Dermoscopy in Europe: coming of age

Dermoscopy Use in Africa: Determinants and Challenges

INTRODUCTION

Dermoscopy has evolved over the years beyond distinguishing benign pigmented lesions from melanoma to diagnosing virtually all diseases in dermatology. Overwhelming evidence demonstrates its utility in improving diagnostic accuracy, reducing unnecessary biopsies and lesion monitoring. Dermoscopy is widely used in Western nations, hence most descriptions of lesions in literature are predominantly on Fitzpatrick skin types I-III. Current evidence shows that there are unique dermoscopic features in the dark skin as a result of pigment and pathological reactions. Nationwide surveys and reports have been conducted across several continents to highlight prevalence and factors influencing dermoscopy use with the hope of maximizing its apparent benefits. There are currently no such reports from Africa.

OBJECTIVES

To evaluate dermoscopy use and its determinants among dermatologists in Africa.

METHODS

A cross-sectional study. Online forms were e-mailed to individual practicing dermatologists and members of the African Society of Dermatologists and Venereologists.

RESULTS

There were 196 respondents from 24 African countries. Half of them used dermoscopy. Training, practice settings and location, provision of dermatoscopes by institutions and knowledge of criteria were notable significant determinants. Multiple training exposures, knowledge of criteria, availability of dermatoscopes, use of both hand-held and videodermatoscopes, average number of patients seen per day, and a positive outlook towards dermoscopy were significant determinants of frequency of use. Leading impediments were lack of training and inadequate dermatoscopes in practice.

CONCLUSIONS

Dermoscopy use in Africa is relatively low. Incorporating dermoscopy training into the curriculum with provision of dermatoscopes by training institutions will promote wider usage.

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

Simple Summary

Malignant melanomas (MMs) with aypical clinical presentation constitute a diagnostic pitfall, and false negatives carry the risk of a diagnostic delay and improper disease management. Among the most common, challenging presentation forms of MMs are those that clinically resemble seborrheic keratosis (SK). On the other hand, SK may mimic melanoma, producing ‘false positive overdiagnosis’ and leading to needless excisions. The evolving efficiency of deep learning algorithms in image recognition and the availability of large image databases have accelerated the development of advanced computer-aided systems for melanoma detection. In the present study, we used image data from the International Skin Image Collaboration archive to explore the capacity of deep knowledge transfer in the challenging diagnostic task of the atypical skin tumors of MM and SK.

Abstract

Malignant melanomas resembling seborrheic keratosis (SK-like MMs) are atypical, challenging to diagnose melanoma cases that carry the risk of delayed diagnosis and inadequate treatment. On the other hand, SK may mimic melanoma, producing a ‘false positive’ with unnecessary lesion excisions. The present study proposes a computer-based approach using dermoscopy images for the characterization of SΚ-like MMs. Dermoscopic images were retrieved from the International Skin Imaging Collaboration archive. Exploiting image embeddings from pretrained convolutional network VGG16, we trained a support vector machine (SVM) classification model on a data set of 667 images. SVM optimal hyperparameter selection was carried out using the Bayesian optimization method. The classifier was tested on an independent data set of 311 images with atypical appearance: MMs had an absence of pigmented network and had an existence of milia-like cysts. SK lacked milia-like cysts and had a pigmented network. Atypical MMs were characterized with a sensitivity and specificity of 78.6% and 84.5%, respectively. The advent of deep learning in image recognition has attracted the interest of computer science towards improved skin lesion diagnosis. Open-source, public access archives of skin images empower further the implementation and validation of computer-based systems that might contribute significantly to complex clinical diagnostic problems such as the characterization of SK-like MMs.