Adaptive Optics Retinal Imaging

National Eye Institute

Investigators

Linked publications, trials & patents

Abstract

By the time diseases of the retina are detected, serious damage has often already been done. An advanced optical imaging instrument utilizing adaptive optics can be used to directly visualize the cellular structure of the retina in the living human eye. Adaptive optics is a technology for measuring and correcting the optical imperfections in the human eye. When adaptive optics is combined with an imaging platform, highly detailed images of the human retina can be acquired. Our research utilizes this technology to image cells in patients’ eyes through the Adaptive Optics Clinic within the NIH Clinical Center. Application of data science to rich adaptive optics imaging datasets can be greatly enhanced through artificial intelligence. We are continuing to explore the use of artificial intelligence to augment and enhance advanced optical imaging capabilities, as well as for the efficient analysis of adaptive optics imaging data. One breakthrough area that we have continued to pioneer is in the area of artificial intelligence assisted imaging (AI-assisted imaging). In this approach, we leverage AI technology to enhance the acquisition strategy of adaptive optics imaging, such as for adaptive optics enhanced indocyanine green (AO-ICG) imaging of retinal pigment epithelial (RPE) cells. Using this AI-assisted imaging approach, the overall throughput of imaging RPE cells by over 100X. In addition, incorporating AI with high resolution adaptive optics imaging in comparison with established clinical imaging modalities has demonstrated that it is possible to routinely visualize the RPE cells in clinical practice through the assistance of artificial intelligence using established clinical imaging modalities, an important step towards improved detection of microscopic changes that are associated with disease onset and progression in patient eyes. We have continued to makee progress towards improving the resolution of AO-OCT using optical methods that surpass the fundamental optical diffraction limit of resolution. This pilot study has been completed. Additional studies to collect and create the largest (to date) normative databases of adaptive optics enhanced indocyanine green images of RPE cells, adaptive optics non-confocal split detection images of cone cells, and adaptive optics optical coherence tomography images across the lifespan are all in progress. We continue to upgrade our imaging technology, through the design and implementation of a next generation, custom-built adaptive optics instrument in the NEI eye clinic which integrates technological advancements related to adaptive optics imaging which were developed in collaboration with Stanford University through the Audacious Goals Initiative program at the National Eye Institute. In addition to these extramural design upgrades, we have for the first time demonstrated intramural design upgrades that allow for real time streaming and recording of MHz speed AO-OCT imaging data with real time eye tracking accurate to the cellular level. This last effort is a major undertaking that has taken place together with the BETA center and IDEAS group at NIBIB. These advanced instrumentation capabilities are currently being optimized for improved reliability, efficiency, and technical features to improve government operations. Together, the synergistic activities in artificial intelligence, data science, clinical application, and instrumentation development pave a path forward toward new horizons in live cell imaging directly in the living human eye with the potential to reveal the pathophysiology of retinal and neurodegenerative diseases throughout the onset and progression of disease.