Feature extraction and machine learning techniques for Melanoma recognition by using dermoscopy images

Muhammad Farid Omar

Publication:

Feature extraction and machine learning techniques for Melanoma recognition by using dermoscopy images

dc.contributor.author	Muhammad Farid Omar
dc.date.accessioned	2024-05-20T07:19:14Z
dc.date.available	2024-05-20T07:19:14Z
dc.date.issued	2021
dc.description.abstract	Melanoma is a potentially life-threatening neoplasm or a skin cancer that only exist on skin surface of human body. It was manifested by the growing, unusual-looking skin lesion, of the odd-shaped, uneven, or uncertain borders and multiple colors in advanced cases. Thin melanomas a few millimeters in diameter can mimic benign nevi and cannot be detected by the normal eye’s examination. The only possibility to diagnose them is using the dermoscopy as a tool. Early recognition and surgical excision can be curative for the patient. The help of technology such as data mining and machine learning can improve the diagnosis accuracy. Thus, in this work a preprocessing of dermatology cancer recognition is proposed. Several experiments were performed on MIAS databases. Single Segmentation Based Fractal Analysis (SFTA), Gray Level Co-Occurrence Matrix (GLCM), Gabor filter and Hu Moment vector feature extraction information yielded a good recognition result. However, by a combination of features gives higher results of more than 90% on five different classifiers with various algorithms such as k-Nearest Neighbors (kNN), Fuzzy k-Nearest Neighbors (FkNN), Linear Discriminat Analysis (LDA) and Feed Forward Neural Network (FFNN) with different performance measurement such as Sensitivity, Specificity, Accuracy, Area under Curve (AUC), Cohen's kappa (k), Precession and F-Measure.
dc.identifier.uri	https://hdl.handle.net/20.500.14170/2695
dc.language.iso	en
dc.subject	Melanoma
dc.subject	Dermoscopy
dc.subject	Melanoma recognition
dc.title	Feature extraction and machine learning techniques for Melanoma recognition by using dermoscopy images
dc.type	Resource Types::text::thesis::master thesis
dspace.entity.type	Publication
oairecerif.author.affiliation	#PLACEHOLDER_PARENT_METADATA_VALUE#