Comparison Between Convolutional Neural Network CNN and SVM in Skin Cancer Images Recognition

Zaid Ghazi Hadi; Ahmed R. Ajel; Ayad Q. Al-Dujaili

doi:10.51173/jt.v3i4.390

Authors

Zaid Ghazi Hadi Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq
Ahmed R. Ajel Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq
Ayad Q. Al-Dujaili Electrical Engineering Technical College, Middle Technical University, Baghdad, Iraq

DOI:

https://doi.org/10.51173/jt.v3i4.390

Keywords:

Convolutional Neural Networks (CNN), skin cancer, support vector machine (SVM), lesion classification, melanoma classification, DLNN, residual network (ResNet-50)

Abstract

As compared with benign, the common human malignancy of skin cancer can be diagnosed visually starting from clinical screening and ending with histopathological examination. Accurate automatic classification of skin lesion images is a great challenge as the image features are very close in these images. In this paper we used two methods for image recognition. The first method was carried out with Convolution neural networks (CNN) that promise to provide a potential classifier for skin lesions. This work presents a dermatologist-level classification of skin cancer by using residual network (ResNet-50) as a deep learning convolutional neural network (DLCNN) that maps images to class labels. It presents a classifier with a single CNN to automatically recognize benign and malignant skin images. As for the second method, we used the Support Vector Machine. Which is a supervised learning algorithm and it is used for classification of data for the different classes based on a separating hyperplane. The network inputs are only disease labels and image pixels. About 320 clinical images of the different diseases have been used to train the CNN. The model performance has been tested with untrained images from the two labels. This model identifies the most common skin cancers and can be updated with a new unlimited number of images. The DLCNN was trained by the ResNet-50 model and it showed good classification of the benign and malignant skin categories. The ResNet-50 as a DLCNN has achieved a significant recognition rate of more than 97% on the testing images, which proves that the benign and malignant lesion skin images are properly classified. Support vector machine (SVM) classifier for the classification of skin cancer, for the feature extraction step achieved 86.9% accuracy. This means in CNN; we had more accuracy with 11%. These results were attained using MATLAB.

Downloads

Download data is not yet available.

References

K. G. Paulson et al., “Age-Specific Incidence of Melanoma in the United States,” JAMA Dermatology, 2020.

ACS, “Key Statistics for Basal and Squamous Cell Skin Cancers,” Am. Cancer Soc., 2019.

A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, 2017.

M. N. Bajwa et al., “Computer-aided diagnosis of skin diseases using deep neural networks,” Appl. Sci., 2020.

R. Zell et al., “ICTV virus taxonomy profile: Picornaviridae,” J. Gen. Virol., 2017.

S. W. Kashem, M. Haniffa, and D. H. Kaplan, “Antigen-presenting cells in the skin,” Annual Review of Immunology. 2017.

R. H. Abiyev and A. Helwan, “Fuzzy Neural Networks for Identification of Breast Cancer Using Images’ Shape and Texture Features,” J. Med. Imaging Heal. Informatics, 2018.

Z. Xian, X. Wang, S. Yan, D. Yang, J. Chen, and C. Peng, “Main Coronary Vessel Segmentation Using Deep Learning in Smart Medical,” Math. Probl. Eng., 2020.

B. N. Walker et al., “Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies,” EBioMedicine, 2019.

A. Hekler et al., “Effects of Label Noise on Deep Learning-Based Skin Cancer Classification,” Front. Med., 2020.

W. B.N. et al., “Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies,” EBioMedicine, 2019.

M. C. M. van Zon, J. D. van der Waa, M. Veta, and G. A. M. Krekels, “Whole-slide margin control through deep learning in Mohs micrographic surgery for basal cell carcinoma,” Exp. Dermatol., 2021.

A. Rezvantalab, H. Safigholi, and S. Karimijeshni, “Dermatologist level dermoscopy skin cancer classification using different deep learning convolutional neural networks algorithms,” arXiv. 2018.

