International Journal of Imaging Systems and Technology

RESEARCH ARTICLE

Skin lesion classification based on the VGG-16 fusion residual structure

Pu Yan

Anhui International Joint Research Center for Ancient Architecture Intellisencing and Multi-Dimensional Modeling, Anhui Jianzhu University, Hefei, China

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Search for more papers by this author

Gang Wang,

Gang Wang

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei, China

Search for more papers by this author

Jie Chen,

Corresponding Author

Jie Chen

[email protected]

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei, China

Correspondence

Jie Chen, College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230000, China.

Email: [email protected]

Search for more papers by this author

Qingwei Tang,

Qingwei Tang

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei, China

Search for more papers by this author

Heng Xu,

Heng Xu

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei, China

Search for more papers by this author

Pu Yan,

Pu Yan

Anhui International Joint Research Center for Ancient Architecture Intellisencing and Multi-Dimensional Modeling, Anhui Jianzhu University, Hefei, China

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Search for more papers by this author

Gang Wang,

Gang Wang

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei, China

Search for more papers by this author

Jie Chen,

Corresponding Author

Jie Chen

[email protected]

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei, China

Correspondence

Jie Chen, College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230000, China.

Email: [email protected]

Search for more papers by this author

Qingwei Tang,

Qingwei Tang

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei, China

Search for more papers by this author

Heng Xu,

Heng Xu

College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei, China

Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei, China

Search for more papers by this author

First published: 27 August 2022

https://doi.org/10.1002/ima.22798

Citations: 2

Funding information: Educational Commission of Anhui Province of China, Grant/Award Number: KJ2020A0471; Anhui Provincial DOHURD Science Foundation, Grant/Award Number: 2020-YF22; Anhui Provincial Natural Science Foundation, Grant/Award Numbers: 2008085MF182, 1908085QF281; National Natural Science Foundation of China, Grant/Award Numbers: 62 001 004, 62 105 002, 61 901 006; University Synergy Innovation Program of Anhui Province, Grant/Award Number: GXXT-2019-007

Share a link

Email
Wechat
Bluesky

Abstract

The analysis of skin lesion images is challenging due to the high interclass similarity and intraclass variance. Therefore, improving the ability to automatically classify based on skin lesion images is necessary to help physicians classify skin lesions. We propose a network model based on the Visual Geometry Group Network (VGG-16) fusion residual structure for the multiclass classification of skin lesions. based on the VGG-16 network, we simplify and improve the network structure by adding a preprocessing layer (CBRM layer) and fusing the residual structure. We also use a hair removal algorithm and perform six data augmentation operations on a small number of skin lesion images to balance the total number of the seven skin lesions in the dataset. The model was evaluated on the ISIC2018 dataset. Experiments have shown that our network model achieves good classification performance, with a test accuracy rate of 88.14% and a macroaverage of 98%.

CONFLICT OF INTEREST

This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution, and reproduction in any medium, provided the original work is properly cited.

Open Research

DATA AVAILABILITY STATEMENT

The datasets generated or analyzed during this study are available from the corresponding author on reasonable request.

REFERENCES

1Hay R, Johns N, Williams H, et al. The global burden of skin disease in 2010: an analysis of the prevalence and impact of skin conditions. Journal of Investigative Dermatology. 2014; 134(6): 1527-1534.
10.1038/jid.2013.446
CAS PubMed Web of Science® Google Scholar
2Kasmi R, Mokrani K. Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule. IET Image Process. 2016; 10(6): 448-455. doi:10.1049/iet-ipr.2015.0385
10.1049/iet-ipr.2015.0385
Web of Science® Google Scholar
3Rogers H, Weinstock M, Feldman S, et al. Incidence estimate of nonmelanoma skin cancer (keratinocyte carcinomas) in the US population, 2012. JAMA Dermatol. 2015; 151(10): 1081-1086.
10.1001/jamadermatol.2015.1187
PubMed Web of Science® Google Scholar
4Zhongyu L, William P, Andrew K, et al. Role of Alpha-1 Adrenoceptor subtypes mediating constriction of the rabbit ear thermoregulatory microvasculature. J Bone Joint Surg Am. 2000; 82(5): 16.
10.2106/00004623-200005000-00030
PubMed Web of Science® Google Scholar
5Conic R, Cabrera C, Khorana A, et al. Determination of the impact of melanoma surgical timing on survival using the National Cancer Database. J Am Acad Dermatol. 2017; 79(4):S0190962217323009.
Web of Science® Google Scholar
6Ralph A, Harold B, Msn B, et al. Dermoscopy of pigmented skin lesions. J Am Acad Dermatol. 2001; 52(1): 109-121.
Google Scholar
7Peng T, Qiaokang L, Xintong Y, et al. GP-CNN-DTEL: global-part CNN model with data-transformed ensemble learning for skin lesion classification. IEEE J Biomed Health Inform. 2020; 24(10): 2870-2882. doi:10.1109/JBHI.2020.2977013
10.1109/JBHI.2020.2977013
PubMed Web of Science® Google Scholar
8Wu J, Hu W, Wen Y, et al. Skin lesion classification using densely connected convolutional networks with attention residual learning. Sensors. Vol 20. Multidisciplinary Digital Publishing Institute (MDPI); 2020.
Google Scholar
9Wu H, Pan J, Li Z, Wen Z, Qin J. Automated skin lesion segmentation via an adaptive dual attention module. IEEE Trans Med Imaging. 2021; 40: 357-370.
10.1109/TMI.2020.3027341
PubMed Web of Science® Google Scholar
10Long E, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015; 2015: 3431-3440.
Google Scholar
11Chen L, Papandreou G, Kokkinos I, et al. DeepLab: semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell. 2018; 40: 834-848.
10.1109/TPAMI.2017.2699184
PubMed Web of Science® Google Scholar
12Huang G, Liu Z, Weinberger K. Densely connected convolutional networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017; 2017: 2261-2269.
Google Scholar
13He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Institute of Electrical and Electronics Engineering (IEEE); 2016: 770-778.
10.1109/CVPR.2016.90
Google Scholar
14Tommasi T, Elisabetta L, Caputo B. Melanoma recognition using representative and discriminative kernel classifiers. Second Eccv International Conference on Computer Vision Approaches to Medical Image Analysis. European Conference on Computer Vision (ECCV); 2006.
10.1007/11889762_1
Google Scholar
15Garnavi R, Mohammad A, Bailey J. Computer-aided diagnosis of melanoma using border- and wavelet-based texture analysis. IEEE Trans Inf Technol Biomed. 2012; 16: 1239-1252.
10.1109/TITB.2012.2212282
PubMed Web of Science® Google Scholar
16Ballerini L, Fisher R, Aldridge B, et al. A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions. Springer; 2013: 63-86.
Google Scholar
17Alfed N, Khelifi F, Bouridane A. Improving a bag of words approach for skin cancer detection in dermoscopic images. International Conference on Control, Decision and Information Technologies (CoDIT). Vol 2016. Institute of Electrical and Electronics Engineering (IEEE); 2016: 24-27.
10.1109/CoDIT.2016.7593529
Google Scholar
18Schaefer G, Krawczyk B, Celebi M, et al. An ensemble classification approach for melanoma diagnosis. Memetic Comput. 2014; 6: 233-240.
10.1007/s12293-014-0144-8
Web of Science® Google Scholar
19Li Y, Shen L. Skin lesion analysis towards melanoma detection using deep learning network. Sensors. 2018; 18(2): 322.
10.3390/s18020556
Web of Science® Google Scholar
20Yi X, Walia E, Babyn P. Unsupervised and semi-supervised learning with categorical generative adversarial networks assisted by Wasserstein distance for dermoscopy image classification. ArXiv. 2018;abs/1804.03700.
Google Scholar
21Mariam A, Sharwy A, Mabrouk M. Pigmented skin lesion diagnosis using geometric and chromatic features. 2014 Cairo International Biomedical Engineering Conference. Institute of Electrical and Electronics Engineering (IEEE); 2014: 115-120.
Google Scholar
