Machine learning quantitative OCT derived fibrosis indicators for corneal haze evaluation
- 1Laboratoire d'Optique et Biosciences, CNRS, INSERM, École polytechnique, Institut polytechnique de Paris, Palaiseau, France.
- 2Laboratoire d'Optique Appliquée (LOA), CNRS, ENSTA, École polytechnique, Institut polytechnique de Paris, Palaiseau, France.
- 3GRC 32, Transplantation et Thérapies Innovantes de la Cornée, Sorbonne Université, Centre Hospitalier National d'Ophtalmologie des Quinze-Vingts, Paris, France.
Abstract
Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. In some cases, it leads to temporary subepithelial fibrosis linked to visual haze, but objective and quantitative tools to monitor these symptoms are lacking. We here present a machine learning-based method for the classification of corneal images from spectral domain optical coherence tomography images recorded in vivo on standard clinical devices and use it to extract quantitative fibrosis indicators. Because of the transient nature and relative rarity of significant post-PRK haze, we trained the model on corneas presenting Fuchs’ Endothelial Corneal Dystrophy, causing similar, but permanent, fibrotic changes, and applied it to images from patients who have undergone PRK surgery. Our study shows that the model output (probability of pathological classification) combined with OCT-derived quantitative fibrosis descriptors provides an interpretable and explainable indicator of corneal healing for post-operative follow-up.
Related
- Quantitative CT Evaluation of Bronchiectasis Improvement in Cystic Fibrosis after CFTR-Modulator Therapy
- YieldLearn: An interpretable machine-learning pipeline for estimating yield-related traits based on physiological indicators
- Integrating multi-omics and machine learning to reveal IL1R2-driven macrophage-fibroblast spatial interactions in polycyclic aromatic hydrocarbon-induced pulmonary fibrosis
- Food insecurity and its related indicators in an Iranian population: An application of machine learning methods in data from Golestan Province
- Integrative network toxicology and machine learning reveal the potential role of 5-hydroxymethylfurfural in exacerbating pulmonary fibrosis
BibTeX
@article{soubeiran2026machine,
title = {{Machine learning quantitative OCT derived fibrosis indicators for corneal haze evaluation}},
author = {Corentin Soubeiran and Maëlle Vilbert and Benjamin Memmi and Cristina Georgeon and Vincent Borderie and Anatole Chessel and Karsten Plamann},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0328320},
url = {https://doi.org/10.1371/journal.pone.0328320},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine learning quantitative OCT derived fibrosis indicators for corneal haze evaluation
AU - Corentin Soubeiran
AU - Maëlle Vilbert
AU - Benjamin Memmi
AU - Cristina Georgeon
AU - Vincent Borderie
AU - Anatole Chessel
AU - Karsten Plamann
PY - 2026
DA - 2026/10/22
JO - PLOS One
DO - 10.1371/journal.pone.0328320
UR - https://doi.org/10.1371/journal.pone.0328320
AB - Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. In some cases, it leads to temporary subepithelial fibrosis linked to visual haze, but objective and quantitative tools to monitor these symptoms are lacking. We here present a machine learning-based method for the classification of corneal images from spectral domain optical coherence tomography images recorded in vivo on standard clinical devices and use it to extract quantitative fibrosis indicators. Because of the transient nature and relative rarity of significant post-PRK haze, we trained the model on corneas presenting Fuchs’ Endothelial Corneal Dystrophy, causing similar, but permanent, fibrotic changes, and applied it to images from patients who have undergone PRK surgery. Our study shows that the model output (probability of pathological classification) combined with OCT-derived quantitative fibrosis descriptors provides an interpretable and explainable indicator of corneal healing for post-operative follow-up.
SN - 1932-6203
ER -