Skin melanoma classification using ROI and data augmentation with deep convolutional neural networks
- PDF / 1,935,074 Bytes
- 27 Pages / 439.37 x 666.142 pts Page_size
- 35 Downloads / 176 Views
Skin melanoma classification using ROI and data augmentation with deep convolutional neural networks Khalid M. Hosny 1
2
& Mohamed A. Kassem & Mohamed M. Foaud
3
Received: 7 May 2019 / Revised: 30 March 2020 / Accepted: 15 May 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Automatic classification of color images of skin helps clinicians and dermatologists in examining and investigating skin melanoma. In this paper, a new deep convolutional neural network-based classification method is proposed. The proposed method consists of three main steps. First, the input color images of skin are preprocessed where the region of interest (ROI) are segmented. Second, the segmented ROI images are augmented using rotation and translation transformations. Third, different deep convolutional neural network (DCNN) architectures such as Alex-net, ResNet101, and GoogleNet are utilized. The last three layers are dropped out and replaced with new layers to be more appropriate with the task of lesion classification. The performance of the proposed method has been evaluated using three different datasets, MED-NODE, DermIS & DermQuest and ISIC 2017. The proposed DCNN have fine-tuned and trained using 85%, tested and verified using 15% of the overall datasets. The proposed method significantly improved the classification process especially with modified GoogleNet where the classification accuracy was 99.29%, 99.15%, and 98.14% for MED-NODE, DermIS & DermQuest, and ISIC 2017 respectively.
* Khalid M. Hosny [email protected] Mohamed A. Kassem [email protected]
1
Department of Information Technology, Faculty of Computers and Informatics Zagazig University, Zagazig 44519, Egypt
2
Department of Robotics and Intelligent Machines, Faculty of Artificial intelligence, Kafrelshiekh University, Kafrelshiekh 33511, Egypt
3
Department of Electronics and Communication, Faculty of Engineering Zagazig University, Zagazig 44519, Egypt
Multimedia Tools and Applications
Keywords Skin Cancer . Melanoma . Classification . DCNN . SVM . GoogleNet
1 Introduction The computer-based systems for skin lesion inspection and dermal investigation has been extended over the past years to classify and diagnosis dermatology diseases [34]. The automated systems for analyzing and detecting human skin lesions facing different difficulties and complexities such as humidity and seasonally variation of temperature, geographicallybased different diseases, environment-based factors, and hair presences [3]. Developing computer-aided diagnosis (CAD) systems for skin lesion is an active research area where their main target is to create systems that are able to accurately analyze the images of pigmented skin lesions for automated diagnosis of cancerous lesions and consequently assist dermatologist [35]. Accurate classification of color images of skin lesions is the most important challenge in this context [39]. For dermoscopic images, skin lesions are divided into different categories based on the type of disease,
Data Loading...
