1. A new deep learning approach integrated with clinical data for the dermoscopic differentiation of early melanomas from atypical nevi
- Author
-
Alessandra Cartocci, Danica Tiodorovic, Marco Gori, Susana Puig, Elvira Moscarella, Jean-Luc Perrot, Francesca Farnetani, Monica Bianchini, Aimilios Lallas, Linda Tognetti, Cristina Carrera, Pietro Rubegni, Alberto Balistreri, Alessandro Mecocci, Giuseppe Argenziano, Caterina Longo, Simone Bonechi, Gennaro Cataldo, Elisa Cinotti, Gabriele Cevenini, Franco Scarselli, Giovanni Pellacani, Paolo Andreini, Tognetti, L., Bonechi, S., Andreini, P., Bianchini, M., Scarselli, F., Cevenini, G., Moscarella, E., Farnetani, F., Longo, C., Lallas, A., Carrera, C., Puig, S., Tiodorovic, D., Perrot, J. L., Pellacani, G., Argenziano, G., Cinotti, E., Cataldo, G., Balistreri, A., Mecocci, A., Gori, M., Rubegni, P., and Cartocci, A.
- Subjects
Male ,0301 basic medicine ,Skin Neoplasms ,Cutaneous melanoma, Dermoscopy, Deep convolutional neural network, Deep learning, Non-invasive imaging, Integrated diagnosis ,Datasets as Topic ,Biochemistry ,030207 dermatology & venereal diseases ,0302 clinical medicine ,Non-invasive imaging ,Medicine ,Child ,Melanoma ,Skin ,Aged, 80 and over ,Training set ,Middle Aged ,Child, Preschool ,Female ,Deep convolutional neural network ,Skin lesion ,Cutaneous melanoma ,Adult ,Noninvasive imaging ,medicine.medical_specialty ,Adolescent ,Dermoscopy ,Dermatology ,Diagnosis, Differential ,Young Adult ,03 medical and health sciences ,Integrated diagnosis ,Image Interpretation, Computer-Assisted ,Humans ,Nevus ,Molecular Biology ,Aged ,Retrospective Studies ,business.industry ,Deep learning ,Infant, Newborn ,Infant ,Reproducibility of Results ,Medical decision making ,Atypical nevus ,030104 developmental biology ,Artificial intelligence ,business ,Integrated diagnosi - Abstract
Background Timely recognition of malignant melanoma (MM) is challenging for dermatologists worldwide and represents the main determinant for mortality. Dermoscopic examination is influenced by dermatologists’ experience and fails to achieve adequate accuracy and reproducibility in discriminating atypical nevi (AN) from early melanomas (EM). Objective We aimed to develop a Deep Convolutional Neural Network (DCNN) model able to support dermatologists in the classification and management of atypical melanocytic skin lesions (aMSL). Methods A training set (630 images), a validation set (135) and a testing set (214) were derived from the idScore dataset of 979 challenging aMSL cases in which the dermoscopic image is integrated with clinical data (age, sex, body site and diameter) and associated with histological data. A DCNN_aMSL architecture was designed and then trained on both dermoscopic images of aMSL and the clinical/anamnestic data, resulting in the integrated “iDCNN_aMSL” model. Responses of 111 dermatologists with different experience levels on both aMSL classification (intuitive diagnosis) and management decisions (no/long follow-up; short follow-up; excision/preventive excision) were compared with the DCNNs models. Results In the lesion classification study, the iDCNN_aMSL achieved the best accuracy, reaching an AUC = 90.3 %, SE = 86.5 % and SP = 73.6 %, compared to DCNN_aMSL (SE = 89.2 %, SP = 65.7 %) and intuitive diagnosis of dermatologists (SE = 77.0 %; SP = 61.4 %). Conclusions The iDCNN_aMSL proved to be the best support tool for management decisions reducing the ratio of inappropriate excision. The proposed iDCNN_aMSL model can represent a valid support for dermatologists in discriminating AN from EM with high accuracy and for medical decision making by reducing their rates of inappropriate excisions.
- Published
- 2021