QUANTITATIVE ASSESSMENT OF AUTOMATED OPTICAL COHERENCE TOMOGRAPHY IMAGE ANALYSIS USING A HOME-BASED DEVICE FOR SELF-MONITORING NEOVASCULAR AGE-RELATED MACULAR DEGENERATION.

PURPOSE: To evaluate a prototype home optical coherence tomography device and automated analysis software for detection and quantification of retinal fluid relative to manual human grading in a cohort of patients with neovascular age-related macular degeneration. METHODS: Patients undergoing anti-vascular endothelial growth factor therapy were enrolled in this prospective observational study. In 136 optical coherence tomography scans from 70 patients using the prototype home optical coherence tomography device, fluid segmentation was performed using automated analysis software and compared with manual gradings across all retinal fluid types using receiver-operating characteristic curves. The Dice similarity coefficient was used to assess the accuracy of segmentations, and correlation of fluid areas quantified end point agreement. RESULTS: Fluid detection per B-scan had area under the receiver-operating characteristic curves of 0.95, 0.97, and 0.98 for intraretinal fluid, subretinal fluid, and subretinal pigment epithelium fluid, respectively. On a per volume basis, the values for intraretinal fluid, subretinal fluid, and subretinal pigment epithelium fluid were 0.997, 0.998, and 0.998, respectively. The average Dice similarity coefficient values across all B-scans were 0.64, 0.73, and 0.74, and the coefficients of determination were 0.81, 0.93, and 0.97 for intraretinal fluid, subretinal fluid, and subretinal pigment epithelium fluid, respectively. CONCLUSION: Home optical coherence tomography device images assessed using the automated analysis software showed excellent agreement to manual human grading.

Changes in macular layers in the early course of non-arteritic ischaemic optic neuropathy.

PURPOSE: To characterise the changes of the retinal layers in patients with acute anterior ischaemic optic neuropathy (AION), aiming to identify imaging markers for predicting the residual visual function. METHODS: This was a retrospective review of consecutive patients with unilateral AION from January 2010 to December 2013. We analysed affected eyes at baseline and 1 month later, compared to fellow healthy eyes. Utilising novel image analysis software, we conducted algorithmic segmentation in layers and division in early treatment of diabetic retinopathy study (ETDRS) quadrants of optical coherence tomography images of the macula. Pearson product moment regression analysis of retinal layer thickness and best corrected visual acuity (BCVA) in logMAR units and mean deviation of the SITA 24-2 visual field (VF) were carried out at the 1-month time point. RESULTS: Twenty eyes from 20 patients were included and compared to 20 healthy fellow eyes. At baseline, we found a significantly increased mean thickness of the retinal nerve fibre layer (RNFL) of 42.2 µm (±6.7SD) in AION eyes compared to 37.9 µm (±4.2 SD) in healthy eyes (p = 0.002). The outer nuclear layer (ONL) was also significantly thickened at 96.6 µm (±7.2 SD) compared to 90.8 µm (±5.7 SD) in the fellow eye (p < 0.001). After 1 month, the RNFL and the ganglion cell layer (GCL) were thinned 17.7 % [to 31.2 µm (±6.4 SD), p < 0.001] and 19.3 % [to 66.5 µm (±7.0 SD), p < 0.001] compared to the contralateral eye. Additionally, the ONL remained thickened at 96.7 µm (±7.0 SD, p < 0.001). At baseline, we found a significant correlation between the ONL thickness and the VF (r = -0.482, p = 0.005) and the BCVA at discharge (r = 0.552, p < 0.001), indicating that a thicker ONL correlates with poorer visual function. The GCL thickness also correlates with the BCVA at discharge (r = 0.411, p = 0.02), where a thinner GCL predicts worse BCVA. At the 1-month time point, the GCL thinning was correlated with both the VF (r = 0.471, p = 0.005) and the BCVA (r = -0.456, p = 0.007), indicating worse visual function. CONCLUSIONS: Changes in the thickness of different layers of the retina occur early in the course of AION and evolve over time, resulting in the atrophy of the GCL and RNFL. ONL thickening at baseline is associated with visual dysfunction. Thinning of the GCL after 1 month correlates with poorer VF and BCVA at 1 month after acute AION.

Loss of corneal sensory nerve fibers in SIV-infected macaques: an alternate approach to investigate HIV-induced PNS damage.

