Our analysis demonstrated a high discriminative power, with AUC values of 0.96 for controls, indicating strong identification of healthy cases; 0.99 for CRAO, showing high detection capabilities; and 0.90 for differential diagnoses, indicating a lower yet highly significant effectiveness.
← all excerpts
Automated Detection of Central Retinal Artery Occlusion Using OCT Imaging via Explainable Deep Learning.
1
—
—