AI combined with polarization-sensitive OCT enables earlier and more accurate detection of subclinical keratoconus compared to standard tomography.
Key Details
- 1Researchers analyzed imaging data from 359 eyes using PS-OCT and compared it with two widespread corneal tomography devices (Pentacam, MS-39).
- 2AI models built on PS-OCT data were more effective in classifying subclinical keratoconus than shape-based tomography models.
- 3PS-OCT focuses on corneal collagen organization and sublayer thickness, revealing microstructural changes not captured by conventional imaging.
- 4Healthy and established keratoconus cases were classified similarly by all models; the main difference appeared for subclinical eyes.
- 5The research suggests PS-OCT provides complementary information to current imaging, improving the confidence of early keratoconus diagnosis.
Why It Matters
Detecting keratoconus at its subclinical stage can prevent progression and support safer refractive surgery decisions. Integrating advanced high-resolution imaging with AI may transform early eye disease diagnosis, reduce false positives in at-risk patients, and inform more precise clinical management.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.