Peripheral neuropathy is the most frequent neurological complication of HIV infection, affecting more than one-third of infected patients, including patients treated with antiretroviral therapy. Although emerging noninvasive techniques for corneal nerve assessments are increasingly being used to diagnose and monitor peripheral neuropathies, corneal nerve alterations have not been characterized in HIV. Here, to determine whether SIV infection leads to corneal nerve fiber loss, we immunostained corneas for the nerve fiber marker ßIII tubulin. We developed and applied both manual and automated methods to measure nerves in the corneal subbasal plexus. These counting methods independently indicated significantly lower subbasal corneal nerve fiber density among SIV-infected animals that rapidly progressed to AIDS compared with slow progressors. Concomitant with decreased corneal nerve fiber density, rapid progressors had increased levels of SIV RNA and CD68-positive macrophages and expression of glial fibrillary acidic protein by glial satellite cells in the trigeminal ganglia, the location of the neuronal cell bodies of corneal sensory nerve fibers. In addition, corneal nerve fiber density was directly correlated with epidermal nerve fiber length. These findings indicate that corneal nerve assessment has great potential to diagnose and monitor HIV-induced peripheral neuropathy and to set the stage for introducing noninvasive techniques to measure corneal nerve fiber density in HIV clinical settings.

Deep-learning based automated quantification of critical optical coherence tomography features in neovascular age-related macular degeneration.

PURPOSE: To validate a deep learning algorithm for automated intraretinal fluid (IRF), subretinal fluid (SRF) and neovascular pigment epithelium detachment (nPED) segmentations in neovascular age-related macular degeneration (nAMD). METHODS: In this IRB-approved study, optical coherence tomography (OCT) data from 50 patients (50 eyes) with exudative nAMD were retrospectively analysed. Two models, A1 and A2, were created based on gradings from two masked readers, R1 and R2. Area under the curve (AUC) values gauged detection performance, and quantification between readers and models was evaluated using Dice and correlation (R2) coefficients. RESULTS: The deep learning-based algorithms had high accuracies for all fluid types between all models and readers: per B-scan IRF AUCs were 0.953, 0.932, 0.990, 0.942 for comparisons A1-R1, A1-R2, A2-R1 and A2-R2, respectively; SRF AUCs were 0.984, 0.974, 0.987, 0.979; and nPED AUCs were 0.963, 0.969, 0.961 and 0.966. Similarly, the R2 coefficients for IRF were 0.973, 0.974, 0.889 and 0.973; SRF were 0.928, 0.964, 0.965 and 0.998; and nPED were 0.908, 0.952, 0.839 and 0.905. The Dice coefficients for IRF averaged 0.702, 0.667, 0.649 and 0.631; for SRF were 0.699, 0.651, 0.692 and 0.701; and for nPED were 0.636, 0.703, 0.719 and 0.775. In an inter-observer comparison between manual readers R1 and R2, the R2 coefficient was 0.968 for IRF, 0.960 for SRF, and 0.906 for nPED, with Dice coefficients of 0.692, 0.660 and 0.784 for the same features. CONCLUSIONS: Our deep learning-based method applied on nAMD can segment critical OCT features with performance akin to manual grading.

Validation of a deep learning model for automatic detection and quantification of five OCT critical retinal features associated with neovascular age-related macular degeneration.

PURPOSE: To develop and validate a deep learning model for the segmentation of five retinal biomarkers associated with neovascular age-related macular degeneration (nAMD). METHODS: 300 optical coherence tomography volumes from subject eyes with nAMD were collected. Images were manually segmented for the presence of five crucial nAMD features: intraretinal fluid, subretinal fluid, subretinal hyperreflective material, drusen/drusenoid pigment epithelium detachment (PED) and neovascular PED. A deep learning architecture based on a U-Net was trained to perform automatic segmentation of these retinal biomarkers and evaluated on the sequestered data. The main outcome measures were receiver operating characteristic curves for detection, summarised using the area under the curves (AUCs) both on a per slice and per volume basis, correlation score, enface topography overlap (reported as two-dimensional (2D) correlation score) and Dice coefficients. RESULTS: The model obtained a mean (±SD) AUC of 0.93 (±0.04) per slice and 0.88 (±0.07) per volume for fluid detection. The correlation score (R2) between automatic and manual segmentation obtained by the model resulted in a mean (±SD) of 0.89 (±0.05). The mean (±SD) 2D correlation score was 0.69 (±0.04). The mean (±SD) Dice score resulted in 0.61 (±0.10). CONCLUSIONS: We present a fully automated segmentation model for five features related to nAMD that performs at the level of experienced graders. The application of this model will open opportunities for the study of morphological changes and treatment efficacy in real-world settings. Furthermore, it can facilitate structured reporting in the clinic and reduce subjectivity in clinicians' assessments.

Optical coherence tomography segmentation reveals ganglion cell layer pathology after optic neuritis.

