An analysis for melanoma diagnosis in dermascopic images using integrated segmentation and multiple feature extraction

Abstract

Skin lesions are highly useful in the diagnosis of disease such as chickenpox, keratodermia, melanoma, etc. Early detection of the skin disease is highly complex to the inexperienced dermatologist. The Computer-Aided Diagnosis (CAD) systems facilitated early diagnosis of the skin disease without requiring physical contact with the skin. Computerized image analysis methods are developed for improving the visual interpretation of the dermoscopic images. Computer-based analysis of the skin lesion images is highly significant in the skin cancer prevention. Skin cancer is found to be one of the most common types of deadly cancers among the human beings in the recent years. Computational-based techniques are developed to support the dermatologists for the early diagnosis of skin cancer. Computational analysis of the skin lesions in the dermascopic images is a challenging task due to the difficulties such as low-level of contrast between the lesion and surrounding skin regions, irregular and vague lesion borders, artifacts and poor imaging conditions. This work presents a U-Net based segmentation and multiple feature extraction of the dermascopic images for the efficient diagnosis of skin cancer. The input dermascopic image is preprocessed to remove the noise and hair in the skin image. Fast Independent Component Analysis (FastICA) is applied to the skin images for obtaining the melanin and hemoglobin components. The U-net segmentation is applied to the dermascopic image to separate the cancer region from the background of the skin image newline