In our role, as the GEYEDANCE project coordinator, ACMIT is proud to highlight a newly published study on IEEE Xplore titled: “Robust Distance Estimation with Out-of-distribution Detection in Ophthalmic Surgery” released in February, 2026.
This new IEEE‑published work introduces a deep learning method that improves micrometer‑scale instrument‑to‑retina distance estimation, a key factor for patient safety in ophthalmic surgery.
Validation on ex vivo human eyes shows strong performance: The pipeline achieves 88.8% accuracy in identifying out-of-distribution (OOD) measurements. Additionally, distance estimation improved by 89% and 93% when compared to two existing methods, resulting in an mean absolute error (MAE) of less than 40 μm across diverse conditions, including scans with blood and obstructions.
These results mark a major step forward in improving the accuracy of instrument-to-retina distance estimation thus enhancing patient safety in ophthalmic procedures. The approach opens new opportunities for sensor‑equipped instruments across various surgical disciplines, supporting the development of safer surgical systems.
For more information, please visit:
