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

Sharif Amit Kamran; Khondker Fariha Hossain; Joshua Ong; Ethan Waisberg; Nasif Zaman; Salah A Baker; Andrew G Lee; Alireza Tavakkoli

doi:10.1016/j.xops.2024.100493

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

Ophthalmol Sci. 2024 Feb 15;4(4):100493. doi: 10.1016/j.xops.2024.100493. eCollection 2024 Jul-Aug.

Authors

Sharif Amit Kamran¹, Khondker Fariha Hossain¹, Joshua Ong², Ethan Waisberg³, Nasif Zaman¹, Salah A Baker⁴, Andrew G Lee^{5

6

7

8

9

10

11

12}, Alireza Tavakkoli¹

Affiliations

¹ Human-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Reno, Nevada.
² Department of Ophthalmology and Visual Sciences, University of Michigan Kellogg Eye Center, Ann Arbor, Michigan.
³ Department of Ophthalmology, University College Dublin School of Medicine, Belfield, Dublin, Ireland.
⁴ Department of Physiology and Cell Biology, University of Nevada School of Medicine, Reno, Nevada.
⁵ Center for Space Medicine, Baylor College of Medicine, Houston, Texas.
⁶ Department of Ophthalmology, Blanton Eye Institute, Houston Methodist Hospital, Houston, Texas.
⁷ Houston Methodist Research Institute, Houston Methodist Hospital, Houston, Texas.
⁸ Departments of Ophthalmology, Neurology, and Neurosurgery, Weill Cornell Medicine, New York, New York.
⁹ Department of Ophthalmology, University of Texas Medical Branch, Galveston, Texas.
¹⁰ Department of Ophthalmology, University of Texas MD Anderson Cancer Center, Houston, Texas.
¹¹ Department of Ophthalmology, Texas A&M College of Medicine, Texas.
¹² Department of Ophthalmology, The University of Iowa Hospitals and Clinics, Iowa City, Iowa.

Abstract

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.

Keywords: Astronaut; Generative adversarial networks; Ophthalmic imaging; Space medicine; Spaceflight-associated neuro-ocular syndrome.