Post-mortem ganglion cell dropout has been observed in multiple sclerosis; however, longitudinal in vivo assessment of retinal neuronal layers following acute optic neuritis remains largely unexplored. Peripapillary retinal nerve fibre layer thickness, measured by optical coherence tomography, has been proposed as an outcome measure in studies of neuroprotective agents in multiple sclerosis, yet potential swelling during the acute stages of optic neuritis may confound baseline measurements. The objective of this study was to ascertain whether patients with multiple sclerosis or neuromyelitis optica develop retinal neuronal layer pathology following acute optic neuritis, and to systematically characterize such changes in vivo over time. Spectral domain optical coherence tomography imaging, including automated retinal layer segmentation, was performed serially in 20 participants during the acute phase of optic neuritis, and again 3 and 6 months later. Imaging was performed cross-sectionally in 98 multiple sclerosis participants, 22 neuromyelitis optica participants and 72 healthy controls. Neuronal thinning was observed in the ganglion cell layer of eyes affected by acute optic neuritis 3 and 6 months after onset (P < 0.001). Baseline ganglion cell layer thicknesses did not demonstrate swelling when compared with contralateral unaffected eyes, whereas peripapillary retinal nerve fibre layer oedema was observed in affected eyes (P = 0.008) and subsequently thinned over the course of this study. Ganglion cell layer thickness was lower in both participants with multiple sclerosis and participants with neuromyelitis optica, with and without a history of optic neuritis, when compared with healthy controls (P < 0.001) and correlated with visual function. Of all patient groups investigated, those with neuromyelitis optica and a history of optic neuritis exhibited the greatest reduction in ganglion cell layer thickness. Results from our in vivo longitudinal study demonstrate retinal neuronal layer thinning following acute optic neuritis, corroborating the hypothesis that axonal injury may cause neuronal pathology in multiple sclerosis. Further, these data provide evidence of subclinical disease activity, in both participants with multiple sclerosis and with neuromyelitis optica without a history of optic neuritis, a disease in which subclinical disease activity has not been widely appreciated. No pathology was seen in the inner or outer nuclear layers of eyes with optic neuritis, suggesting that retrograde degeneration after optic neuritis may not extend into the deeper retinal layers. The subsequent thinning of the ganglion cell layer following acute optic neuritis, in the absence of evidence of baseline swelling, suggests the potential utility of quantitative optical coherence tomography retinal layer segmentation to monitor neuroprotective effects of novel agents in therapeutic trials.

Scrybe: A Secure Audit Trail for Clinical Trial Data Fusion.

Clinical trials are a multi-billion dollar industry. One of the biggest challenges facing the clinical trial research community is satisfying Part 11 of Title 21 of the Code of Federal Regulations [7] and ISO 27789 [40]. These controls provide audit requirements that guarantee the reliability of the data contained in the electronic records. Context-aware smart devices and wearable IoT devices have become increasingly common in clinical trials. Electronic Data Capture (EDC) and Clinical Data Management Systems (CDMS) do not currently address the new challenges introduced using these devices. The healthcare digital threat landscape is continually evolving, and the prevalence of sensor fusion and wearable devices compounds the growing attack surface. We propose Scrybe, a permissioned blockchain, to store proof of clinical trial data provenance. We illustrate how Scrybe addresses each control and the limitations of the Ethereum-based blockchains. Finally, we provide a proof-of-concept integration with REDCap to show tamper resistance.

Primary retinal pathology in multiple sclerosis as detected by optical coherence tomography.

Optical coherence tomography studies in multiple sclerosis have primarily focused on evaluation of the retinal nerve fibre layer. The aetiology of retinal changes in multiple sclerosis is thought to be secondary to optic nerve demyelination. The objective of this study was to use optical coherence tomography to determine if a subset of patients with multiple sclerosis exhibit primary retinal neuronopathy, in the absence of retrograde degeneration of the retinal nerve fibre layer and to ascertain if such patients may have any distinguishing clinical characteristics. We identified 50 patients with multiple sclerosis with predominantly macular thinning (normal retinal nerve fibre-layer thickness with average macular thickness < 5th percentile), a previously undescribed optical coherence tomography defined phenotype in multiple sclerosis, and compared them with 48 patients with multiple sclerosis with normal optical coherence tomography findings, 48 patients with multiple sclerosis with abnormal optical coherence tomography findings (typical for multiple sclerosis) and 86 healthy controls. Utilizing a novel retinal segmentation protocol, we found that those with predominant macular thinning had significant thinning of both the inner and outer nuclear layers, when compared with other patients with multiple sclerosis (P < 0.001 for both), with relative sparing of the ganglion cell layer. Inner and outer nuclear layer thicknesses in patients with non-macular thinning predominant multiple sclerosis were not different from healthy controls. Segmentation analyses thereby demonstrated extensive deeper disruption of retinal architecture in this subtype than may be expected due to retrograde degeneration from either typical clinical or sub-clinical optic neuropathy. Functional corroboration of retinal dysfunction was provided through multi-focal electroretinography in a subset of such patients. These findings support the possibility of primary retinal pathology in a subset of patients with multiple sclerosis. Multiple sclerosis-severity scores were also significantly increased in patients with the macular thinning predominant phenotype, compared with those without this phenotype (n = 96, P=0.006). We have identified a unique subset of patients with multiple sclerosis in whom there appears to be disproportionate thinning of the inner and outer nuclear layers, which may be occurring as a primary process independent of optic nerve pathology. In vivo analyses of retinal layers in multiple sclerosis have not been previously performed, and structural demonstration of pathology in the deeper retinal layers, such as the outer nuclear layer, has not been previously described in multiple sclerosis. Patients with inner and outer nuclear layer pathology have more rapid disability progression and thus retinal neuronal pathology may be a harbinger of a more aggressive form of multiple sclerosis.

