Purpose: To design and evaluate the diagnostic performance of a neural network model based on spectral domain OCT parameters for discriminating glaucoma patients. Meth- ods: 196 controls and 154 glaucoma patients underwent imaging with Cirrus OCT. Retinal nerve fiber layer and optic nerve head parameters were included in the neural network model. Results: In the validating set, the neural network yielded a 95% sensitivity and 98.3% specificity. Compared with OCT-provided parameters, the neural network had the largest area under the ROC curve (0.995). Conclusion: The artificial neural network im- proved the diagnostic ability of isolated OCT parameters.
A., F., A. B., P., B., M., L. E., P., P., F., M., F., et al. (2012). Artificial Neural Network for Glaucoma Diagnosis Using Spectral Domain OCT, 216-216.
Artificial Neural Network for Glaucoma Diagnosis Using Spectral Domain OCT
FREZZOTTI, PAOLO;
2012-01-01
Abstract
Purpose: To design and evaluate the diagnostic performance of a neural network model based on spectral domain OCT parameters for discriminating glaucoma patients. Meth- ods: 196 controls and 154 glaucoma patients underwent imaging with Cirrus OCT. Retinal nerve fiber layer and optic nerve head parameters were included in the neural network model. Results: In the validating set, the neural network yielded a 95% sensitivity and 98.3% specificity. Compared with OCT-provided parameters, the neural network had the largest area under the ROC curve (0.995). Conclusion: The artificial neural network im- proved the diagnostic ability of isolated OCT parameters.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/41676
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo