Abstract
This chapter proposes a novel method, based on the multivariate parametric statistical tests of hypotheses, which classifies the normal skin lesion images and the various stages of the melanoma images. The melanoma images are categorized into two classes, such as initial stage and advanced stage, based on the degree of aggressiveness of the cancer. The region of interest is identified and segmented from the input skin melanoma image. The features, such as HSV color, shape, and texture, are extracted from the region of interest. The features are treated as a feature space, which is assumed to be a multivariate normal random field. The proposed statistical tests are employed to identify and classify the melanoma images. The proposed method yields an average correct classification up to 91.55% for the normal skin lesion versus the initial and the advanced stages of the melanoma images, up to 91.39% for initial stage melanoma versus the normal skin lesion and the advanced stages melanoma, and up to 92.27% for the advanced stage melanoma versus the normal skin lesion and the initial stage melanoma. The proposed method yields better results.
TopBackground
Despite there are a number of methods available for medical image classification, some methods require high computational complexity for feature extraction and classification (Li & Shen, 2018; Lee et al., 2018; Ma et al., 2017), for instance the method which comprises of deep learning, deep convolutional learning while some other methods follow a lot of procedures for feature extraction (Lee et al., 2018; Ma et al., 2017; Silveria et al., 2009). The medical image classification comprises of image acquisition, preprocessing, feature extraction, classification, and performance evaluation. The pre-processing is a course of actions that is executed on raw image data, in order to achieve a best recital of a data set. It has a significant impact on the performance of the classification algorithm. Data pre-processing phase, in medical image processing, comprises of image cropping, filtering, segmentation, gradient operations and scaling. Feature extraction engages feature estimation and feature selection methods. A considerable number of texture feature extraction methods available in the literature, such as Gabor, Haralick’s, and wavelet histogram, and so on; each of them describes some aspects of image contents. Therefore, feature extraction is a process of analyzing objects and images, which extracts the most prominent features that corresponds to various classes of objects. Therefore, it is worth to state that improving the feature extraction process will improve the performance of a described classification algorithm.