Proof-of-Concept Analysis of a Deep Learning Model to Conduct Automated Segmentation of OCT Images for Macular Hole Volume.

BACKGROUND AND OBJECTIVE: To determine whether an automated artificial intelligence (AI) model could assess macular hole (MH) volume on swept-source optical coherence tomography (OCT) images. PATIENTS AND METHODS: This was a proof-of-concept consecutive case series. Patients with an idiopathic full-thickness MH undergoing pars plana vitrectomy surgery with 1 year of follow-up were considered for inclusion. MHs were manually graded by a vitreoretinal surgeon from preoperative OCT images to delineate MH volume. This information was used to train a fully three-dimensional convolutional neural network for automatic segmentation. The main outcome was the correlation of manual MH volume to automated volume segmentation. RESULTS: The correlation between manual and automated MH volume was R2 = 0.94 (n = 24). Automated MH volume demonstrated a higher correlation to change in visual acuity from preoperative to the postoperative 1-year time point compared with the minimum linear diameter (volume: R2 = 0.53; minimum linear diameter: R2 = 0.39). CONCLUSION: MH automated volume segmentation on OCT imaging demonstrated high correlation to manual MH volume measurements. [Ophthalmic Surg Lasers Imaging Retina. 2022;53(4):208-214.].

Utilization of deep learning to quantify fluid volume of neovascular age-related macular degeneration patients based on swept-source OCT imaging: The ONTARIO study.

PURPOSE: To evaluate the predictive ability of a deep learning-based algorithm to determine long-term best-corrected distance visual acuity (BCVA) outcomes in neovascular age-related macular degeneration (nARMD) patients using baseline swept-source optical coherence tomography (SS-OCT) and OCT-angiography (OCT-A) data. METHODS: In this phase IV, retrospective, proof of concept, single center study, SS-OCT data from 17 previously treated nARMD eyes was used to assess retinal layer thicknesses, as well as quantify intraretinal fluid (IRF), subretinal fluid (SRF), and serous pigment epithelium detachments (PEDs) using a novel deep learning-based, macular fluid segmentation algorithm. Baseline OCT and OCT-A morphological features and fluid measurements were correlated using the Pearson correlation coefficient (PCC) to changes in BCVA from baseline to week 52. RESULTS: Total retinal fluid (IRF, SRF and PED) volume at baseline had the strongest correlation to improvement in BCVA at month 12 (PCC = 0.652, p = 0.005). Fluid was subsequently sub-categorized into IRF, SRF and PED, with PED volume having the next highest correlation (PCC = 0.648, p = 0.005) to BCVA improvement. Average total retinal thickness in isolation demonstrated poor correlation (PCC = 0.334, p = 0.189). When two features, mean choroidal neovascular membranes (CNVM) size and total fluid volume, were combined and correlated with visual outcomes, the highest correlation increased to PCC = 0.695 (p = 0.002). CONCLUSIONS: In isolation, total fluid volume most closely correlates with change in BCVA values between baseline and week 52. In combination with complimentary information from OCT-A, an improvement in the linear correlation score was observed. Average total retinal thickness provided a lower correlation, and thus provides a lower predictive outcome than alternative metrics assessed. Clinically, a machine-learning approach to analyzing fluid metrics in combination with lesion size may provide an advantage in personalizing therapy and predicting BCVA outcomes at week 52.

Corneal Nerve Changes Observed by In Vivo Confocal Microscopy in Patients Receiving Oxaliplatin for Colorectal Cancer: The COCO Study.

