What is it about?

Medical diagnosis of melanoma is becoming more complex in recent years, with doctors focusing on making both earlier and accurate diagnoses to save patients’ lives. In this paper, we propose a fuzzy ontology–based melanoma diagnosis system. A fuzzy classifier is proposed to cope with the qualitative description of experts. Then, a fuzzy inference system is proposed to generate the decision. We have used both optical and dermoscopic images from two public datasets to validate our proposed system.

Featured Image

Why is it important?

we propose a fuzzy ontology–based melanoma diagnosis system. A fuzzy classifier is proposed to cope with the qualitative description of experts. Then, a fuzzy inference system is proposed to generate the decision. Experimental validation is undertaken on both optical and dermoscopic images from public datasets DermQuest, Dermatology Information System, and International Skin Imaging Collaboration (ISIC). For optical images, we get a sensitivity of 91 %, a specificity of 88 %, and an accuracy of 90 %, whereas for dermoscopic images, we obtain a sensitivity of 92 % and 91 %, a specificity of 91 % and 93 %, and an accuracy of 91 % and 92 % for ISIC 2016 and ISIC 2017, respectively. A comparative study with existing approaches shows that these performances ensure higher accuracy rates and the best compromise between sensitivity and specificity.

Perspectives

Our future work involves a collection of a big optical lesion image data set for enabling the application of deep learning and artificial intelligence–based melanoma CAD system.

Wiem ABBES
National Engineering School of Sfax (ENIS)

Read the Original

This page is a summary of: Fuzzy Ontology for Automatic Skin Lesion Classification, Journal of Testing and Evaluation, January 2021, ASTM International,
DOI: 10.1520/jte20200134.
You can read the full text:

Read

Contributors

The following have contributed to this page