Fuzzy description of skin lesions

Abstract

We propose a system for describing skin lesions images based on a human perception model. Pigmented skin lesions including melanoma and other types of skin cancer as well as non-malignant lesions are used. Works on classification of skin lesions already exist but they mainly concentrate on melanoma. The novelty of our work is that our system gives to skin lesion images a semantic label in a manner similar to humans. This work consists of two parts: first we capture they way users perceive each lesion, second we train a machine learning system that simulates how people describe images. For the first part, we choose 5 attributes: colour (light to dark), colour uniformity (uniform to non-uniform), symmetry (symmetric to non-symmetric), border (regular to irregular), texture (smooth to rough). Using a web based form we asked people to pick a value of each attribute for each lesion. In the second part, we extract 93 features from each lesions and we trained a machine learning algorithm using such features as input and the values of the human attributes as output. Results are quite promising, especially for the colour related attributes, where our system classifies over 80% of the lesions into the same semantic classes as humans.

Utility of Non-rule-based Visual Matching as a Strategy to Allow Novices to Achieve Skin Lesion Diagnosis

“…Our view is that as the database increases in size it may become increasingly powerful, assuming that we can order it in a way that is intuitive to the user. This can either be based on ordering of images based on automatically extracted properties ("computer vision"), or user feedback, or some combination ofthe two (21)(22)(23)(24)(25).…”

Viewing Exemplars of Melanomas and Benign Mimics of Melanoma Modestly Improves Diagnostic Skills in Comparison with the ABCD Method and Other Image-based Methods for Lay Identification of Melanoma

“…These include asymmetry (A), border regularity (B) and colour variation (C) of the lesion and (D) diameter, and in some instances, information about whether the lesion is elevated or is evolving (E). A number of publications have challenged the efficacy of such ABCD(E) approaches both on theoretical and empirical grounds (13)(14)(15)(16)(17)(18). Alternative approaches have made greater use of images, in which examples of melanomas (with or without benign lesions) are provided to subjects, with the hypothesis that non-experts will be able to use these exemplars to improve their ability to distinguish between melanoma and mimics of melanoma (13,(18)(19)(20)(21)(22).…”

Melanoma Detection From Lesion Images Using Optimized Features Selected by Metaheuristic Algorithms

“…With traditional features, Laskaris (Laskaris, Ballerini, Fisher, Aldridge, & Rees, 2010) and McDonagh (McDonagh, Fisher, & Rees, 2008) using Dermofit dataset classified into the malignant and benign lesions and achieved classification accuracy of 80.64% and 83.7% using 31 and 234 images respectively. Mukherjee et al (Mukherjee, Adhikari, & Roy, 2018d) done a work with only top level 163 features, where all the 163 features have highest ranks in four types of different feature ranking algorithms and found a classification accuracy of 86.2% is found using Dermofit dataset.…”