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.
Scheda prodotto non validato
Scheda prodotto in fase di analisi da parte dello staff di validazione
Titolo: | Artificial Neural Network for Glaucoma Diagnosis Using Spectral Domain OCT |
Autori: | |
Anno: | 2012 |
Citazione: | 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. |
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. |
Handle: | http://hdl.handle.net/11365/41676 |
Appare nelle tipologie: | 4.3 Poster |
File in questo prodotto:
http://hdl.handle.net/11365/41676