Computer-Aided Diagnosis for Early Signs of Skin Diseases Using Multi Types Feature Fusion Based on a Hybrid Deep Learning Model

被引:7
作者
Almuayqil, Saleh Naif [1 ]
Abd El-Ghany, Sameh [1 ,2 ]
Elmogy, Mohammed [3 ]
机构
[1] Jouf Univ, Coll Comp & Informat Sci, Dept Informat Syst, Sakaka 72388, Al Jouf, Saudi Arabia
[2] Mansoura Univ, Fac Comp & Informat, Dept Informat Syst, Mansoura 35516, Egypt
[3] Mansoura Univ, Fac Comp & Informat, Dept Informat Technol, Mansoura 35516, Egypt
关键词
skin disorders' diagnosis; deep learning techniques; computer-aided diagnosis system; multi-label classification;
D O I
10.3390/electronics11234009
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
According to medical reports and statistics, skin diseases have millions of victims worldwide. These diseases might affect the health and life of patients and increase the costs of healthcare services. Delays in diagnosing such diseases make it difficult to overcome the consequences of these types of disease. Usually, diagnosis is performed using dermoscopic images, where specialists utilize certain measures to produce the results. This approach to diagnosis faces multiple disadvantages, such as overlapping infectious and inflammatory skin diseases and high levels of visual diversity, obstructing accurate diagnosis. Therefore, this article uses medical image analysis and artificial intelligence to present an automatic diagnosis system of different skin lesion categories using dermoscopic images. The addressed diseases are actinic keratoses (solar keratoses), benign keratosis (BKL), melanocytic nevi (NV), basal cell carcinoma (BCC), dermatofibroma (DF), melanoma (MEL), and vascular skin lesions (VASC). The proposed system consists of four main steps: (i) preprocessing the input raw image data and metadata; (ii) feature extraction using six pre-trained deep learning models (i.e., VGG19, InceptionV3, ResNet50, DenseNet201, and Xception); (iii) features concatenation; and (iv) classification/diagnosis using machine learning techniques. The evaluation results showed an average accuracy, sensitivity, specificity, precision, and disc similarity coefficient (DSC) of around 99.94%, 91.48%, 98.82%, 97.01%, and 94.00%, respectively.
引用
收藏
页数:16
相关论文
共 30 条
[1]  
A Ameri, 2020, J Biomed Phys Eng, V10, P801, DOI 10.31661/jbpe.v0i0.2004-1107
[2]   A Transfer Learning Evaluation of Deep Neural Networks for Image Classification [J].
Abou Baker, Nermeen ;
Zengeler, Nico ;
Handmann, Uwe .
MACHINE LEARNING AND KNOWLEDGE EXTRACTION, 2022, 4 (01) :22-41
[3]   Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network [J].
Aldhyani, Theyazn H. H. ;
Verma, Amit ;
Al-Adhaileh, Mosleh Hmoud ;
Koundal, Deepika .
DIAGNOSTICS, 2022, 12 (09)
[4]   An enhanced technique of skin cancer classification using deep convolutional neural network with transfer learning models [J].
Ali, Md Shahin ;
Miah, Md Sipon ;
Haque, Jahurul ;
Rahman, Md Mahbubur ;
Islam, Md Khairul .
MACHINE LEARNING WITH APPLICATIONS, 2021, 5
[5]   Developing a Recognition System for Diagnosing Melanoma Skin Lesions Using Artificial Intelligence Algorithms [J].
Alsaade, Fawaz Waselallah ;
Aldhyani, Theyazn H. H. ;
Al-Adhaileh, Mosleh Hmoud .
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2021, 2021
[6]  
Amarathunga A.a.L.C., 2015, Int. J. Sci. Technol. Res., V4, P174
[7]  
[Anonymous], 2017, P 2017 IEEE C COMP V
[8]  
[Anonymous], Rethinking the inception architecture for computer vision
[9]   Computer-Aided Diagnosis of Skin Diseases Using Deep Neural Networks [J].
Bajwa, Muhammad Naseer ;
Muta, Kaoru ;
Malik, Muhammad Imran ;
Siddiqui, Shoaib Ahmed ;
Braun, Stephan Alexander ;
Homey, Bernhard ;
Dengel, Andreas ;
Ahmed, Sheraz .
APPLIED SCIENCES-BASEL, 2020, 10 (07)
[10]   Detection of Skin Cancer Based on Skin Lesion Images Using Deep Learning [J].
Gouda, Walaa ;
Sama, Najm Us ;
Al-Waakid, Ghada ;
Humayun, Mamoona ;
Jhanjhi, Noor Zaman .
HEALTHCARE, 2022, 10 (07)