Simple But Efficient Approach for Image Based Skin Cancer Diagnosis

The impact and influence of digital images on modern society are enormous, and image processing is now a crucial component of science and technology. The quick progress in computer-based medical image reconstruction, and the associated developments in analysis methods and computerized diagnosis, hav...

Full description

Saved in:
Bibliographic Details
Published in2018 15th International Multi-Conference on Systems, Signals & Devices (SSD) pp. 274 - 280
Main Authors Smaoui, Nadia, Derbel, Nabil
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2018
Subjects
Feature extraction
Hair
Image edge detection
Lesions
Melanoma
Skin
Online AccessGet full text

Cover

More Information
Summary:The impact and influence of digital images on modern society are enormous, and image processing is now a crucial component of science and technology. The quick progress in computer-based medical image reconstruction, and the associated developments in analysis methods and computerized diagnosis, have brought medical imaging into one of the most important sub-fields in scientific imaging. In this context, our paper fits. The work presents a simple method for a preprocessing and an automatic detection of the area of interest in order to make the necessary diagnosis. The proposed approach has been applied for the detection of melanoma. Once detected, the ABeD rule can be applied to conclude on the malignancy of the lesion. The proposed approach is implemented in MATLAB environment and the experiment is based on a PH2 database containing suspicious melanoma skin cancer. Based on the experiment, the accuracy of the developed approach is 92 %, which reflects its reliability.
ISSN:2474-0446
DOI:10.1109/SSD.2018.8570526