An objective method of early identification of people at risk of chemotherapy-induced peripheral neuropathy is needed to minimize long-term toxicity and maximize dose intensity. The aims of the study were to observe corneal nerve microstructure and corneal sensitivity changes and peripheral neuropathy in patients receiving oxaliplatin, and to determine its association with corneal parameters at different stages of treatment and assess utility as non-invasive markers to detect and monitor peripheral neuropathy. Twenty-three patients scheduled to receive oxaliplatin chemotherapy with intravenous 5-FU for gastro-intestinal cancer were recruited and followed up with for 12 months. Ocular examinations including corneal and retinal evaluations, alongside peripheral neuropathy assessment, were performed. The corneal nerve density did not show significant change after chemotherapy when measured with a widely used semi-automated program or an automated analysis technique. Macula and optic nerve function did not change during or after oxaliplatin chemotherapy. However, the corneal nerve density modestly correlated with clinical peripheral neuropathy after 20 weeks of chemotherapy (r = 0.61, p = 0.01) when peripheral neuropathy is typical most profound, and corneal nerve sensitivity correlated with neuropathy at 12 (r = 0.55, p = 0.01) and 20 weeks (r = 0.64, p = 0.006). In conclusion, corneal changes detected on confocal microscopy show moderate association with peripheral neuropathy, indicating their potential to identify the development of oxaliplatin-induced peripheral neuropathy. However, further studies are required to confirm these findings.

Ability of cirrus HD-OCT optic nerve head parameters to discriminate normal from glaucomatous eyes.

PURPOSE: To determine the ability of optic nerve head (ONH) parameters measured with spectral domain Cirrus HD-OCT (Carl Zeiss Meditec, Inc., Dublin, CA) to discriminate between normal and glaucomatous eyes and to compare them with the discriminating ability of peripapillary retinal nerve fiber layer (RNFL) thickness measurements performed with Cirrus HD-OCT. DESIGN: Evaluation of diagnostic test or technology. PARTICIPANTS: Seventy-three subjects with glaucoma and 146 age-matched normal subjects. METHODS: Peripapillary ONH parameters and RNFL thickness were measured in 1 randomly selected eye of each participant within a 200 × 200 pixel A-scan acquired with Cirrus HD-OCT centered on the ONH. MAIN OUTCOME MEASURES: Optic nerve head topographic parameters, peripapillary RNFL thickness, and area under receiver operating characteristic curves (AUCs). RESULTS: To distinguish normal from glaucomatous eyes, regardless of disease stage, the 6 best parameters (expressed as AUC) were vertical rim thickness (VRT, 0.963), rim area (0.962), RNFL thickness at clock-hour 7 (0.957), RNFL thickness of the inferior quadrant (0.953), vertical cup-to-disc ratio (VCDR, 0.951), and average RNFL thickness (0.950). The AUC for distinguishing between normal eyes and eyes with mild glaucoma was greatest for RNFL thickness of clock-hour 7 (0.918), VRT (0.914), rim area (0.912), RNFL thickness of inferior quadrant (0.895), average RNFL thickness (0.893), and VCDR (0.890). There were no statistically significant differences between AUCs for the best ONH parameters and RNFL thickness measurements (P > 0.05). CONCLUSIONS: Cirrus HD-OCT ONH parameters are able to discriminate between normal eyes and eyes with glaucoma or even mild glaucoma. There is no difference in the ability of ONH parameters and RNFL thickness measurement, as measured with Cirrus OCT, to distinguish between normal and glaucomatous eyes.

Comparison of automated analysis of Cirrus HD OCT spectral-domain optical coherence tomography with stereo photographs of the optic disc.

