RESUMO
BACKGROUND: In vivo imaging of the human retina using adaptive optics optical coherence tomography (AO-OCT) has transformed medical imaging by enabling visualization of 3D retinal structures at cellular-scale resolution, including the retinal pigment epithelial (RPE) cells, which are essential for maintaining visual function. However, because noise inherent to the imaging process (e.g., speckle) makes it difficult to visualize RPE cells from a single volume acquisition, a large number of 3D volumes are typically averaged to improve contrast, substantially increasing the acquisition duration and reducing the overall imaging throughput. METHODS: Here, we introduce parallel discriminator generative adversarial network (P-GAN), an artificial intelligence (AI) method designed to recover speckle-obscured cellular features from a single AO-OCT volume, circumventing the need for acquiring a large number of volumes for averaging. The combination of two parallel discriminators in P-GAN provides additional feedback to the generator to more faithfully recover both local and global cellular structures. Imaging data from 8 eyes of 7 participants were used in this study. RESULTS: We show that P-GAN not only improves RPE cell contrast by 3.5-fold, but also improves the end-to-end time required to visualize RPE cells by 99-fold, thereby enabling large-scale imaging of cells in the living human eye. RPE cell spacing measured across a large set of AI recovered images from 3 participants were in agreement with expected normative ranges. CONCLUSIONS: The results demonstrate the potential of AI assisted imaging in overcoming a key limitation of RPE imaging and making it more accessible in a routine clinical setting.
The retinal pigment epithelium (RPE) is a single layer of cells within the eye that is crucial for vision. These cells are unhealthy in many eye diseases, and this can result in vision problems, including blindness. Imaging RPE cells in living human eyes is time consuming and difficult with the current technology. Our method substantially speeds up the process of RPE imaging by incorporating artificial intelligence. This enables larger areas of the eye to be imaged more efficiently. Our method could potentially be used in the future during routine eye tests. This could lead to earlier detection and treatment of eye diseases, and the prevention of some causes of blindness.
RESUMO
Purpose: To test the hypothesis that rod energy biomarkers in light and dark are similar in mice without functional rod transducin (Gnat1rd17). Methods: Gnat1rd17 and wildtype (WT) mice were studied in canonically low energy demand (light) and high energy demand (dark) conditions. We measured rod inner segment ellipsoid zone (ISez) profile shape, external limiting membrane-retinal pigment epithelium (ELM-RPE) thickness, and magnitude of a hyporeflective band (HB) intensity dip located between photoreceptor tips and apical RPE; antioxidants were given in a subset of mice. Oxygen consumption rate (OCR) and visual performance indexes were also measured. Results: The lower energy demand expected in light-adapted wildtype retinas was associated with an elongated ISez, thicker ELM-RPE, and higher HB magnitude, and lower OCR compared to high energy demand conditions in the dark. Gnat1rd17 mice showed a wildtype-like ISez profile shape at 20 minutes of light that became rounder at 60 minutes; at both times, ELM-RPE was smaller than wildtype values, and the HB magnitude was unmeasurable. OCR was higher than in the dark. Light-adapted Gnat1rd17 mice biomarkers were unaffected by anti-oxidants. Gnat1rd17 mice showed modest outer nuclear layer thinning and no reduction in visual performance indexes. Conclusions: Light-stimulated changes in all biomarkers in WT mice are consistent with the established light-induced decrease in net energy demand. In contrast, biomarker changes in Gnat1rd17 mice raise the possibility that light increases net energy demand in the absence of rod phototransduction.
