Related Experiment Video
Updated: Jun 15, 2025
07:18
Evaluation of Capillary and Other Vessel Contribution to Macular Perfusion Density Measured with Optical Coherence Tomography Angiography
Published on: February 18, 2022
1.8K
Comparative Analysis of Macular and Optic Disc Perfusion Pre and Post Silicone Oil Removal: A Machine Learning
Georgios Feretzakis1, Christina Karakosta2, Aris Gkoulalas-Divanis3
1School of Science and Technology, Hellenic Open University, Patras, Greece.
Studies in Health Technology and Informatics
|August 23, 2024
Summary
Machine learning accurately predicts outer retina flow after silicone oil removal. However, predicting deep capillary plexus vessel density in specific regions remains challenging for these ophthalmic surgery models.
Area of Science:
- Ophthalmology
- Medical Imaging
- Machine Learning
Background:
- Silicone oil is a common tamponade in retinal detachment surgery.
- Its removal can impact ocular perfusion.
- Understanding these changes is crucial for patient outcomes.
Purpose of the Study:
- To analyze macular and optic disc perfusion changes post-silicone oil removal.
- To develop machine learning models for predicting these perfusion changes using OCTA data.
Main Methods:
- Utilized Optical Coherence Tomography Angiography (OCTA) data.
- Employed Gaussian Process Regression (GPR) and Long Short-Term Memory (LSTM) networks.
- Compared flow in the outer retina and vessel density in the deep capillary plexus.
Main Results:
- Machine learning models showed reasonable accuracy in predicting outer retina flow.
- Predicting vessel density in the deep capillary plexus, especially in the superior-hemi and perifovea, proved challenging.
Conclusions:
- Machine learning shows potential for personalized ophthalmology patient care.
- Predicting complex ocular perfusion changes requires further research and model refinement.
