Open Access iconOpen Access

ARTICLE

crossmark

Skin Lesion Segmentation and Classification Using Conventional and Deep Learning Based Framework

Amina Bibi1, Muhamamd Attique Khan1, Muhammad Younus Javed1, Usman Tariq2, Byeong-Gwon Kang3, Yunyoung Nam3,*, Reham R. Mostafa4, Rasha H. Sakr5

1 Department of Computer Science, HITEC University, Taxila, Pakistan
2 College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Khraj, Saudi Arabia
3 Department of ICT Convergence, Soonchunhyang University, Asan, 31538, Korea
4 Information Systems Department, Faculty of Computers and Information Sciences, Mansoura University, Mansoura, 35516, Egypt
5 Computer Science Department, Faculty of Computers and Information Sciences, Mansoura University, Mansoura, 35516, Egypt

* Corresponding Author: Yunyoung Nam. Email: email

(This article belongs to the Special Issue: Recent Advances in Deep Learning for Medical Image Analysis)

Computers, Materials & Continua 2022, 71(2), 2477-2495. https://doi.org/10.32604/cmc.2022.018917

Abstract

Background: In medical image analysis, the diagnosis of skin lesions remains a challenging task. Skin lesion is a common type of skin cancer that exists worldwide. Dermoscopy is one of the latest technologies used for the diagnosis of skin cancer. Challenges: Many computerized methods have been introduced in the literature to classify skin cancers. However, challenges remain such as imbalanced datasets, low contrast lesions, and the extraction of irrelevant or redundant features. Proposed Work: In this study, a new technique is proposed based on the conventional and deep learning framework. The proposed framework consists of two major tasks: lesion segmentation and classification. In the lesion segmentation task, contrast is initially improved by the fusion of two filtering techniques and then performed a color transformation to color lesion area color discrimination. Subsequently, the best channel is selected and the lesion map is computed, which is further converted into a binary form using a thresholding function. In the lesion classification task, two pre-trained CNN models were modified and trained using transfer learning. Deep features were extracted from both models and fused using canonical correlation analysis. During the fusion process, a few redundant features were also added, lowering classification accuracy. A new technique called maximum entropy score-based selection (MESbS) is proposed as a solution to this issue. The features selected through this approach are fed into a cubic support vector machine (C-SVM) for the final classification. Results: The experimental process was conducted on two datasets: ISIC 2017 and HAM10000. The ISIC 2017 dataset was used for the lesion segmentation task, whereas the HAM10000 dataset was used for the classification task. The achieved accuracy for both datasets was 95.6% and 96.7%, respectively, which was higher than the existing techniques.

Keywords


Cite This Article

APA Style
Bibi, A., Khan, M.A., Javed, M.Y., Tariq, U., Kang, B. et al. (2022). Skin lesion segmentation and classification using conventional and deep learning based framework. Computers, Materials & Continua, 71(2), 2477-2495. https://doi.org/10.32604/cmc.2022.018917
Vancouver Style
Bibi A, Khan MA, Javed MY, Tariq U, Kang B, Nam Y, et al. Skin lesion segmentation and classification using conventional and deep learning based framework. Comput Mater Contin. 2022;71(2):2477-2495 https://doi.org/10.32604/cmc.2022.018917
IEEE Style
A. Bibi et al., “Skin Lesion Segmentation and Classification Using Conventional and Deep Learning Based Framework,” Comput. Mater. Contin., vol. 71, no. 2, pp. 2477-2495, 2022. https://doi.org/10.32604/cmc.2022.018917

Citations




cc Copyright © 2022 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 2759

    View

  • 1608

    Download

  • 0

    Like

Share Link