Frontiers in Communications and Networks (Jun 2024)

Health of Things Melanoma Detection System—detection and segmentation of melanoma in dermoscopic images applied to edge computing using deep learning and fine-tuning models

  • José Jerovane Da Costa Nascimento,
  • José Jerovane Da Costa Nascimento,
  • Adriell Gomes Marques,
  • Adriell Gomes Marques,
  • Yasmim Osório Adelino Rodrigues,
  • Yasmim Osório Adelino Rodrigues,
  • Guilherme Freire Brilhante Severiano,
  • Guilherme Freire Brilhante Severiano,
  • Icaro de Sousa Rodrigues,
  • Icaro de Sousa Rodrigues,
  • Carlos Dourado,
  • Carlos Dourado,
  • Luís Fabrício De Freitas Souza,
  • Luís Fabrício De Freitas Souza

DOI
https://doi.org/10.3389/frcmn.2024.1376191
Journal volume & issue
Vol. 5

Abstract

Read online

According to the World Health Organization (WHO), melanoma is a type of cancer that affects people globally in different parts of the human body, leading to deaths of thousands of people every year worldwide. Intelligent diagnostic tools through automatic detection in medical images are extremely effective in aiding medical diagnosis. Computer-aided diagnosis (CAD) systems are of utmost importance for image-based pre-diagnosis, and the use of artificial intelligence–based tools for monitoring, detection, and segmentation of the pathological region are increasingly used in integrated smart solutions within smart city systems through cloud data processing with the use of edge computing. This study proposes a new approach capable of integrating into computational monitoring and medical diagnostic assistance systems called Health of Things Melanoma Detection System (HTMDS). The method presents a deep learning–based approach using the YOLOv8 network for melanoma detection in dermatoscopic images. The study proposes a workflow through communication between the mobile device, which extracts captured images from the dermatoscopic device and uploads them to the cloud API, and a new approach using deep learning and different fine-tuning models for melanoma detection and segmentation of the region of interest, along with the cloud communication structure and comparison with methods found in the state of the art, addressing local processing. The new approach achieved satisfactory results with over 98% accuracy for detection and over 99% accuracy for skin cancer segmentation, surpassing various state-of-the-art works in different methods, such as manual, semi-automatic, and automatic approaches. The new approach demonstrates effective results in the performance of different intelligent automatic models with real-time processing, which can be used in affiliated institutions or offices in smart cities for population use and medical diagnosis purposes.

Keywords