Artificial Intelligence Recognizes Deteriorating Photoreceptors

A software based on Artificial Intelligence (AI), developed by researchers at University Hospital Bonn, Stanford University, and the University of Utah’s Eye Clinic, which enables accurate assessment of the progression of geographic atrophy (GA), a disease. is. Photosensitive retina due to age-related macular degeneration (AMD). This innovative approach allows fully automated measurement of the main atrophic lesions using data from optical coherence tomography, which provides a three-dimensional view of the structure of the retina.

In addition, the research team can precisely determine the integrity of the photosensitive cells of the entire central retina and also detect progressive degenerative changes of the so-called photoreceptor beyond the main lesions. The findings will be used to assess the effectiveness of new innovative therapeutic approaches. The study is now published in the journal “Jama Ophthalmology”.

There is no effective treatment for geographic atrophy, the most common cause of blindness in industrialized countries. This disease damages the cells of the retina and causes their death. The main lesions, areas of the degenerated retina, also known as “geographic atrophy”, expand as a result of disease progression and blind spots in the visual area of ​​the affected person.

A major challenge for the evaluation of therapies is that these lesions progress slowly, meaning that a longer follow-up period is required for intervention studies. “While evaluating the therapeutic approach, we have so far mainly focused on the main lesions of the disease.

However, in addition to loss of the central visual field, patients also suffer from symptoms such as low light sensitivity in the surrounding retina. “Preserving the microcirculation of the retina outside the main lesions will therefore be an already significant achievement, which can be used to verify the effectiveness of future therapeutic approaches.”

Integrity of photosensitive cells predicts disease progression

Researchers were able to show that the integrity of photosensitive cells outside areas of geographic atrophy is a predictor of future progression of the disease.

“Therefore it is possible that using therapeutic approaches that protect surrounding photosensitive cells may slow the progression of main atrophic lesions,” Proc of the Moran Eye Center at the University of Utah, USA. Says Monica Fleckenstein. The study of bone-based natural history on the geographical atrophy on which current publication is based.

“Research in ophthalmology is increasingly data-driven. The finest, fully automated, accurate analysis of microscopic changes in optical coherence tomography data using AI represents an important step towards personalized therapy for patients with age-related macular degeneration, ”explains Dr. Maximilian Pfau is the lead author of the eye clinic at the university.

Hospital Bonn, currently working as a fellow of the German Research Foundation (DFG) and a postdoctoral fellow at Stanford University in the Department of Biomedical Data Science. “It would also be useful to reevaluate old treatment studies with new methods to assess potential effects on photoreceptor integrity.”

An objective

To evaluate its association with future GA progression, and to characterize its ratio-temporal progression, to determine the amount of photoreceptor degeneration outside areas of GA in eyes with no AMD.

Investment risk

Longitudinal spectral-domain optical coherence tomography (SD-OCT) volume scans (121 B-scans across 30 ° × 25 °) were fragmented with a deep-learning pipeline and age-adjusted normal data (z score) Was standardized in a pointwise manner with. .

The thickness of the outer nuclear layer (ONL), photoreceptor inner segment (IS), and outer segment (OS) were determined with contour lines evenly spread around the GA lesions.

Linear mixed models were applied to assess the association between photoreceptor-related imaging features and GA progression rates and to characterize patterns of photoreceptor degeneration over time.