Automated MRI-based quantification of posterior ocular globe flattening and recovery after long-duration spaceflight

Imaging in spaceflight associated neuro-ocular syndrome (SANS): Current technology and future directions in modalities

With plans for future long-duration crewed exploration, NASA has identified several high priority potential health risks to astronauts in space. One such risk is a collection of neurologic and ophthalmic findings termed spaceflight associated neuro-ocular syndrome (SANS). The findings of SANS include optic disc edema, globe flattening, retinal nerve fiber layer thickening, chorioretinal folds, hyperopic shifts, and cotton-wool spots. The cause of SANS was initially thought to be a cephalad fluid shift in microgravity leading to increased intracranial pressure, venous stasis and impaired CSF outflow, but the precise etiology of SANS remains ill defined. Recent studies have explored multiple possible pathogenic mechanisms for SANS including genetic and hormonal factors; a cephalad shift of fluid into the orbit and brain in microgravity; and disruption to the brain glymphatic system. Orbital, ocular, and cranial imaging, both on Earth and in space has been critical in the diagnosis and monitoring of SANS (e.g., fundus photography, optical coherence tomography (OCT), magnetic resonance imaging (MRI), and orbital/cranial ultrasound). In addition, we highlight near-infrared spectroscopy and diffusion tensor imaging, two newer modalities with potential use in future studies of SANS. In this manuscript we provide a review of these modalities, outline their current and potential use in space and on Earth, and review the reported major imaging findings in SANS.

FA4SANS-GAN: A Novel Machine Learning Generative Adversarial Network to Further Understand Ophthalmic Changes in Spaceflight Associated Neuro-Ocular Syndrome (SANS)

Purpose

To provide an automated system for synthesizing fluorescein angiography (FA) images from color fundus photographs for averting risks associated with fluorescein dye and extend its future application to spaceflight associated neuro-ocular syndrome (SANS) detection in spaceflight where resources are limited.

Design

Development and validation of a novel conditional generative adversarial network (GAN) trained on limited amount of FA and color fundus images with diabetic retinopathy and control cases.

Participants

Color fundus and FA paired images for unique patients were collected from a publicly available study.

Methods

FA4SANS-GAN was trained to generate FA images from color fundus photographs using 2 multiscale generators coupled with 2 patch-GAN discriminators. Eight hundred fifty color fundus and FA images were utilized for training by augmenting images from 17 unique patients. The model was evaluated on 56 fluorescein images collected from 14 unique patients. In addition, it was compared with 3 other GAN architectures trained on the same data set. Furthermore, we test the robustness of the models against acquisition noise and retaining structural information when introduced to artificially created biological markers.

Main Outcome Measures

For GAN synthesis, metric Fréchet Inception Distance (FID) and Kernel Inception Distance (KID). Also, two 1-sided tests (TOST) based on Welch's t test for measuring statistical significance.

Results

On test FA images, mean FID for FA4SANS-GAN was 39.8 (standard deviation, 9.9), which is better than GANgio model's mean of 43.2 (standard deviation, 13.7), Pix2PixHD's mean of 57.3 (standard deviation, 11.5) and Pix2Pix's mean of 67.5 (standard deviation, 11.7). Similarly for KID, FA4SANS-GAN achieved mean of 0.00278 (standard deviation, 0.00167) which is better than other 3 model's mean KID of 0.00303 (standard deviation, 0.00216), 0.00609 (standard deviation, 0.00238), 0.00784 (standard deviation, 0.00218). For TOST measurement, FA4SANS-GAN was proven to be statistically significant versus GANgio (P = 0.006); versus Pix2PixHD (P < 0.00001); and versus Pix2Pix (P < 0.00001).

Conclusions

Our study has shown FA4SANS-GAN to be statistically significant for 2 GAN synthesis metrics. Moreover, it is robust against acquisition noise, and can retain clear biological markers compared with the other 3 GAN architectures. This deployment of this model can be crucial in the International Space Station for detecting SANS.

Financial Disclosures

The authors have no proprietary or commercial interest in any materials discussed in this article.

Fully Automated Segmentation of Human Eyeball Using Three-Dimensional U-Net in T2 Magnetic Resonance Imaging

Purpose

To develop and validate a fully automated deep-learning-based tool for segmentation of the human eyeball using a three-dimensional (3D) U-Net, compare its performance to semiautomatic segmentation ground truth and a two-dimensional (2D) U-Net, and analyze age and sex differences in eyeball volume, as well as gaze-dependent volume consistency in normal subjects.

