Artificial Intelligence Enhances Diagnostic Precision for Macular Edema

Strategic Insights -

Researchers at the Jordan University of Science and Technology have made significant strides in utilizing artificial intelligence to improve the diagnosis and treatment of macular edema, a prevalent cause of vision loss. By developing and evaluating a deep learning framework, investigators were able to accurately differentiate between diabetic macular edema, age-related macular degeneration, and normal retinal conditions using optical coherence tomography (OCT) images. The findings suggest the potential for artificial intelligence to enhance diagnostic precision and aid clinical decision-making in ophthalmology.

Key Takeaways:

  • The researchers developed a deep learning framework to distinguish between diabetic macular edema, age-related macular degeneration, and normal retinal conditions using OCT images.
  • The framework achieved high accuracy rates, with InceptionV3 and ResNet152 models achieving 95-98% accuracy across both datasets.
  • Explainable AI (XAI) techniques, specifically Grad-CAM, were applied to visualize the model predictions, and the outcomes were manually validated against annotated data to assess interpretability.
  • The study's findings support the integration of a robust CNN architecture and XAI techniques to enhance diagnostic precision and aid clinical decision-making in ophthalmology.
  • The researchers used a retrospective dataset comprising 1040 OCT images from King Abdullah University Hospital (KAUH) and a public dataset for benchmarking.
  • The study's conclusion highlights the potential for artificial intelligence to improve the diagnosis and treatment of macular edema, a prevalent cause of vision loss.

Statistics:

  • 95-98% accuracy achieved by InceptionV3 and ResNet152 models across both datasets.
  • 89% accuracy achieved by MobileNetV2 on the KAUH dataset.
  • 97% accuracy achieved by MobileNetV2 on the public dataset.
  • 1040 OCT images used in the retrospective dataset from King Abdullah University Hospital (KAUH).
  • Two datasets used in the study: a retrospective dataset from KAUH and a public dataset.

Sources:

  • NewsRx. Studies from Jordan University of Science and Technology Reveal New Findings on Artificial Intelligence (The utility of artificial intelligence in characterization and detecting causes of macular edema: A spectral-domain OCT-based algorithm study). Health & Medicine Week. September 19, 2025; p 7259.
  • The utility of artificial intelligence in characterization and detecting causes of macular edema: A spectral-domain OCT-based algorithm study. Experimental Eye Research, 2025;260:110619.
  • Academic Press Ltd- Elsevier Science Ltd, 24-28 Oval Rd, London NW1 7DX, England. (Elsevier - www.elsevier.com; Experimental Eye Research - www.journals.elsevier.com/experimental-eye-research/)
  • Amal Alzu'bi, Dept. of Computer Information Systems, Faculty of Computer and Information Technology, Jordan University of Science and Technology, P. O. Box 3030, Irbid, 22110, Jordan.