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

Linda Tognetti, Simone Bonechi, Paolo Andreini, Monica Bianchini, Franco Scarselli, Gabriele Cevenini, Elvira Moscarella, Francesca Farnetani, Caterina Longo, Aimilios Lallas, Cristina Carrera, Susana Puig, Danica Tiodorovic, Jean Luc Perrot, Giovanni Pellacani, Giuseppe Argenziano, Elisa Cinotti, Gennaro Cataldo, Alberto Balistreri, Alessandro MecocciMarco Gori, Pietro Rubegni, Alessandra Cartocci

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish
Pages (from-to)115-122
Number of pages8
JournalJournal of Dermatological Science
Volume101
Issue number2
DOIs
Publication statusPublished - Feb 2021

Keywords

  • Cutaneous melanoma
  • Deep convolutional neural network
  • Deep learning
  • Dermoscopy
  • Integrated diagnosis
  • Non-invasive imaging

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Dermatology

Fingerprint

Dive into the research topics of 'A new deep learning approach integrated with clinical data for the dermoscopic differentiation of early melanomas from atypical nevi'. Together they form a unique fingerprint.

Cite this