outperformed for qualitative comparisons based on accuracy, clarity, and personal preference. Overall, our results demonstrate the effectiveness and efficiency of a deep learning approach to denoising OCT images, while maintaining subtle details in the images.

PURPOSE/OBJECTIVE:To evaluate the ability of OCT optic nerve head (ONH) and macular parameters to detect disease progression in eyes with advanced structural glaucomatous damage of the circumpapillary retinal nerve fiber layer (cRNFL). DESIGN/METHODS:Longitudinal study. PARTICIPANTS/METHODS:Forty-four eyes from 37 patients with advanced average cRNFL damage (≤60 μm) followed up for an average of 4.0 years. METHODS:All patients were examined with spectral-domain OCT and visual field (VF) assessment during at least 4 visits. MAIN OUTCOME MEASUREMENTS/METHODS:Visual field mean deviation (MD) and VF index. OCT cRNFL (average, superior, and inferior quadrants), ganglion cell-inner plexiform layer (GCIPL) (average, superior, and inferior), rim area, cup volume, average cup-to-disc (C:D) ratio, and vertical C:D ratio. RESULTS:/year). CONCLUSIONS:Macula GCIPL and ONH parameters may be useful in tracking progression in patients with advanced glaucoma.

PURPOSE/OBJECTIVE:Previously, we introduced a state-based 2-dimensional continuous-time hidden Markov model (2D CT HMM) to model the pattern of detected glaucoma changes using structural and functional information simultaneously. The purpose of this study was to evaluate the detected glaucoma change prediction performance of the model in a real clinical setting using a retrospective longitudinal dataset. DESIGN/METHODS:Longitudinal, retrospective study. PARTICIPANTS/METHODS:One hundred thirty-four eyes from 134 participants diagnosed with glaucoma or as glaucoma suspects (average follow-up, 4.4±1.2 years; average number of visits, 7.1±1.8). METHODS:A 2D CT HMM model was trained using OCT (Cirrus HD-OCT; Zeiss, Dublin, CA) average circumpapillary retinal nerve fiber layer (cRNFL) thickness and visual field index (VFI) or mean deviation (MD; Humphrey Field Analyzer; Zeiss). The model was trained using a subset of the data (107 of 134 eyes [80%]) including all visits except for the last visit, which was used to test the prediction performance (training set). Additionally, the remaining 27 eyes were used for secondary performance testing as an independent group (validation set). The 2D CT HMM predicts 1 of 4 possible detected state changes based on 1 input state. MAIN OUTCOME MEASURES/METHODS:Prediction accuracy was assessed as the percentage of correct prediction against the patient's actual recorded state. In addition, deviations of the predicted long-term detected change paths from the actual detected change paths were measured. RESULTS:Baseline mean ± standard deviation age was 61.9±11.4 years, VFI was 90.7±17.4, MD was -3.50±6.04 dB, and cRNFL thickness was 74.9±12.2 μm. The accuracy of detected glaucoma change prediction using the training set was comparable with the validation set (57.0% and 68.0%, respectively). Prediction deviation from the actual detected change path showed stability throughout patient follow-up. CONCLUSIONS:The 2D CT HMM demonstrated promising prediction performance in detecting glaucoma change performance in a simulated clinical setting using an independent cohort. The 2D CT HMM allows information from just 1 visit to predict at least 5 subsequent visits with similar performance.

Glaucoma is the second leading cause of blindness world-wide. Despite active research efforts driven by the importance of diagnosis and treatment of the optic degenerative neuropathy, the relationship between structural and functional changes along the glaucomateous evolution are still not clearly understood. Dynamic changes of the lamina cribrosa (LC) in the presence of intraocular pressure (IOP) were suggested to play a significant role in optic nerve damage, which motivates the proposed research to explore the relationship of changes of the 3D structure of the LC collagen meshwork to clinical diagnosis. We introduce a framework to quantify 3D dynamic morphological changes of the LC under acute IOP changes in a series of swept-source optical coherence tomography (SS-OCT) scans taken under different pressure states. Analysis of SS-OCT images faces challenges due to low signal-to-noise ratio, anisotropic resolution, and observation variability caused by subject and ocular motions. We adapt unbiased diffeomorphic atlas building which serves multiple purposes critical for this analysis. Analysis of deformation fields yields desired global and local information on pressure-induced geometric changes. Deformation variability, estimated with repeated images of a healthy volunteer without IOP elevation, is found to be a magnitude smaller than pressure-induced changes and thus illustrates feasibility of the proposed framework. Results in a clinical study with healthy, glaucoma suspect, and glaucoma subjects demonstrate the potential of the proposed method for non-invasive in vivo analysis of LC dynamics, potentially leading to early prediction and diagnosis of glaucoma.

Purpose/UNASSIGNED:To determine if inner retinal layer reflectivity in eyes with acute central retinal vein occlusion (CRVO) correlates with visual acuity at 12 months. Methods/UNASSIGNED:Macular optical coherence tomography (OCT) scans were obtained from 22 eyes of 22 patients with acute CRVO. Optical intensity ratios (OIRs), defined as the mean OCT reflectivity of the inner retinal layers normalized to the mean reflectivity of the RPE, were measured from the presenting and 1-month OCT image by both manual measurements of grayscale B-scans and custom algorithmic measurement of raw OCT volume data. OIRs were assessed for association with final visual outcome. Cohort subgroup division for analysis was determined statistically. Results/UNASSIGNED:Eyes with poorer final visual acuity (≥20/70) at 1 year were more likely to have a higher ganglion cell layer OIR than eyes with better final visual acuity (<20/70) at 1 month (manually: 0.591 to 0.735, P = 0.006, algorithmically: 0.663 to 0.799, P = 0.014). At 1 month, eyes with a poorer final visual acuity demonstrated a higher variance of OIR measurements (algorithmically: 0.087 vs. 0.160, P = 0.002) per scan than eyes with better final visual acuity. Conclusions/UNASSIGNED:In acute CRVO, ganglion cell layer changes at 1 month, including increased reflectivity and increased heterogeneity of reflectivity signal as expressed as OIR and OIR variance, were associated with a poorer visual prognosis at 1 year. Technique calibration with larger sample sizes and automated integration into OCT platforms will be necessary to determine if OIR can be a clinically useful prognostic tool.