Abstract

Computer-aided systems for skin lesion diagnosis is a growing area of research. Recently, researchers have shown an increasing interest in developing computer-aided diagnosis systems. This paper aims to review, synthesize and evaluate the quality of evidence for the diagnostic accuracy of computer-aided systems. This study discusses the papers published in the last five years in ScienceDirect, IEEE, and SpringerLink databases. It includes 53 articles using traditional machine learning methods and 49 articles using deep learning methods. The studies are compared based on their contributions, the methods used and the achieved results. The work identified the main challenges of evaluating skin lesion segmentation and classification methods such as small datasets, ad hoc image selection and racial bias.

Highlights

  • The annual incidence of melanoma cases has increased by 53%

  • Despite the fact that melanoma is one of the deadliest types of skin cancer, early identification can lead to a high chance of survival

  • We have looked for systematic reviews and original research papers written in English in the ScienceDirect, IEEE, and SpringerLink databases

Read more

Summary

Introduction

The annual incidence of melanoma cases has increased by 53%. This is due in part to increased ultraviolet (UV) exposure [1]. Despite the fact that melanoma is one of the deadliest types of skin cancer, early identification can lead to a high chance of survival. Cancer develops when cells in the body begin to proliferate uncontrollably. Metastasizing means that cancerous cells may form in practically any place of the body and spread [2]. In this regard, the uncontrolled proliferation of abnormal skin cells is referred to as skin cancer. Uncorrected DNA damage to skin cells, most typically produced by UV radiation from the sun or tanning beds, creates mutations, or genetic flaws, that cause skin cells to reproduce rapidly and produce malignant tumors

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call