A new deep learning approach integrated with clinical data for the dermoscopic differentiation of early melanomas from atypical nevi

•The diagnosis of Atypical melanocytic skin lesions (aMSL) is worldwide challenging.•Deep convolutional neural network (DCNN) provide high accuracy in image recognition.•We developed the first hybrid DCNN model trained with aMSL images and clinical data (maximum diameter, site, age, sex).•Dermoscopi...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of dermatological science Vol. 101; no. 2; pp. 115 - 122
Main Authors:	Tognetti, Linda, Bonechi, Simone, Andreini, Paolo, Bianchini, Monica, Scarselli, Franco, Cevenini, Gabriele, Moscarella, Elvira, Farnetani, Francesca, Longo, Caterina, Lallas, Aimilios, Carrera, Cristina, Puig, Susana, Tiodorovic, Danica, Perrot, Jean Luc, Pellacani, Giovanni, Argenziano, Giuseppe, Cinotti, Elisa, Cataldo, Gennaro, Balistreri, Alberto, Mecocci, Alessandro, Gori, Marco, Rubegni, Pietro, Cartocci, Alessandra
Format:	Journal Article
Language:	English
Published:	Netherlands Elsevier B.V 01.02.2021
Subjects:	Cutaneous melanoma Deep convolutional neural network Deep learning Dermoscopy Integrated diagnosis Non-invasive imaging DCNN_aMSL ST Cutaneous melanoma ROC aMSL EM DCNNs Dermoscopy Non-invasive imaging AN AUC CNNs Deep learning SE Deep convolutional neural network SP iDCNN_aMSL Integrated diagnosis
ISSN:	0923-1811, 1873-569X, 1873-569X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!