Abstract
Medical images have made a great contribution to early diagnosis. In this study, a new strategy is presented for analyzing medical images of skin with melanoma and nevus to model, classify and identify lesions on the skin. Machine learning applied to the data generated by first and second order statistics features, Gray Level Co-occurrence Matrix (GLCM), keypoints and color channel information—Red, Green, Blue and grayscale images of the skin were used to characterize decisive information for the classification of the images. This work proposes a strategy for the analysis of skin images, aiming to choose the best mathematical classifier model, for the identification of melanoma, with the objective of assisting the dermatologist in the identification of melanomas, especially towards an early diagnosis.
Highlights
IntroductionMelanoma is the most dangerous type of skin cancer, caused by over production of melanin pigments that change the color and texture of skin, resulting as a dark area on the skin [2]
The skin cancer is among the most common types of cancer in the world [1]
The proposed mechanism of identifying and classifying skin tissue is general; in future work it can be applied to other medical images to verify the results, since the strategy analyzes the texture of the images and reveals their differences according to the parameters set, enabling the image classification
Summary
Melanoma is the most dangerous type of skin cancer, caused by over production of melanin pigments that change the color and texture of skin, resulting as a dark area on the skin [2]. Data indicate that the incidence of melanoma, which is a type of cancer that metastasizes rapidly, has increased alarmingly [3]. Visual analysis is limited by human visual ability, as well as human perception and sensitivity, in addition to the fact that not all melanomas have the same characteristics. The tumor is an exceptional expansion of human cells that reproduce in an unrestricted way and that can be identified by a variation of color and texture of the human tissue under study, making information contained in the images extremely valuable. When partitioned into sub-images by regions of interest, they are able to be properly classified
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
