A non-invasive approach to monitor anemia during long-duration spaceflight with retinal fundus images and deep learning

Abstract

During spaceflight, astronauts can experience significantly higher levels of hemolysis. With future space missions exposing astronauts to longer periods of microgravity, such as missions to Mars, there will be a need to better understand this phenomenon. We have proposed that retinal fundus photography and deep learning may be utilized to help further understand this microgravity-induced, anemic process for future spaceflight. By utilizing astronaut and terrestrial analog metadata, a foundation can be built to develop an algorithm that allows for non-invasive retinal imaging to quantify hemoglobin levels and detect anemia during spaceflight. This approach would allow for a non-invasive retinal photograph that can be done frequently during spaceflight as opposed to an invasive blood draw and subsequent tests.

Keywords: Long-duration spaceflight; Machine learning; Non-invasive anemia detection; Retinal fundus photo.