An Accelerated System for Melanoma Diagnosis Based on Subset Feature Selection

Abstract

In this paper we present an accelerated system for diagnosing skin lesions based on digitized dermatoscopic color images. This system is composed mainly of three levels : lesion detection, lesion description (features selection) and decision. The lesion detection level consists in the preprocessing of the lesion image in order to remove the undesired objects from the original image. Then, the extraction of the lesion is done by separating it from the healthy surrounding skin. The lesion description level is based on the extraction of a set of features modeling clinical signs of malignancy. The decision level is based on the produced vector of features scores, which is used as input to a multi-layer perceptron classifier in order to assign the lesion to the class of benign lesions or to the one of malignant melanomas. We focus particularly in this paper on the critical step of the features selection allowing to select a reasonable reduced number of useful features while removing redundant information and approximating the properties of melanoma recognition. This permits to reduce the dimension of the lesion's vector, and consequently the computing time, without a significant loss of information. In fact, a large set of features was investigated by the application of relevant features selection techniques. Then, the number of features for classification was optimised and only five well-selected features were used to cover the discriminatory information about lesions malignancy. With this approach, for reasonably balanced training/test sets, we record a good classification rate of 77:7% in a very promising CPU time.

Symmetry Extraction in High Sensitivity Melanoma Diagnosis

“…Reference Used Databases [13] Melanoma vs. Clark Nevus [16] Melanoma vs. Nevus [22] Melanoma vs. Dysplastic Nevus [25] Melanoma vs. Nevus This proposal Melanoma and Dysplastic Nevus vs. 5 kinds of Nevus…”

“…Noise is mainly represented by hair over the area of lesion which disturbs on contour extraction [24,25]. To remove possible hairs, the algorithm applies morphological operators [26] such as erosion and dilatation.…”

A high performance algorithm to diagnosis of skin lesions deterioration in dermatoscopic images using new feature extraction

“…It has some human effects, psychologic and physical (anesthesia), on the patients, particulary for those with multiple lesions, since it could cause unnecessary surgery. Besides, it has some material effects since it is necessary to pay for operations and hospitalization expenses [5]. Thus computerized diagnosis of pigmented skin lesions is proposed in recent years [6].…”

Search for Resolution Invariant Wavelet Features of Melanoma Learned by a Limited ANN Classifier

“…Article [39] described a multi-layer perceptron classifier for melanoma recognition with accuracy of 77.7%. The number of features for classification was optimised to only five which speeds up the CPU time.…”