In this study, we trained a neural network to perform automatic grading of digital images of acne patients with reliabilities comparable or superior to those of expert physicians. A dedicated device was employed to acquire images of 479 patients belonging to three different ethnic groups. A convolutional neural network trained with features extracted from local patches extracted from the facial skin showed an accuracy of 0.85 and a correlation between manual evaluation and automatized IGA of r=0.96. This is the first work where a neural network was able to directly classify acne patients according to an ordinal scale with no human intervention and no need to count lesions.
Automatic grading of Acne vulgaris using deep learning / Melina, A.; Ngo Dinh, N.; Tafuri, B.; De Vitis, S.; Schipani, G.; Nisticò, S.; Cosentino, C.; Amato, F.; Cherubini, A.. - (2018), pp. 1-4. (Intervento presentato al convegno GNB 2018, the Sixth National Congress of Bioengineering tenutosi a Milano, Italy nel 25-27 Giugno 2018).
Automatic grading of Acne vulgaris using deep learning
F. Amato;
2018
Abstract
In this study, we trained a neural network to perform automatic grading of digital images of acne patients with reliabilities comparable or superior to those of expert physicians. A dedicated device was employed to acquire images of 479 patients belonging to three different ethnic groups. A convolutional neural network trained with features extracted from local patches extracted from the facial skin showed an accuracy of 0.85 and a correlation between manual evaluation and automatized IGA of r=0.96. This is the first work where a neural network was able to directly classify acne patients according to an ordinal scale with no human intervention and no need to count lesions.File | Dimensione | Formato | |
---|---|---|---|
GNB_2018_Paper_209.pdf
non disponibili
Descrizione: Articolo principale
Tipologia:
Documento in Post-print
Licenza:
Accesso privato/ristretto
Dimensione
20.81 MB
Formato
Adobe PDF
|
20.81 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.