Skin Lesion Segmentation and Multiclass Classification Using Deep Learning Features and Improved Moth Flame Optimization

Diagnostics

Rytis Maskeliūnas¹  MuhammadAttique Khan²  Muhammad Sharif²  Tallha Akram³  Robertas Damaševičius⁴ 

[1] Department of Applied Informatics, Vytautas Magnus University, 44404 Kaunas, Lithuania;Department of Computer Science, Wah Campus, COMSATS University Islamabad, Wah Cantonment 47040, Pakistan;Department of Electrical Engineering, Wah Campus, COMSATS University Islamabad, Islamabad 45550, Pakistan;Faculty of Applied Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland;

关键词: skin cancer;    melanoma;    heuristic feature optimization;    moth flame optimization;    deep features;    feature fusion;   

DOI  :  10.3390/diagnostics11050811

来源: DOAJ

【 摘 要 】

Manual diagnosis of skin cancer is time-consuming and expensive; therefore, it is essential to develop automated diagnostics methods with the ability to classify multiclass skin lesions with greater accuracy. We propose a fully automated approach for multiclass skin lesion segmentation and classification by using the most discriminant deep features. First, the input images are initially enhanced using local color-controlled histogram intensity values (LCcHIV). Next, saliency is estimated using a novel Deep Saliency Segmentation method, which uses a custom convolutional neural network (CNN) of ten layers. The generated heat map is converted into a binary image using a thresholding function. Next, the segmented color lesion images are used for feature extraction by a deep pre-trained CNN model. To avoid the curse of dimensionality, we implement an improved moth flame optimization (IMFO) algorithm to select the most discriminant features. The resultant features are fused using a multiset maximum correlation analysis (MMCA) and classified using the Kernel Extreme Learning Machine (KELM) classifier. The segmentation performance of the proposed methodology is analyzed on ISBI 2016, ISBI 2017, ISIC 2018, and PH2 datasets, achieving an accuracy of 95.38%, 95.79%, 92.69%, and 98.70%, respectively. The classification performance is evaluated on the HAM10000 dataset and achieved an accuracy of 90.67%. To prove the effectiveness of the proposed methods, we present a comparison with the state-of-the-art techniques.

【 授权许可】

Unknown