O. T. Jones, C. K. I. Ranmuthu, P. N. Hall, G. Funston, and F. M. Walter, “Recognising Skin Cancer in Primary Care,” Adv. Ther., 2020.

S. S. Chaturvedi, J. V. Tembhurne, and T. Diwan, “A multi-class skin Cancer classification using deep convolutional neural networks,” Multimed. Tools Appl., 2020.

H. H. Wang, Y. H. Wang, C. W. Liang, and Y. C. Li, “Assessment of Deep Learning Using Nonimaging Information and Sequential Medical Records to Develop a Prediction Model for Nonmelanoma Skin Cancer,” JAMA Dermatology, 2019.

D. E. Webster et al., “The Mole Mapper Study, mobile phone skin imaging and melanoma risk data collected using ResearchKit,” Sci. Data, 2017.

L.-J. Li et al., “ImageNet: a Large-Scale Hierarchical Image Database Shrimp Project View project hybrid intrusion detction systems View project ImageNet: A Large-Scale Hierarchical Image Database,” 2009 IEEE Conf. Comput. Vis. Pattern Recognit., 2009.

M. Jaderberg, “Deep Learning for Text Spotting University of Oxford Supervisors : Professor Andrew Zisserman Doctor Andrea Vedaldi,” Thesis, D Phil, 2014.

N. A. Tu, T. Huynh-The, K. S. Wong, D. M. Bui, and Y. K. Lee, “Distributed Feature Extraction on Apache Spark for Human Action Recognition,” in Proceedings of the 2020 14th International Conference on Ubiquitous Information Management and Communication, IMCOM 2020, 2020.

O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,” Int. J. Comput. Vis., 2015, doi: 10.1007/s11263-015-0816-y.

K. H. Mahmud, Adiwijaya, and S. Al Faraby, “Klasifikasi Citra Multi-Kelas Menggunakan Convolutional Neural Network,” e-Proceeding Eng., 2019.

D. Silver et al., “Mastering the game of Go with deep neural networks and tree search,” Nature, 2016.

J. R. Hagerty et al., “Deep Learning and Handcrafted Method Fusion: Higher Diagnostic Accuracy for Melanoma Dermoscopy Images,” IEEE J. Biomed. Heal. Informatics, 2019, doi: 10.1109/JBHI.2019.2891049.

“Robust Melanoma Screening - Datasets.” https://sites.google.com/site/robustmelanomascreening/dataset (accessed Apr. 10, 2021).

“ResNet-50 convolutional neural network - MATLAB resnet50.” https://www.mathworks.com/help/deeplearning/ref/resnet50.html;jsessionid=bdfe63b8d35bfa4b58f44aca0512 (accessed Apr. 10, 2021).

K. Weiss, T. M. Khoshgoftaar, and D. D. Wang, “08,” J. Big Data, 2016.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016.

A. Vilardi, “Very Deep Convolutional Neural Networks for face identification,” IEEE/ACM Trans. Audio, Speech, Lang. Process., 2016.

M. T. Hagos and S. Kant, “Transfer learning based detection of Diabetic Retinopathy from small dataset,” arXiv. 2019.

H. Zhu, H. Wei, B. Li, X. Yuan, and N. Kehtarnavaz, “A review of video object detection: Datasets, metrics and methods,” Applied Sciences (Switzerland). 2020.

A. Zisserman, Lecture 2: "The SVM Classifier. C19 Machine Learning "(Hilary Term 2015). Available Online At: Http: //Www. Robots. Ox. Ac. Uk/~ Az/Lectures/Ml/Lect2. Pdf (Accessed March 23, 2019), 2015

C.W. Hsu, And C.J. Lin, "A Comparison of Methods for Multiclass Support Vector Machines. IEEE Transactions on Neural Networks", 13(2), pp.415-425, 2002.

X. Yuan, Z. Yang, G. Zouridakis, and N. Mullani, , "SVM-Based Texture Classification And Application To Early Melanoma Detection", In International Conference Of The IEEE Engineering In Medicine and Biology Society, pp. 4775-4778, IEEE, 2006.