Pearse Andrew Keane

Cross-Species Adaptation of RETFound for Rodent OCT Age Estimation Reveals Strong CNN Baselines in Data-Scarce Space Biology

This paper benchmarks cross-species adaptation of a human retinal model to rodent OCT for age estimation, finding that CNN baselines outperform transformer models in small-sample settings.

Autoencoder-based phenotyping of ophthalmic images highlights genetic loci influencing retinal morphology and provides epidemiologically informative biomarkers.

The paper uses an autoencoder to derive retinal phenotypes from OCT images, identifies 118 genetic loci, and shows their relevance to retinal morphology and disease prediction.

Feasibility of Automated Deep Learning Design for Medical Image Classification by Healthcare Professionals with Limited Coding Experience

This study evaluates automated deep learning tools for medical image classification by non-experts, showing high performance in some tasks but limitations in external validation and dataset quality.

Forecasting Future Humphrey Visual Fields Using Deep Learning

This study trains a deep learning model to predict future 24-2 Humphrey Visual Fields up to 5.5 years ahead using historical data from glaucomatous patients.