Accurate Detection of Retinal Disease Progression Using Artificial Intelligence

Friday 14 March 2025


Scientists have made a major breakthrough in the field of medical imaging, developing a new technology that can accurately detect changes in retinal disease over time. This innovation has the potential to revolutionize the way doctors diagnose and treat conditions such as age-related macular degeneration (AMD), which is a leading cause of blindness worldwide.


The new system uses artificial intelligence (AI) to analyze optical coherence tomography (OCT) scans, which are high-resolution images of the retina. By comparing these scans over time, the AI can detect even subtle changes in the tissue that may indicate disease progression or treatment response.


One of the key challenges in developing this technology was addressing the class imbalance problem, where there are many more stable cases than cases of significant change. To overcome this issue, the researchers used a combination of focal loss and earth mover’s distance-based loss to train their model. This approach allowed the AI to focus on the most informative features and make accurate predictions even in the presence of noisy or incomplete data.


The system was tested using a large dataset of OCT scans from patients with AMD, and it achieved impressive accuracy levels. The researchers found that the AI was able to correctly classify changes in disease severity up to 85% of the time, which is significantly better than current manual methods.


This technology has the potential to greatly improve patient outcomes by enabling doctors to make more accurate diagnoses and monitor treatment response over time. It could also help reduce the need for invasive procedures and minimize the risk of complications associated with repeated imaging sessions.


The researchers are already working on refining their system and exploring its applications in other areas of medicine. They believe that this technology has far-reaching potential, not only in the field of ophthalmology but also in other fields such as neurology and cardiology where longitudinal changes can be crucial for diagnosis and treatment.


In addition to improving patient outcomes, this technology could also help reduce healthcare costs by minimizing the need for unnecessary procedures and reducing the risk of complications. It’s an exciting development that has the potential to make a real difference in people’s lives.


Cite this article: “Accurate Detection of Retinal Disease Progression Using Artificial Intelligence”, The Science Archive, 2025.


Medical Imaging, Retinal Disease, Age-Related Macular Degeneration, Amd, Artificial Intelligence, Oct Scans, Class Imbalance Problem, Focal Loss, Earth Mover’S Distance-Based Loss, Healthcare Costs


Reference: Taha Emre, Teresa Araújo, Marzieh Oghbaie, Dmitrii Lachinov, Guilherme Aresta, Hrvoje Bogunović, “Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality” (2025).


Leave a Reply