Correcting Axial Length‐Related Magnification Errors in Optical Coherence Tomography Angiography Improves Machine Learning Classification Performance in High Myopia
Clinical & Experimental Ophthalmology · 2026-11 · 54 (8) · 1003-1012
DOI: 10.1111/ceo.70162 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical & Experimental Ophthalmology, online erschienen am 01.09.2026. Verfasst von Danuta M Sampson und 9 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Ophthalmology and Visual Science (Incorporating Lions Eye Institute), The University of Western Australia, Perth, Australia. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Retinal Vessels, Machine Learning, Fluorescein Angiography. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Department of Health, Government of Western Australia.
Abstract (Originalsprache)
Background
To determine whether axial length‐related magnification correction in optical coherence tomography angiography (OCTA) improves machine learning classification of high myopia and resolves inconsistencies in the values and discriminatory power of OCTA microvascular metrics.
Methods
We analysed retinal OCTA images from a prior Hong Kong Polytechnic University study. Fourteen superficial vascular plexus metrics were extracted before and after magnification correction and used to train random forest (RF) models to classify high versus non‐high myopia. Outcomes included classifier performance (the area under the receiver operating characteristic curve (AUC), sensitivity, specificity and feature importance) and changes in OCTA metrics between groups before and after correction.
Results
Image magnification correction significantly improved the classification of high versus non‐high myopia. When all 14 features were used to train the model, the AUC increased from 0.77 (fair) to 0.88 (good), and when restricted to the top five features (fractal dimension (Df), vessel length density (VLD), branchpoint density (BD), parafoveal rim VLD, and vessel area density (VAD)), similarly, from 0.79 to 0.88.
Conclusions
OCTA image magnification correction improves RF classification of high myopia and clarifies inconsistencies across studies. Underreported metrics, fractal dimension, parafoveal rim VLD and BD, emerged as key discriminators. Magnification correction with ML may improve characterisation of myopia‐related microvascular changes and enhance diagnostic precision, warranting further study.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Centre for Ophthalmology and Visual Science (Incorporating Lions Eye Institute), The University of Western Australia, Perth, Australia.
- Department of Optometry, School of Rehabilitation, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Department of Medicine, University of Chicago, Chicago, Illinois, USA.
- Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark.
- Lions Outback Vision, Nedlands, Australia.
- Centre for Myopia Research, School of Optometry, Faculty of Health and Social Science, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China.
ORCID-Profile: Danuta M Sampson, Mila Yue Zhang, Hemn Baghban Jaldian, Madeleine S Torcasso, Gavrielle R Untracht, Jocelyn J Drinkwater, Mei Zhao, David D Sampson, Andrew Lam, Fred K Chen
Förderung
- Department of Health, Government of Western Australia
Zitieren
APA
Sampson, D. M., Zhang, M. Y., Baghban Jaldian, H., Torcasso, M. S., Untracht, G. R., Drinkwater, J. J., Zhao, M., Sampson, D. D., Lam, A., & Chen, F. K. (2026). Correcting Axial Length‐Related Magnification Errors in Optical Coherence Tomography Angiography Improves Machine Learning Classification Performance in High Myopia. Clinical & Experimental Ophthalmology, 54(8), 1003-1012. https://doi.org/10.1111/ceo.70162
Vancouver
Sampson DM, Zhang MY, Baghban Jaldian H, Torcasso MS, Untracht GR, Drinkwater JJ, et al. Correcting Axial Length‐Related Magnification Errors in Optical Coherence Tomography Angiography Improves Machine Learning Classification Performance in High Myopia. Clinical & Experimental Ophthalmology. 2026;54(8):1003-1012. doi:10.1111/ceo.70162
BibTeX
@article{Sampson2026,
author = {Sampson, Danuta M and Zhang, Mila Yue and Baghban Jaldian, Hemn and Torcasso, Madeleine S and Untracht, Gavrielle R and Drinkwater, Jocelyn J and Zhao, Mei and Sampson, David D and Lam, Andrew and Chen, Fred K},
title = {Correcting Axial Length‐Related Magnification Errors in Optical Coherence Tomography Angiography Improves Machine Learning Classification Performance in High Myopia},
journal = {Clinical & Experimental Ophthalmology},
year = {2026},
volume = {54},
number = {8},
pages = {1003--1012},
doi = {10.1111/ceo.70162}
}
EUVIMED