OBJECTIVE: To evaluate a new automated analysis of optic disc images obtained by spectral-domain optical coherence tomography (SD OCT). Areas of the optic disc, cup, and neural rim in SD OCT images were compared with these areas from stereoscopic photographs to represent the current traditional optic nerve evaluation. The repeatability of measurements by each method was determined and compared. DESIGN: Evaluation of diagnostic technology. PARTICIPANTS: One hundred nineteen healthy eyes, 23 eyes with glaucoma, and 7 glaucoma suspect eyes. METHODS: Optic disc and cup margins were traced from stereoscopic photographs by 3 individuals independently. Optic disc margins and rim widths were determined automatically in SD OCT. A subset of photographs was examined and traced a second time, and duplicate SD OCT images also were analyzed. MAIN OUTCOME MEASURES: Agreement among photograph readers, between duplicate readings, and between SD OCT and photographs were quantified by the intraclass correlation coefficient (ICC), by the root mean square, and by the standard deviation of the differences. RESULTS: Optic disc areas tended to be slightly larger when judged in photographs than by SD OCT, whereas cup areas were similar. Cup and optic disc areas showed good correlation (0.8) between the average photographic reading and SD OCT, but only fair correlation of rim areas (0.4). The SD OCT was highly reproducible (ICC, 0.96-0.99). Each reader also was consistent with himself on duplicate readings of 21 photographs (ICC, 0.80-0.88 for rim area and 0.95-0.98 for all other measurements), but reproducibility was not as good as SD OCT. Measurements derived from SD OCT did not differ from photographic readings more than the readings of photographs by different readers differed from each other. CONCLUSIONS: Designation of the cup and optic disc boundaries by an automated analysis of SD OCT was within the range of variable designations by different readers from color stereoscopic photographs, but use of different landmarks typically made the designation of the optic disc size somewhat smaller in the automated analysis. There was better repeatability among measurements from SD OCT than from among readers of photographs. The repeatability of automated measurement of SD OCT images is promising for use both in diagnosis and in monitoring of progression.

Visual dysfunction in multiple sclerosis correlates better with optical coherence tomography derived estimates of macular ganglion cell layer thickness than peripapillary retinal nerve fiber layer thickness.

BACKGROUND: Post-mortem analyses of multiple sclerosis (MS) eyes demonstrate prominent retinal neuronal ganglion cell layer (GCL) loss, in addition to related axonal retinal nerve fiber layer (RNFL) loss. Despite this, clinical correlations of retinal neuronal layers remain largely unexplored in MS. OBJECTIVES: To determine if MS patients exhibit in vivo retinal neuronal GCL loss, deeper retinal neuronal loss, and investigate correlations between retinal layer thicknesses, MS clinical subtype and validated clinical measures. METHODS: Cirrus HD-optical coherence tomography (OCT), utilizing automated intra-retinal layer segmentation, was performed in 132 MS patients and 78 healthy controls. MS classification, Expanded Disability Status Scale (EDSS) and visual function were recorded in study subjects. RESULTS: GCL+inner plexiform layer (GCIP) was thinner in relapsing-remitting MS (RRMS; n = 96, 71.6 µm), secondary progressive MS (SPMS; n = 20, 66.4 µm) and primary progressive MS (PPMS; n = 16, 74.1 µm) than in healthy controls (81.8 µm; p < 0.001 for all). GCIP thickness was most decreased in SPMS, and although GCIP thickness correlated significantly with disease duration, after adjusting for this, GCIP thickness remained significantly lower in SPMS than RRMS. GCIP thickness correlated significantly, and better than RNFL thickness, with EDSS, high-contrast, 2.5% low-contrast and 1.25% low-contrast letter acuity in MS. 13.6% of patients also demonstrated inner or outer nuclear layer thinning. CONCLUSIONS: OCT segmentation demonstrates in vivo GCIP thinning in all MS subtypes. GCIP thickness demonstrates better structure-function correlations (with vision and disability) in MS than RNFL thickness. In addition to commonly observed RNFL/GCIP thinning, retinal inner and outer nuclear layer thinning occur in MS.

Effects of subthreshold nanosecond laser therapy in age-related macular degeneration using artificial intelligence (STAR-AI Study).

PURPOSE: To investigate changes in retinal thickness, drusen volume, and visual acuity following subthreshold nanosecond laser (SNL) treatment in patients with age-related macular degeneration (ARMD). DESIGN: Retrospective chart review. METHODS: Patients with intermediate ARMD treated with a single session of SNL (2RT®, Ellex R&D Pty Ltd, Adelaide, Australia) were included. Swept-source optical coherence tomography (OCT) imaging (Triton; Topcon Medical Systems, Tokyo, Japan) was performed within 6 months before and after SNL treatment. Retinal layers were segmented using the artificial intelligence-enabled Orion® software (Voxeleron LLC, San Francisco, USA). The macular region was analyzed according to the Early Treatment Diabetic Retinopathy Study map. Mean difference and standard deviation in baseline and post-treatment retinal layer thicknesses are reported. RESULTS: 37 eyes from 25 patients were included in this study (mean age 74.7±9.2 years). An average of 51±6 spots were applied around the macula of each study eye, with a mean spot power of 0.33±0.04mJ. Increases in total retinal thickness were observed within the outer temporal and inferior sectors (P<0.05). Within the annulus, there was an increase in thickness of the sub-retinal pigment epithelial (RPE) space [0.88±2.41µm, P = 0.03], defined between the RPE and Bruch's membrane. An increase in thickness of 1.13±2.55µm (P = 0.01) was also noted in the inferior sector of the photoreceptor complex, defined from the inner and outer segment junction to the RPE. Decreases in thickness were observed within the superior sector of the inner nuclear layer (INL) [-1.08±2.55µm, P = 0.01], and within the annulus of the outer nuclear layer (ONL) [-1.44±3.55µm, P = 0.02]. CONCLUSIONS: At 6 months post-SNL treatment, there were sectoral increases in OPL, photoreceptor complex, and sub-RPE space thicknesses and sectoral decreases in INL and ONL thicknesses. This pilot study demonstrates the utility of OCT combined with artificial intelligence-enabled software to track retinal changes that occur following SNL treatment in intermediate ARMD.

