Further characterizing the physiological process of posterior globe flattening in spaceflight associated neuro-ocular syndrome with generative adversarial networks.

Abstract

Letter to the EditorFurther characterizing the physiological process of posterior globe flattening in spaceflight associated neuro-ocular syndrome with generative adversarial networksEthan Waisberg, Joshua Ong, Sharif Amit Kamran, Nasif Zaman, Phani Paladugu, Prithul Sarker, Alireza Tavakkoli, and Andrew G. LeeEthan WaisbergUniversity College Dublin School of Medicine, Dublin, Ireland, Joshua OngMichigan Medicine, University of Michigan, Ann Arbor, Michigan, Sharif Amit KamranHuman-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Nevada, Nasif ZamanHuman-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Nevada, Phani PaladuguBrigham and Women’s Hospital, Harvard Medical School, Boston, MassachusettsSidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, Pennsylvania, Prithul SarkerHuman-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Nevada, Alireza TavakkoliHuman-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Nevada, and Andrew G. LeeCenter for Space Medicine, Baylor College of Medicine, Houston, TexasDepartment of Ophthalmology, Blanton Eye Institute, Houston Methodist Hospital, Houston, TexasThe Houston Methodist Research Institute, Houston Methodist Hospital, Houston, TexasDepartment of Ophthalmology, Weill Cornell Medicine, New York City, New YorkDepartment of Neurology, Weill Cornell Medicine, New York City, New YorkDepartment of Neurosurgery, Weill Cornell Medicine, New York City, New YorkDepartment of Ophthalmology, University of Texas Medical Branch, Galveston, TexasUniversity of Texas MD Anderson Cancer Center, Houston, TexasTexas A&M College of Medicine, Bryan, TexasDepartment of Ophthalmology, The University of Iowa Hospitals and Clinics, Iowa City, IowaPublished Online:02 Jan 2023https://doi.org/10.1152/japplphysiol.00747.2022MoreSectionsPDF (193 KB)Download PDF ToolsExport citationAdd to favoritesGet permissionsTrack citations ShareShare onFacebookTwitterLinkedInWeChat to the editor In a recent issue of Journal of Applied Physiology, Sater et al. (1) conducted an eloquent study on 24 healthy participants and found that strict 6° head-down tilt bed-rest (HDTBR) increased displacement of the posterior globe on magnetic resonance imaging (MRI), with a greater displacement seen as the duration of HDTBR increased. In addition, 30 min of artificial gravity did not significantly impact globe displacement in this study (1). We commend the authors for sharing these noteworthy findings, which add to the current knowledge on physiological changes from strict 6° HDTBR. HDTBR is currently considered to be the gold standard terrestrial analog for spaceflight-associated neuro-ocular syndrome (SANS), and further understanding of the physiological changes associated with HDTBR testing is essential for further understanding the neuro-ophthalmic phenomenon and developing countermeasures.One of the noted study limitations by the study authors was that although HDTBR was able to reproduce some effects of spaceflight, other microgravity-based findings were unable to be reproduced including axial length and choroidal thickening. The authors suggested that there are limitations to HDTBR as a spaceflight analog. Thus, further characterizing posterior globe flattening during spaceflight may provide additional knowledge of SANS. This study demonstrates the immense knowledge gained on the physiological process of posterior globe flattening from MRI. However, MRI is unavailable on the International Space Station (ISS), with a large logistical barrier for future spaceflight given its strong magnetic fields. Although MRI is unavailable, several ophthalmic imaging modalities, including optical coherence tomography (OCT), OCT angiography, and ocular/orbital ultrasound exist on the ISS (2). To help address MRI limitations for spaceflight, we propose the usage of generative adversarial networks (GANs) to be applied to current ophthalmic imaging on the ISS (3). GANs are an emerging and powerful deep-learning framework that has become the most successful generative model. GANs can take multiple inputs, including ophthalmic imaging and functional visual assessments (4–6). The usage of a stacked generative adversarial network has previously been used to transform ultrasound images into