Prediction of Dermoscopy Patterns for Recognition of both Melanocytic and Non-Melanocytic Skin Lesions

Abstract

Abstract:A differentiation between all types of melanocytic and non-melanocytic skin lesions (MnM-SK) is a challenging task for both computer-aided diagnosis (CAD) and dermatologists due to the complex structure of patterns. The dermatologists are widely using pattern analysis as a first step with clinical attributes to recognize all categories of pigmented skin lesions (PSLs). To increase the diagnostic accuracy of CAD systems, a new pattern classification algorithm is proposed to predict skin lesions patterns by integrating the majority voting (MV-SVM) scheme with multi-class support vector machine (SVM). The optimal color and texture features are also extracted from each region-of-interest (ROI) dermoscopy image and then these normalized features are fed into an MV-SVM classifier to recognize seven classes. The overall system is evaluated using a dataset of 350 dermoscopy images (50 ROIs per class). On average, the sensitivity of 94%, specificity of 84%, 93% of accuracy and area under the receiver operating curve (AUC) of 0.94 are achieved by the proposed MnM-SK system compared to state-of-the-art methods. The obtained result indicates that the MnM-SK system is successful for obtaining the high level of diagnostic accuracy. Thus, it can be used as an alternative pattern classification system to differentiate among all types of pigmented skin lesions (PSLs).

The role of AI classifiers in skin cancer images

“…Its overall sensitivity and accuracy exceeded RF, Gentle AdaBoost, SVM, k‐NN, Fuzzy NN and systems based on Bagging of Features (BoF) models. Lastly, Abbas et al manipulated image features representative of lesion' patterns to classify pigmented skin tumours, through the use of majority voting with support vector machine, achieving accuracy, sensitivity and specificity values of 93%, 94% and 84%, respectively.…”

The Study of Recognition Methods Based on Wavelet Transform for Melanoma Detection

“…[8], [14], [18], [26], our method DWT [12], [13], [15], [23], [24], [29], [30], [31] GWT [21], [27] CT [19], [20], [25] PCA…”

“…[8], [14], [19], [23], [29] Texture features [24], [25], [26], [28], [31] Color feature [19], [20], [21] Shape features [26], [27] Statistical parameters…”

“…From 2016 -2020: There are twelve published articles in this period. And there is a common dataset used in three articles [23,24,29] from DermQuest and two papers used PH2 dataset [27,31]. In the preprocessing stage, most of these papers applied different image sizes of the same implemented dataset.…”

“…In the preprocessing stage, most of these papers applied different image sizes of the same implemented dataset. Some papers applied the median filter to remove unwanted objects such as air bubbles as in references [20], [23,24]. Amir Reza suggested the hair removal from the images in [22], Spatarshi at [26], Uzma [27] and Akhiyar [31].…”