Deep Learning–Based SD-OCT Layer Segmentation Quantifies Outer Retina Changes in Patients With Biallelic RPE65 Mutations Undergoing Gene Therapy
2025

Deep Learning for Analyzing Retina Changes in Gene Therapy Patients

Sample size: 116 publication 10 minutes Evidence: moderate

Author Information

Author(s): German Pinedo-Diaz, Birgit Lorenz, Sandrine H. Künzel, Sarah Thiele, Susana Ortega-Cisneros, Eduardo Bayro Corrochano, Frank G. Holz, Alexander Effland

Primary Institution: Center for Research and Advanced Studies, Cinvestav, Zapopan, Mexico

Hypothesis

Can deep learning-based segmentation quantify outer retina changes in patients with RPE65 mutations undergoing gene therapy?

Conclusion

The study shows that automated analysis can reveal significant structural differences in the outer retina of patients undergoing gene therapy.

Supporting Evidence

  • Significant differences in EZ biomarkers were found between RPE65-IRD patients and healthy controls.
  • EZ thickness and granularity changes were significant in adults but not in pediatric patients.
  • Automated segmentation allows for efficient analysis of retinal changes over time.

Takeaway

Researchers used computers to look at pictures of the eye to see how a special treatment helps kids and adults with a certain eye problem.

Methodology

The study used deep learning to analyze SD-OCT scans and quantify five biomarkers of the ellipsoid zone in patients with RPE65-IRD.

Potential Biases

Manual segmentation variability could introduce bias.

Limitations

The study had a small dataset and potential effects on OCT scans from high myopia.

Participant Demographics

Average age was 22.87 years, with 68 males and 48 females.

Statistical Information

P-Value

<0.0013

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1167/iovs.66.1.5

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication