A novel and efficient approach for the classification of skin melanoma
- PDF / 3,272,495 Bytes
- 25 Pages / 595.276 x 790.866 pts Page_size
- 104 Downloads / 152 Views
ORIGINAL RESEARCH
A novel and efficient approach for the classification of skin melanoma A. Sherly Alphonse1 · M. S. Starvin2 Received: 11 April 2020 / Accepted: 25 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Melanoma is a very common type of skin cancer that is an out-of-control growth of the cell. The detection of melanoma is very crucial in clinical practice due to irregularity in the shape of border and difference of tissue. Even though there are several methods proposed in literature, the identification of melanoma is still a complex process. This work proposes a novel Color Local Directional Pattern-based feature extraction technique for the classification of the skin cancer images. Along with the Color Local Directional Pattern this work also uses various descriptors for shape, color and Pyramid Histogram of Oriented Gradients. This method also uses a stacked Restricted Boltzmann Machine in Deep Belief Network, Support Vector Machine and Random Forest classifier for the classification. The experiments used the images from International Skin Imaging Collaboration (ISIC) 2016, ISIC 2017, Pedro Hispano Hospital (PH2) dataset, Dermnet and DermIS datasets. The performance metrics like specificity, sensitivity, F-Score, positive predictive value, accuracy, harmonic mean, and Area Under the Curve (AUC) are used for the experimental analysis. The results show that the proposed work achieves best results while using the combination of texture, color and shape descriptors and stacked RBM in DBN. Keywords Feature extraction · Image classification · Melanoma · Skin,rbm
1 Introduction Cancer is seen most prevalently in human and there are over 100 categories of cancer. The tumors can grow and intrude the way of the digestive, nervous and circulatory systems. The hormones generated also affect the function of breast, lung and skin etc. Aging, exposure to ultra-violet rays and usage of harmful chemicals are the main causes of skin cancer. Melanoma is a form of skin cancer which is a destructive one and very dangerous. Non-melanoma is a type of skin cancer that is very common. Melanoma ranks 19 among the most common cancer types and 300,000 new cases were found in 2018. Almost, 2490 females and 4740 males have died due to melanoma in the year 2019 (Siegel et al. 2019). It can be seen that among 2 to 3 million people every year, nearly 40% people are affected by non-melanoma. It can be seen very commonly in the people having very light * A. Sherly Alphonse [email protected] M. S. Starvin [email protected] 1
Ponjesly College of Engineering, Nagercoil, India
University College of Engineering, Nagercoil 629004, India
2
skin. The mortality rate of the people can be reduced by predicting the cancer earlier. This also aids in a better treatment of the patient. Skin cancers are formed due to the abnormality of the cells and they also spread to the other parts of the body (de Gruul et al. 1980). There are three main categories in skin cancer in the PH2 dataset. They are common
Data Loading...
