Related Experiment Video
Updated: Jul 27, 2026
Using Optical Coherence Tomography and Optokinetic Response As Structural and Functional Visual System Readouts in Mice and Rats
Published on: January 10, 2019
AI-Driven Optical Coherence Tomography Biomarkers for Choroidal Neovascularization Assessment in Punctate Inner
Lorenzo Ferro Desideri1, Mathias Gallardo2, Muriel Ott3
1From the Department of Ophthalmology, Inselspital, Bern University Hospital, University of Bern (L.F.D., M.O., S.Y., M.T., M.Z., M.R.M.), Bern, Switzerland; Bern Photographic Reading Center, Inselspital, Bern University Hospital, University of Bern (L.F.D., M.O., M.T., M.Z., M.R.M.), Bern, Switzerland.
Larger lesion volume and longer disease duration predict secondary choroidal neovascularization (CNV) in patients with inflammatory eye conditions like punctate inner choroidopathy (PIC) and multifocal choroiditis (MFC). AI-powered OCT analysis can identify these biomarkers for personalized treatment.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Punctate inner choroidopathy (PIC) and multifocal choroiditis (MFC) are inflammatory eye diseases that can lead to secondary choroidal neovascularization (CNV).
- Identifying biomarkers for CNV development is crucial for timely intervention and improved visual outcomes.
Purpose of the Study:
- To evaluate optical coherence tomography (OCT) biomarkers for the presence and progression of secondary CNV in PIC and MFC using AI-based segmentation.
- To assess the utility of AI in identifying morphological biomarkers and lesion characteristics associated with CNV.
Main Methods:
- A retrospective study analyzed OCT scans from 208 eyes of 156 patients with PIC or MFC.
- Artificial intelligence software (Discovery OCT Biomarker Detector) segmented lesions, measured volumes, and assessed retinal layers.
- Linear mixed effects modeling identified predictive biomarkers for CNV development.
Main Results:
- CNV was present in 72.6% of eyes at baseline and developed in 20 eyes during follow-up.
- CNV-positive eyes had significantly lower best-corrected visual acuity (BCVA) and larger baseline lesion volumes compared to CNV-negative eyes.
- Increased baseline lesion volume and longer disease duration were significantly associated with CNV presence.
Conclusions:
- Larger baseline lesion volume and longer disease duration are key indicators for secondary CNV in PIC and MFC.
- AI-driven OCT analysis shows promise in identifying critical biomarkers for CNV.
- These findings support the development of personalized treatment strategies to improve patient outcomes in inflammatory chorioretinal diseases.
