Dermoscopic image classification using CNN with Handcrafted features

Abstract

Globally skin cancer is one of the main cause of death in humans. Early diagnosis plays a major role in increasing the prevention of death rate caused due to any kind of cancer. Conventional diagnosis of skin cancer is a tedious and time-consuming process. To overcome this an automated skin lesion classification must develop. Automated skin lesion classification is a challenging task due to the fine-grained variability in the visibility of skin lesions. In this work dermoscopic images are obtained from the International Skin Image Collaboration Archive 2016 (ISIC 2016). In the proposed method the analysis and classification of skin lesions is done with the help of a Convolution Neural Network (CNN) along with the hand crafted features of dermoscopic image using Scattered Wavelet Transform as additional input to the fully connected layer of CNN, which leads to an improvement in the accuracy for identifying Melanoma and different skin lesion classification when compared to the other state of the art methods. When raw dermoscopic image is given as an input to the CNN and feature values of segmented dermoscopic image as input to the fully connected layer as an additional information, the proposed method gives a classification accuracy of 98.13% for identification of Melanoma and the accuracy achieved for classification of skin lesions is 93.14% for Melanoma Vs Nevus, 95.4% for Seborrheic Keratosis (SK) vs Squamous Cell Carcinoma (SCC), 96.87% for Melanoma vs Seborrheic Keratosis (SK), 95.65% for Melanoma vs Basal Cell Carcinoma (BCC), 98.5% for Nevus vs Basal Cell Carcinoma(BCC).