0
0
In a landmark development, researchers at the National Institutes of Health (NIH) have harnessed the power of artificial intelligence (AI) to revolutionize the imaging of cells in the eye, significantly improving diagnostic capabilities for conditions such as age-related macular degeneration (AMD) and other retinal diseases.
Led by Johnny Tam, Ph.D., head of the Clinical and Translational Imaging Section at NIH’s National Eye Institute, the team applied AI to a cutting-edge technique that produces high-resolution images of retinal pigment epithelium (RPE) cells. The results were staggering: imaging became 100 times faster, and image contrast improved 3.5-fold.
“Artificial intelligence helps overcome a key limitation of imaging cells in the retina, which is time,” explained Dr. Tam. “Our breakthrough will provide researchers with a superior tool to evaluate retinal diseases, enabling earlier detection and more effective treatment.”
The technology at the heart of this advancement is adaptive optics (AO), a method developed by Dr. Tam to enhance optical coherence tomography (OCT), a standard imaging technique in eye clinics. While OCT is noninvasive and widely used, imaging RPE cells with AO-OCT presents challenges due to a phenomenon called speckle, akin to clouds obstructing aerial photography.
To address this, the team developed a novel AI-based method called parallel discriminator generative adverbial network (P-GAN), a deep learning algorithm. By training P-GAN with thousands of manually analyzed images of human RPE, the network learned to identify and recover speckle-obscured cellular features.
“When tested on new images, P-GAN successfully de-speckled the RPE images, recovering cellular details with unparalleled efficiency,” said Vineeta Das, Ph.D., a postdoctoral fellow in the Clinical and Translational Imaging Section at NEI.
The implications of this breakthrough are profound. “Adaptive optics takes OCT-based imaging to the next level,” Dr. Tam enthused. “With AO, we can reveal 3D retinal structures at cellular-scale resolution, enabling us to zoom in on very early signs of disease.”
Importantly, this advancement has the potential to transform routine clinical imaging, particularly for diseases affecting the RPE, which has traditionally been challenging to image.
“Our results suggest that AI can fundamentally change how images are captured,” Dr. Tam emphasized. “Our P-GAN artificial intelligence will make AO imaging more accessible for routine clinical applications and for studies aimed at understanding blinding retinal diseases.”
The integration of AI with AO-OCT represents a paradigm shift in the field of medical imaging, offering new possibilities for early disease detection and personalized treatment strategies. As research continues, the future of eye care looks brighter than ever before.