22Muhammad K, Zhang Y, Sharif M, et al. Pixels to classes: intelligent learning framework for multiclass skin lesion localization and classification. Comput Electr Eng. 2021; 90:106956.
10.1016/j.compeleceng.2020.106956
Web of Science® Google Scholar
23González-Díaz I. Incorporating the knowledge of dermatologists to convolutional neural networks for the diagnosis of skin lesions. ArXiv. 2017;abs/1703.01976.
Google Scholar
24Esteva A, Kuprel B, Novoa R, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542: 115-118.
10.1038/nature21056
CAS PubMed Web of Science® Google Scholar
25Romero-Lopez A, Giró N, Burdick J, et al. Skin lesion classification from dermoscopic images using deep learning techniques. 2017 13th IASTED International Conference on Biomedical Engineering (BioMed). Institute of Electrical and Electronics Engineering (IEEE); 2017: 49-54.
10.2316/P.2017.852-053
Google Scholar
26Sorokin A. Lesion analysis and diagnosis with mask-RCNN. arXiv: Image and Video Processing; 2018.
Google Scholar
27Liu J, Chen A, Zhou G, Chen W, Peng N, Yan N. Dermatoscopic image melanoma recognition based on CFLDnet fusion network. Multimed Tools Appl. 2021; 80: 25477-25494.
10.1007/s11042-021-10920-1
Web of Science® Google Scholar
28Mahbod A, Schaefer G, Wang C, Dorffner G, Ecker R, Ellinger I. Transfer learning using a multi-scale and multi-network ensemble for skin lesion classification. Comput Methods Prog Biomed. 2020; 193:105475.
10.1016/j.cmpb.2020.105475
PubMed Web of Science® Google Scholar
29Mohamed E, Wessam H. Enhanced skin lesions classification using deep convolutional networks. Ninth International Conference on Intelligent Computing and Information Systems (ICICIS). Vol 2019. Springer-Verlag; 2019: 180-188.
10.1109/ICICIS46948.2019.9014823
Google Scholar
30Al-Antari M, Rivera P, Al-Masni M, et al. An automatic recognition of multi-class skin lesions via deep learning convolutional neural networks. ISIC2018: Skin Image Analysis Workshop and Challenge; 2018.
Google Scholar
31Kitada S, Iyatomi H. Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning. ArXiv. 2018;abs/1809.02568.
Google Scholar
32Pomponiu V, Nejati H, Cheung N. Deepmole: deep neural networks for skin mole lesion classification. IEEE International Conference on Image Processing (ICIP). Vol 2016. Institute of Electrical and Electronics Engineering (IEEE); 2016: 2623-2627.
10.1109/ICIP.2016.7532834
Google Scholar
33Peng Y, Shuwei S, Mengjuan X, et al. Single model deep learning on imbalanced small datasets for skin lesion classification[J]. IEEE Trans Med Imaging. 2021.
Web of Science® Google Scholar
34Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. CoRR. 2015;abs/1409.1556.
Google Scholar
35Shahin M, Sipon M, Haque J, et al. An enhanced technique of skin cancer classification using deep convolutional neural network with transfer learning models. Mach Learn Appl. 2021; 5:100036. doi:10.1016/j.mlwa.2021.100036
10.1016/j.mlwa.2021.100036
Google Scholar
36Meihua B, Siyu G, Yaonan W, et al. Improved bwmorph function in the MATLAB image processing toolbox for fast computation of repeated morphological dilations and erosions. 2009 Second International Conference on Intelligent Computation Technology and Automation. Vol 1. Institute of Electrical and Electronics Engineering (IEEE); 2009: 625-628.
Google Scholar
37Telea A. An image Inpainting technique based on the fast marching method. J Graphics Tools. 2004; 9: 23-34.
10.1080/10867651.2004.10487596
Google Scholar
38Rampáek L, Goldenberg A. TensorFlow: Biology's gateway to deep learning. Cell Syst. 2016; 2(1): 12-14.
10.1016/j.cels.2016.01.009
PubMed Web of Science® Google Scholar
39Zillur R, Sabir M, Rabiul M, et al. An approach for multiclass skin lesion classification based on ensemble learning. Inf Med Unlocked. 2021;25:100659.
Google Scholar
40Lin T, Goyal P, Girshick P, et al. Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell. 2020; 42: 318-327.
10.1109/TPAMI.2018.2858826
PubMed Web of Science® Google Scholar

Citing Literature

Volume33, Issue1

January 2023

Pages 53-68

This article also appears in:

Skin cancer and melanoma

Skin lesion classification based on the VGG-16 fusion residual structure

Abstract

CONFLICT OF INTEREST

Open Research

DATA AVAILABILITY STATEMENT

REFERENCES

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Skin lesion classification based on the VGG-16 fusion residual structure

Abstract

CONFLICT OF INTEREST

Open Research

DATA AVAILABILITY STATEMENT

REFERENCES

Citing Literature

References

Related

Information