Deep learning based an automated skin lesion segmentation and intelligent classification model
- PDF / 2,196,988 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 67 Downloads / 207 Views
ORIGINAL RESEARCH
Deep learning based an automated skin lesion segmentation and intelligent classification model Mohamed Yacin Sikkandar1 · Bader Awadh Alrasheadi2 · N. B. Prakash3 · G. R. Hemalakshmi4 · A. Mohanarathinam5 · K. Shankar6 Received: 30 March 2020 / Accepted: 5 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Internet of Medical Things (IoMT) includes interconnected sensors, wearable devices, medical devices, and clinical systems. At the same time, skin cancer is a commonly available type of cancer that exists all over the globe. This study projects a new segmentation based classification model for skin lesion diagnosis by combining a GrabCut algorithm and Adaptive NeuroFuzzy classifier (ANFC) model. The proposed method involves four main steps: preprocessing, segmentation, feature extraction, and classification. Initially, the preprocessing step is carried out using a Top hat filter and inpainting technique. Then, the Grabcut algorithm is used to segment the preprocessed images. Next, the feature extraction process takes place by the use of a deep learning based Inception model. Finally, an adaptive neuro-fuzzy classifier (ANFC) system gets executed to classify the dermoscopic images into different classes. The proposed model is simulated using a benchmark International Skin Imaging Collaboration (ISIC) dataset and the results are examined interms of accuracy, sensitivity and specificity. The proposed model exhibits better identification and classification of skin cancer. For examining the effective outcome of the projected technique, an extensive comparison of the presented method with earlier models takes place. The experimental values indicated that the proposed method has offered a maximum sensitivity of 93.40%, specificity of 98.70% and accuracy of 97.91%. Keywords IoMT · Skin lesion · Deep learning · Artifact removal · Feature extraction
1 Introduction At present days, Internet of Medical Things (IoMT) is the incorporation of medical gadgets and applications which interconnect healthcare information technology models by the use of networking technologies. It greatly minimizes the unwanted visits to hospitals and reduces the overhead on healthcare systems by linking patients to
the respective doctors and enables them to communicate the medicinal information over a secured network. On the other hand, skin lesion is a commonly available kind of cancer that affects the people around the globe Karimkhani et al. (2017). Diverse kinds of skin cancer like basal cell carcinoma (BCC), melanoma, intraepithelial carcinoma, 1
Department of Medical Equipment Technology, College of Applied Medical Sciences, Majmaah University, Al Majmaah 11952, Saudi Arabia
2
Department of Nursing, College of Applied Medical Sciences, Majmaah University, Al Majmaah 11952, Saudi Arabia
N. B. Prakash [email protected]
3
Department of Electrical and Electronics Engineering, National Engineering College, K.R.Nagar, Kovilpatti, India
G. R. Hemalakshmi [email protected]
Data Loading...
