Proposing a hybrid technique of feature fusion and convolutional neural network for melanoma skin cancer detection

Md Mahbubur Rahman; Mostofa Kamal Nasir; Md Nur-A-Alam; Md Saikat Islam Khan

doi:10.1016/j.jpi.2023.100341

Proposing a hybrid technique of feature fusion and convolutional neural network for melanoma skin cancer detection

J Pathol Inform. 2023 Oct 13:14:100341. doi: 10.1016/j.jpi.2023.100341. eCollection 2023.

Authors

Md Mahbubur Rahman^{1

2}, Mostofa Kamal Nasir², Md Nur-A-Alam^{2

3}, Md Saikat Islam Khan^{2

3}

Affiliations

¹ Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Mirpur-2, Dhaka 1216, Bangladesh.
² Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Tangail, Bangladesh.
³ Department of CSE, Dhaka International University, Dhaka 1205, Bangladesh.

Abstract

Skin cancer is among the most common cancer types worldwide. Automatic identification of skin cancer is complicated because of the poor contrast and apparent resemblance between skin and lesions. The rate of human death can be significantly reduced if melanoma skin cancer could be detected quickly using dermoscopy images. This research uses an anisotropic diffusion filtering method on dermoscopy images to remove multiplicative speckle noise. To do this, the fast-bounding box (FBB) method is applied here to segment the skin cancer region. We also employ 2 feature extractors to represent images. The first one is the Hybrid Feature Extractor (HFE), and second one is the convolutional neural network VGG19-based CNN. The HFE combines 3 feature extraction approaches namely, Histogram-Oriented Gradient (HOG), Local Binary Pattern (LBP), and Speed Up Robust Feature (SURF) into a single fused feature vector. The CNN method is also used to extract additional features from test and training datasets. This 2-feature vector is then fused to design the classification model. The proposed method is then employed on 2 datasets namely, ISIC 2017 and the academic torrents dataset. Our proposed method achieves 99.85%, 91.65%, and 95.70% in terms of accuracy, sensitivity, and specificity, respectively, making it more successful than previously proposed machine learning algorithms.

Keywords: Convolutional Neural Network (CNN); Fast Bounding Box (FBB); Histogram-Oriented Gradient (HOG); Hybrid Feature Extractor (HFE); Local Binary Pattern (LBP); Modified Anisotropic Diffusion Filtering (MADF); Speed Up Robust Feature (SURF).