Combining In Vivo Corneal Confocal Microscopy With Deep Learning-Based Analysis Reveals Sensory Nerve Fiber Loss in Acute Simian Immunodeficiency Virus Infection.

PURPOSE: To characterize corneal subbasal nerve plexus features of normal and simian immunodeficiency virus (SIV)-infected macaques by combining in vivo corneal confocal microscopy (IVCM) with automated assessments using deep learning-based methods customized for macaques. METHODS: IVCM images were collected from both male and female age-matched rhesus and pigtailed macaques housed at the Johns Hopkins University breeding colony using the Heidelberg HRTIII with Rostock Corneal Module. We also obtained repeat IVCM images of 12 SIV-infected animals including preinfection and 10-day post-SIV infection time points. All IVCM images were analyzed using a deep convolutional neural network architecture developed specifically for macaque studies. RESULTS: Deep learning-based segmentation of subbasal nerves in IVCM images from macaques demonstrated that corneal nerve fiber length and fractal dimension measurements did not differ between species, but pigtailed macaques had significantly higher baseline corneal nerve fiber tortuosity than rhesus macaques (P = 0.005). Neither sex nor age of macaques was associated with differences in any of the assessed corneal subbasal nerve parameters. In the SIV/macaque model of human immunodeficiency virus, acute SIV infection induced significant decreases in both corneal nerve fiber length and fractal dimension (P = 0.01 and P = 0.008, respectively). CONCLUSIONS: The combination of IVCM and robust objective deep learning analysis is a powerful tool to track sensory nerve damage, enabling early detection of neuropathy. Adapting deep learning analyses to clinical corneal nerve assessments will improve monitoring of small sensory nerve fiber damage in numerous clinical settings including human immunodeficiency virus.

Corneal confocal microscopy demonstrates axonal loss in different courses of multiple sclerosis.

Axonal loss is the main determinant of disease progression in multiple sclerosis (MS). This study aimed to assess the utility of corneal confocal microscopy (CCM) in detecting corneal axonal loss in different courses of MS. The results were confirmed by two independent segmentation methods. 72 subjects (144 eyes) [(clinically isolated syndrome (n = 9); relapsing-remitting MS (n = 20); secondary-progressive MS (n = 22); and age-matched, healthy controls (n = 21)] underwent CCM and assessment of their disability status. Two independent algorithms (ACCMetrics; and Voxeleron deepNerve) were used to quantify corneal nerve fiber density (CNFD) (ACCMetrics only), corneal nerve fiber length (CNFL) and corneal nerve fractal dimension (CNFrD). Data are expressed as mean ± standard deviation with 95% confidence interval (CI). Compared to controls, patients with MS had significantly lower CNFD (34.76 ± 5.57 vs. 19.85 ± 6.75 fibers/mm2, 95% CI - 18.24 to - 11.59, P < .0001), CNFL [for ACCMetrics: 19.75 ± 2.39 vs. 12.40 ± 3.30 mm/mm2, 95% CI - 8.94 to - 5.77, P < .0001; for deepNerve: 21.98 ± 2.76 vs. 14.40 ± 4.17 mm/mm2, 95% CI - 9.55 to - 5.6, P < .0001] and CNFrD [for ACCMetrics: 1.52 ± 0.02 vs. 1.45 ± 0.04, 95% CI - 0.09 to - 0.05, P < .0001; for deepNerve: 1.29 ± 0.03 vs. 1.19 ± 0.07, 95% - 0.13 to - 0.07, P < .0001]. Corneal nerve parameters were comparably reduced in different courses of MS. There was excellent reproducibility between the algorithms. Significant corneal axonal loss is detected in different courses of MS including patients with clinically isolated syndrome.

A 3D Deep Learning System for Detecting Referable Glaucoma Using Full OCT Macular Cube Scans.

Purpose: The purpose of this study was to develop a 3D deep learning system from spectral domain optical coherence tomography (SD-OCT) macular cubes to differentiate between referable and nonreferable cases for glaucoma applied to real-world datasets to understand how this would affect the performance. Methods: There were 2805 Cirrus optical coherence tomography (OCT) macula volumes (Macula protocol 512 × 128) of 1095 eyes from 586 patients at a single site that were used to train a fully 3D convolutional neural network (CNN). Referable glaucoma included true glaucoma, pre-perimetric glaucoma, and high-risk suspects, based on qualitative fundus photographs, visual fields, OCT reports, and clinical examinations, including intraocular pressure (IOP) and treatment history as the binary (two class) ground truth. The curated real-world dataset did not include eyes with retinal disease or nonglaucomatous optic neuropathies. The cubes were first homogenized using layer segmentation with the Orion Software (Voxeleron) to achieve standardization. The algorithm was tested on two separate external validation sets from different glaucoma studies, comprised of Cirrus macular cube scans of 505 and 336 eyes, respectively. Results: The area under the receiver operating characteristic (AUROC) curve for the development dataset for distinguishing referable glaucoma was 0.88 for our CNN using homogenization, 0.82 without homogenization, and 0.81 for a CNN architecture from the existing literature. For the external validation datasets, which had different glaucoma definitions, the AUCs were 0.78 and 0.95, respectively. The performance of the model across myopia severity distribution has been assessed in the dataset from the United States and was found to have an AUC of 0.85, 0.92, and 0.95 in the severe, moderate, and mild myopia, respectively. Conclusions: A 3D deep learning algorithm trained on macular OCT volumes without retinal disease to detect referable glaucoma performs better with retinal segmentation preprocessing and performs reasonably well across all levels of myopia. Translational Relevance: Interpretation of OCT macula volumes based on normative data color distributions is highly influenced by population demographics and characteristics, such as refractive error, as well as the size of the normative database. Referable glaucoma, in this study, was chosen to include cases that should be seen by a specialist. This study is unique because it uses multimodal patient data for the glaucoma definition, and includes all severities of myopia as well as validates the algorithm with international data to understand generalizability potential.

Deep learning-based analysis of macaque corneal sub-basal nerve fibers in confocal microscopy images.

BACKGROUND: To develop and validate a deep learning-based approach to the fully-automated analysis of macaque corneal sub-basal nerves using in vivo confocal microscopy (IVCM). METHODS: IVCM was used to collect 108 images from 35 macaques. 58 of the images from 22 macaques were used to evaluate different deep convolutional neural network (CNN) architectures for the automatic analysis of sub-basal nerves relative to manual tracings. The remaining images were used to independently assess correlations and inter-observer performance relative to three readers. RESULTS: Correlation scores using the coefficient of determination between readers and the best CNN averaged 0.80. For inter-observer comparison, inter-correlation coefficients (ICCs) between the three expert readers and the automated approach were 0.75, 0.85 and 0.92. The ICC between all four observers was 0.84, the same as the average between the CNN and individual readers. CONCLUSIONS: Deep learning-based segmentation of sub-basal nerves in IVCM images shows high to very high correlation to manual segmentations in macaque data and is indistinguishable across readers. As quantitative measurements of corneal sub-basal nerves are important biomarkers for disease screening and management, the reported work offers utility to a variety of research and clinical studies using IVCM.

Deep Learning for Prediction of AMD Progression: A Pilot Study.

Purpose: To develop and assess a method for predicting the likelihood of converting from early/intermediate to advanced wet age-related macular degeneration (AMD) using optical coherence tomography (OCT) imaging and methods of deep learning. Methods: Seventy-one eyes of 71 patients with confirmed early/intermediate AMD with contralateral wet AMD were imaged with OCT three times over 2 years (baseline, year 1, year 2). These eyes were divided into two groups: eyes that had not converted to wet AMD (n = 40) at year 2 and those that had (n = 31). Two deep convolutional neural networks (CNN) were evaluated using 5-fold cross validation on the OCT data at baseline to attempt to predict which eyes would convert to advanced AMD at year 2: (1) VGG16, a popular CNN for image recognition was fine-tuned, and (2) a novel, simplified CNN architecture was trained from scratch. Preprocessing was added in the form of a segmentation-based normalization to reduce variance in the data and improve performance. Results: Our new architecture, AMDnet, with preprocessing, achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.89 at the B-scan level and 0.91 for volumes. Results for VGG16, an established CNN architecture, with preprocessing were 0.82 for B-scans/0.87 for volumes versus 0.66 for B-scans/0.69 for volumes without preprocessing. Conclusions: A CNN with layer segmentation-based preprocessing shows strong predictive power for the progression of early/intermediate AMD to advanced AMD. Use of the preprocessing was shown to improve performance regardless of the network architecture.