The Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks.

Massimo Salvi,Valentina Romano,Kristen M. Meiburger,Vanessa Tarantino,Silvia Seoni,Elisa Zavattaro,Francesco Branciforti,Paola Savoia,Federica Veronese

doi:10.3390/diagnostics11030451

Abstract

Background. The use of teledermatology has spread over the last years, especially during the recent SARS-Cov-2 pandemic. Teledermoscopy, an extension of teledermatology, consists of consulting dermoscopic images, also transmitted through smartphones, to remotely diagnose skin tumors or other dermatological diseases. The purpose of this work was to verify the diagnostic validity of images acquired with an inexpensive smartphone microscope (NurugoTM), employing convolutional neural networks (CNN) to classify malignant melanoma (MM), melanocytic nevus (MN), and seborrheic keratosis (SK). Methods. The CNN, trained with 600 dermatoscopic images from the ISIC (International Skin Imaging Collaboration) archive, was tested on three test sets: ISIC images, images acquired with the NurugoTM, and images acquired with a conventional dermatoscope. Results. The results obtained, although with some limitations due to the smartphone device and small data set, were encouraging, showing comparable results to the clinical dermatoscope and up to 80% accuracy (out of 10 images, two were misclassified) using the NurugoTM demonstrating how an amateur device can be used with reasonable levels of diagnostic accuracy. Conclusion. Considering the low cost and the ease of use, the NurugoTM device could be a useful tool for general practitioners (GPs) to perform the first triage of skin lesions, aiding the selection of lesions that require a face-to-face consultation with dermatologists.

Highlights

The term telemedicine derives from the Greek word tele meaning distant
The purpose of this work was to verify the diagnostic validity of images acquired with an inexpensive smartphone microscope (NurugoTM), employing convolutional neural networks (CNN) to classify malignant melanoma (MM), melanocytic nevus (MN), and seborrheic keratosis (SK)
The application of telemedicine to dermatology is known as teledermatology (TD), which can be classified into real-time teledermatology (VTC) and store-and-forward teledermatology (SAF) [1]

Summary

Introduction

The term telemedicine derives from the Greek word tele meaning distant. The application of telemedicine to dermatology is known as teledermatology (TD), which can be classified into real-time teledermatology (VTC) and store-and-forward teledermatology (SAF) [1].VTC consists of a live video consultation with the patient, whereas SAF consists of image transmission from the patient to the teleconsultant as the first step, is followed by a plan of action about diagnosis or management from the consultant. The application of telemedicine to dermatology is known as teledermatology (TD), which can be classified into real-time teledermatology (VTC) and store-and-forward teledermatology (SAF) [1]. TD can be a hybrid and combine elements of real-time and store-and-forward TD; TD can use mobile phones and so is defined as mobile-teledermatology [1]. An extension of TD includes teledermoscopy (TDSC), in which doctors consult dermoscopic images transmitted electronically. With dermoscopic patterns being well established, especially for skin malignancies, the combination of TD with TDSC has shown to get better effectiveness than only TD consultations. Teledermoscopy, an extension of teledermatology, consists of consulting dermoscopic images, transmitted through smartphones, to remotely diagnose skin tumors or other dermatological diseases. Considering the low cost and the ease of use, the NurugoTM device could be a useful tool for general practitioners (GPs) to perform the first triage of skin lesions, aiding the selection of lesions that require a face-to-face consultation with dermatologists

Objectives

Methods

Findings

Discussion

Conclusion