Methods

We retrospectively collected 474 magnetic resonance imaging (MRI) scans, including different gazing scans, from 119 patients. A 10-fold cross-validation was applied to separate the dataset into training, test, and validation sets for both the 3D U-Net and 2D U-Net. Performance accuracy was measured using four quantitative metrics compared to the ground truth, and Bland-Altman plot analysis was conducted. Age and sex differences in eyeball volume and variability in eyeball volume differences across gazing directions were analyzed.

Results

The 3D U-Net outperformed the 2D U-Net with mean accuracy scores >0.95, showing acceptable agreement in the Bland-Altman plot analysis despite a tendency for slight overestimation (mean difference = -0.172 cm³). Significant sex differences and age effects on eyeball volume were observed for both methods (P < 0.05). No significant volume differences were found between the segmentation methods or within each method for the different gazing directions. Significant differences in performance accuracy were identified among the five gazing directions, with the upward direction showing a notably lower performance.

Conclusions

Our study demonstrated the effectiveness of 3D U-Net human eyeball volume segmentation using T2-weighted MRI. The robustness and reliability of 3D U-Net across diverse populations and gaze directions support enhanced ophthalmic diagnosis and treatment strategies.

Translational Relevance

Our findings demonstrate the feasibility of using the proposed 3D U-Net model for the automatic segmentation of the human eyeball, with potential applications in various ophthalmic research fields that require the analysis of 3D geometric eye globe shapes or eye movement detection.

Insights into spaceflight-associated neuro-ocular syndrome with review of intraocular and orbital findings

PURPOSE OF REVIEW

Spaceflight-associated neuro-ocular syndrome (SANS) remains a phenomenological term, and advances in ophthalmic imaging as well as new insights from ground-based experiments have given support to new theories of how SANS develops and what may be done to counter it.

RECENT FINDINGS

SANS has been postulated to arise from elevated intracranial pressure (ICP) during long-duration spaceflight (LDSF). However, recent work has shown that acute microgravity exposure does not increase ICP, and the effect of cephalad fluid shifts on ICP in microgravity remain unknown. In addition, structural imaging of the retina and optic nerve show changes after LDSF that are distinct from findings in terrestrial patients with elevated ICP. Since astronauts have not reported symptoms that would be expected with chronic ICP elevation, new theories that orbital and/or intracranial venous pressure may be the primary contributors to the development of SANS.

SUMMARY

Research has been filling knowledge gaps that exist regarding the cause(s) of SANS, and these advances are crucial steps in the effort to design countermeasures that will be required before human deep space exploration missions can be undertaken.

Incidence and Progression of Chorioretinal Folds During Long-Duration Spaceflight

Importance

The primary contributing factor for development of chorioretinal folds during spaceflight is unknown. Characterizing fold types that develop and tracking their progression may provide insight into the pathophysiology of spaceflight-associated neuro-ocular syndrome and elucidate the risk of fold progression for future exploration-class missions exceeding 12 months in duration.

Objective

To determine the incidence and presentation of chorioretinal folds in long-duration International Space Station crew members and objectively quantify the progression of choroidal folds during spaceflight.

Design, Setting, and Participants

In this retrospective cohort study, optical coherence tomography scans of the optic nerve head and macula of crew members completing long-duration spaceflight missions were obtained on Earth prior to spaceflight and during flight. A panel of experts examined the scans for the qualitative presence of chorioretinal folds. Peripapillary total retinal thickness was calculated to identify eyes with optic disc edema, and choroidal folds were quantified based on surface roughness within macular and peripapillary regions of interest.

Interventions or Exposures

Spaceflight missions ranging 6 to 12 months.

Main Outcomes and Measures

Incidence of peripapillary wrinkles, retinal folds, and choroidal folds; peripapillary total retinal thickness; and Bruch membrane surface roughness.

Results

A total of 36 crew members were analyzed (mean [SD] age, 46 [6] years; 7 [19%] female). Chorioretinal folds were observed in 12 of 72 eyes (17%; 6 crew members). In eyes with early signs of disc edema, 10 of 42 (24%) had choroidal folds, 4 of 42 (10%) had inner retinal folds, and 2 of 42 (5%) had peripapillary wrinkles. Choroidal folds were observed in all eyes with retinal folds and peripapillary wrinkles. Macular choroidal folds developed in 7 of 12 eyes (4 of 6 crew members) with folds and progressed with mission duration; these folds extended into the fovea in 6 eyes. Circumpapillary choroidal folds developed predominantly superior, nasal, and inferior to the optic nerve head and increased in prevalence and severity with mission duration.