synthetic CT images (7). Deep learning methods have also been used to synthesize artificial magnetic resonance images (MRI) from brain CT images (8). Given the insight of MRI from this study, such frameworks can be applied toward ultrasound and OCT, which are available on the ISS to help further understand the posterior globe flattening physiology of SANS during spaceflight. We applaud the authors on their well-conducted study and invite their reply to this deep learning technology to help address the current barriers to MRI during spaceflight.GRANTSThe study was supported by National Aeronautics and Space Administration (NASA) Grant No. 80NSSC20K183: A Non-intrusive Ocular Monitoring Framework to Model Ocular Structure and Functional Changes Due to Long-term Spaceflight.DISCLOSURESNo conflicts of interest, financial or otherwise, are declared by the authors.AUTHOR CONTRIBUTIONSE.W. and J.O. conceived and designed research; E.W. and J.O. drafted manuscript; E.W., J.O., S.A.K., N.Z., P.P., P.S., A.T., and A.G.L. edited and revised manuscript; E.W., J.O., S.A.K., N.Z., P.P., P.S., A.T., and A.G.L. approved final version of manuscript.REFERENCES1. Sater SH, Conley Natividad G, Seiner AJ, Fu AQ, Shrestha D, Bershad EM, Marshall-Goebel K, Laurie SS, Macias BR, Martin BA. MRI-based quantification of posterior ocular globe flattening during 60 days of strict 6° head-down tilt bed rest with and without daily centrifugation. J Appl Physiol (1985) 133: 1349–1355, 2022. doi:10.1152/japplphysiol.00082.2022. Link | Google Scholar2. Lee AG, Mader TH, Gibson CR, Tarver W, Rabiei P, Riascos RF, Galdamez LA, Brunstetter T. Spaceflight associated neuro-ocular syndrome (SANS) and the neuro-ophthalmologic effects of microgravity: a review and an update. NPJ Microgravity 6: 7, 2020 [Erratum in NPJ Microgravity. 2020 Aug 26;6:23]. doi:10.1038/s41526-020-0097-9.Crossref | PubMed | ISI | Google Scholar3. Gong M, Chen S, Chen Q, Zeng Y, Zhang Y. Generative adversarial networks in medical image processing. Curr Pharm Des 27: 1856–1868, 2021. doi:10.2174/1381612826666201125110710.Crossref | PubMed | ISI | Google Scholar4. Ong J, Tavakkoli A, Zaman N, Kamran SA, Waisberg E, Gautam N, Lee AG. Terrestrial health applications of visual assessment technology and machine learning in spaceflight associated neuro-ocular syndrome. NPJ Microgravity 8: 37, 2022. doi:10.1038/s41526-022-00222-7.Crossref | PubMed | ISI | Google Scholar5. Ong J, Zaman N, Kamran SA, Waisberg E, Tavakkoli A, Lee AG, Webster M. Contributed Session I: a multi-modal visual assessment system for monitoring spaceflight associated neuro-ocular syndrome (SANS) during long duration spaceflight. J Vis 22: 6, 2022.doi:10.1167/jov.22.3.6.Crossref | Google Scholar6. Waisberg E, Ong J, Zaman N, Kamran SA, Lee AG, Tavakkoli A. Head-mounted dynamic visual acuity for G-transition effects during interplanetary spaceflight: technology development and results from an early validation study. Aerosp Med Hum Perform 93: 800–805, 2022. doi:10.3357/AMHP.6092.2022. Crossref | PubMed | ISI | Google Scholar7. Sun H, Lu Z, Fan R, Xiong W, Xie K, Ni X, Yang J. Research on obtaining pseudo CT images based on stacked generative adversarial network. Quant Imaging Med Surg 11: 1983–2000, 2021. doi:10.21037/qims-20-1019.Crossref | PubMed | ISI | Google Scholar8. Li W, Li Y, Qin W, Liang X, Xu J, Xiong J, Xie Y. Magnetic resonance image (MRI) synthesis from brain computed tomography (CT) images based on deep learning methods for magnetic resonance (MR)-guided radiotherapy. Quant Imaging Med Surg 10: 1223–1236, 2020. doi:10.21037/qims-19-885.Crossref | PubMed | ISI | Google ScholarAUTHOR NOTESCorrespondence: A. G. Lee ([email protected]org). Download PDF Previous Back to Top Next FiguresReferencesRelatedInformationRelated ArticlesMRI-based quantification of posterior ocular globe flattening during 60 days of strict 6° head-down tilt bed rest with and without daily centrifugation 09 Dec 2022Journal of Applied Physiology More from this issue > Volume 134Issue 1January 2023Pages 150-151 Crossmark Copyright & PermissionsCopyright © 2023 the American Physiological Society.https://doi.org/10.1152/japplphysiol.00747.2022PubMed36592406History Received 12 December 2022 Accepted 19 December 2022 Published online 2 January 2023 Published in print 1 January 2023 KeywordsMRIGANgenerative adversarial networkspaceflight associated neuro-ocular syndrome Metrics