Towards accurate classification of skin cancer from dermatology images

Abstract

Skin cancer is the most well-known disease found in the individuals who are exposed to the Sun's ultraviolet (UV) radiations. It is identified when skin tissues on the epidermis grow in an uncontrolled manner and appears to be of different colour than the normal skin tissues. This paper focuses on predicting the class of dermascopic images as benign and malignant. A new feature extraction method has been proposed to carry out this work which can extract relevant features from image texture. Local and gradient information from x and y directions of images has been utilized for feature extraction. After that images are classified using machine learning algorithms by using those extracted features. The efficacy of the proposed feature extraction method has been proved by conducting several experiments on the publicly available image dataset 2016 International Skin Imaging Collaboration (ISIC 2016). The classification results obtained by the method are also compared with state-of-the-art feature extraction methods which show that it performs better than others. The evaluation criteria used to obtain the results are accuracy, true positive rate (TPR) and false positive rate (FPR) where TPR and FPR are used for generating receiver operating characteristic curves.

A Hybrid Stacked Restricted Boltzmann Machine with Sobel Directional Patterns for Melanoma Prediction in Colored Skin Images

“…The confusion matrix and the categorization outcomes for the photos from the ISIC 2016 dataset are shown in Table 4 and Table 5 . Compared to LBP (Local Binary Pattern), CLDP (Color Local Directional Pattern) [ 18 , 55 , 56 , 57 , 58 ] has the highest accuracy. The accuracy of 97.2 percent shows that, compared to GLCM [ 59 ], LBP more accurately captures the texture of skin cancer images [ 18 ].…”

“…SDP more successfully recovers the spatial data of the texture, edges, and opponent color information while also removing noise. Other feature descriptors, such as LTP, Color SIFT, Gradient information, CLDP, Color Gabor wavelet, and multi-feature extraction, do not completely reduce the noise [ 8 , 18 , 55 , 56 , 58 ]. In contrast to LBP and additional descriptors used in the existing methods for the diagnosis of skin lesions, SDP is likewise insensitive to changes in light.…”

Weakly supervised skin lesion segmentation based on spot‐seeds guided optimal regions

“…In the past few years, segmentation methods based on digital image processing (DIP) or deep convolutional neural networks (DCNN) have demonstrated remarkable success on dermoscopy images, attracting the attention of a large number of researchers. Most of the previous work on skin lesion image segmentation is based on fully supervised [2][3][4][5][6][7][8] or semisupervised [9]. Typically, DCNN requires pixel-level annotation, but pixel-level annotation of dermoscopy images requires the diagnosis of a large number of professional doctors, which is extremely difficult for collection.…”