Add BrightSurf on Google Email

Automated lens density screening exposes myopia's unique cataract signature

09.11.26 | Science China Press

Cataract remains the world’s leading cause of preventable blindness, yet clinical assessment still relies heavily on subjective slit-lamp grading. Now, researchers at Peking University People's Hospital have developed an automated method that converts routine pre-operative eye scans into an objective cataract biomarker.

Detailed in Medicine Plus , the study introduces a Python-OpenCV pipeline that extracts "lens average density" from standard IOL Master 700 swept-source optical coherence tomography images. Tested across 1906 eyes, the automated metric demonstrated exceptional diagnostic discrimination (area under the curve = 0.975, 95% CI: 0.969–0.981; cutoff 68.66; sensitivity 88.5%, specificity 94.4%) and strong correlation with the LOCS III nuclear opalescence standard (Spearman ρ = 0.804). Repeatability was excellent across technicians and sessions (intra-class correlation coefficient >0.92, coefficient of variation <2%).

The study’s core advance is the discovery of axial-length-stratified cataract phenotypes. In participants with high myopia (axial length ≥26 mm), nuclear cataracts predominated (83.21% versus 39.83% in non-highly myopic eyes) and appeared at markedly younger ages (mean 58 years versus 71 years). Multivariable models further showed divergent risk mechanisms: in non-highly myopic eyes, anterior chamber depth and lens thickness were the principal predictors, consistent with a "compression-thickening" paradigm. In contrast, in highly myopic eyes, axial length and white-to-white distance took precedence, while each additional millimeter of lens thickness conferred roughly seven-fold increased odds of cataract (OR = 7.012). Significant interaction terms (AL × LT, AL × AQD) confirmed that the effect of lens anatomy on cataract risk is modulated by eye length itself.

Because the IOL Master 700 is already standard equipment in cataract clinics, this automated pipeline could embed screening into existing workflows without additional patient burden. The findings support personalized, eye-length-based risk management to improve early detection and surgical timing for the growing global population with severe myopia.

Medicine Plus

10.1016/j.medp.2026.100162

Observational study

Keywords

Article Information

Contact Information

Siyun Qin
Science China Press
qinsiyun@scichina.com

Source

This article is based on a news release from Science China Press. BrightSurf curates and republishes science news from research institutions worldwide; the original release is linked below.

How to Cite This Article

APA:
Science China Press. (2026, September 11). Automated lens density screening exposes myopia's unique cataract signature. Brightsurf News. https://www.brightsurf.com/news/LMJYVDRL/automated-lens-density-screening-exposes-myopias-unique-cataract-signature.html
MLA:
"Automated lens density screening exposes myopia's unique cataract signature." Brightsurf News, Sep. 11 2026, https://www.brightsurf.com/news/LMJYVDRL/automated-lens-density-screening-exposes-myopias-unique-cataract-signature.html.