Conclusions and Relevance

Choroidal folds were the most common fold type to develop during spaceflight; this differs from reports in idiopathic intracranial hypertension, suggesting differences in the mechanisms underlying fold formation. Quantitative measures demonstrate the development and progression of choroidal folds during weightlessness, and these metrics may help to assess the efficacy of spaceflight-associated neuro-ocular syndrome countermeasures.

Optic nerve sheath diameter and spaceflight: defining shortcomings and future directions

Neuro-ocular changes during long-duration space flight are known as spaceflight-associated neuro-ocular syndrome (SANS). The ability to detect, monitor, and prevent SANS is a priority of current space medicine research efforts. Optic nerve sheath diameter (ONSD) measurement has been used both terrestrially and in microgravity as a proxy for measurements of elevated intracranial pressure. ONSD shows promise as a potential method of identifying and quantitating neuro-ocular changes during space flight. This review examines 13 studies measuring ONSD and its relationship to microgravity exposure or ground-based analogs, including head-down tilt, dry immersion, or animal models. The goal of this correspondence is to describe heterogeneity in the use of ONSD in the current SANS literature and make recommendations to reduce heterogeneity in future studies through standardization of imaging modalities, measurement techniques, and other aspects of study design.

Structural damage to the rat eye following long-term simulated weightlessness

To better perform space missions and develop human spaceflights, the eye health of astronauts is receiving increasing attention from researchers. In this study, we used prolonged tail suspension to simulate microgravity cephalad fluid shift in space to observe intraocular pressure (IOP) changes, retinal structure, and optic nerve damage in rats. We observed significant choroidal thickening and optic nerve demyelination lesions in the rats in each experimental group. At the cellular level, retinal ganglion cells (RGCs) survival was significantly reduced, optic nerve oligodendrocytes were reduced, and apoptotic factors and microglia-mediated inflammation-related factors were detected in both the retina and optic nerve. The severity of these changes increased with increasing tails suspension time. In conclusion, simulated long-term microgravity can lead to slight intraocular pressure fluctuations, choroidal thickening, reduced RGCs survival, and optic nerve demyelination in rats.

Changes in Optic Nerve Head and Retinal Morphology During Spaceflight and Acute Fluid Shift Reversal

Importance

Countermeasures that reverse the headward fluid shift experienced in weightlessness have the potential to mitigate spaceflight-associated neuro-ocular syndrome. This study investigated whether use of the countermeasure lower-body negative pressure during spaceflight was associated with changes in ocular structure.

Objective

To determine whether changes to the optic nerve head and retina during spaceflight can be mitigated by brief in-flight application of 25-mm Hg lower-body negative pressure.

Design, Setting, and Participants

In the National Aeronautics and Space Administration's "Fluid Shifts Study," a prospective cohort study, optical coherence tomography scans of the optic nerve head and macula were obtained from US and international crew members before flight, in-flight, and up to 180 days after return to Earth. In-flight scans were obtained both under normal weightless conditions and 10 to 20 minutes into lower-body negative pressure exposure. Preflight and postflight data were collected in the seated, supine, and head-down tilt postures. Crew members completed 6- to 12-month missions that took place on the International Space Station. Data were analyzed from 2016 to 2021.

Interventions or Exposures

Spaceflight and lower-body negative pressure.

Main Outcomes and Measures

Changes in minimum rim width, optic cup volume, Bruch membrane opening height, peripapillary total retinal thickness, and macular thickness.

Results

Mean (SD) flight duration for the 14 crew members (mean [SD] age, 45 [6] years; 11 male crew members [79%]) was 214 (72) days. Ocular changes on flight day 150, as compared with preflight seated, included an increase in minimum rim width (33.8 μm; 95% CI, 27.9-39.7 μm; P < .001), decrease in cup volume (0.038 mm3; 95% CI, 0.030-0.046 mm3; P < .001), posterior displacement of Bruch membrane opening (-9.0 μm; 95% CI, -15.7 to -2.2 μm; P = .009), and decrease in macular thickness (fovea to 500 μm, 5.1 μm; 95% CI, 3.5-6.8 μm; P < .001). Brief exposure to lower-body negative pressure did not affect these parameters.

Conclusions and Relevance

Results of this cohort study suggest that peripapillary tissue thickening, decreased cup volume, and mild central macular thinning were associated with long-duration spaceflight. Acute exposure to 25-mm Hg lower-body negative pressure did not alter optic nerve head or retinal morphology, suggesting that longer durations of a fluid shift reversal may be needed to mitigate spaceflight-induced changes and/or other factors are involved.