Funding information: Innovation Capacity Construction Project of Jilin Province Development and Reform Commission, Grant/Award Number: 2021FGWCXNLJSSZ10; National Key Research and Development Program of China, Grant/Award Number: 2020YFA0714103; Science & Technology Development Project of Jilin Province,China, Grant/Award Number: 20190302117GX; Fundamental Research Funds for the Central Universities, JLU

Read the full text

About

PDF

Tools

Share a link

Email
Wechat
Bluesky

Abstract

The segmentation of skin lesions is a critical step in the detection of skin cancer. However, it is also difficult because of unclear boundaries, various size and shape of skin lesions, the appearance of interference objects and different backgrounds in dermoscopic images. This study presents proposed multiple attention-based methods based on U-net architecture. At first, dense attention gates (DAG) are proposed to obtain the focus area of the feature map by capturing information through extern feature maps. Then, to extend the capability of capturing feature relationships of the DAG module. We introduced The shuffle attention module which can fuse two self-attention modules in a lightweight yet effective way. According to the experiments conducted on International Skin Imaging Collaboration (ISIC) 2017 and PH2 datasets, the proposed model can generate satisfactory segmentation results and great capability in practical computer-aided diagnosis systems.

CONFLICT OF INTEREST

The author declares no conflict of interest or personal relationships with other people and organizations regarding the publication of this article.

Open Research

DATA AVAILABILITY STATEMENT

The data that support the findings of this study are openly available in ISIC 2017 at https://challenge.isic-archive.com/data/ , reference number [17]. The data that support the findings of this study are openly available in PH2 at https://www.fc.up.pt/addi/ph2%20data base.html, reference number [17].

REFERENCES

1Saba T, Khan MA, Rehman A, Marie-Sainte SL. Region extraction and classification of skin cancer: a heterogeneous framework of deep CNN features fusion and reduction[J]. J Med Syst. 2019; 43(9): 1-19.
10.1007/s10916-019-1413-3
Web of Science® Google Scholar
2Victor A, Ghalib M. Automatic detection and classification of skin cancer[J]. Int J Intell Eng Syst. 2017; 10(3): 444-451.
Google Scholar
3Balch CM, Gershenwald JE, Soong S, et al. Final version of 2009 AJCC melanoma staging and classification[J]. J Clin Oncol. 2009; 27(36): 6199-6206.
10.1200/JCO.2009.23.4799
PubMed Web of Science® Google Scholar
4Binder M, Schwarz M, Winkler A, et al. Epiluminescence microscopy: a useful tool for the diagnosis of pigmented skin lesions for formally trained dermatologists[J]. Arch Dermatol. 1995; 131(3): 286-291.
10.1001/archderm.1995.01690150050011
CAS PubMed Web of Science® Google Scholar
5Yu L, Chen H, Dou Q, Qin J, Heng PA. Automated melanoma recognition in dermoscopy images via very deep residual networks[J]. IEEE Trans Med Imaging. 2016; 36(4): 994-1004.
10.1109/TMI.2016.2642839
PubMed Web of Science® Google Scholar
6Burroni M, Corona R, Dell'Eva G, et al. Melanoma computer-aided diagnosis: reliability and feasibility study[J]. Clin Cancer Res. 2004; 10(6): 1881-1886.
10.1158/1078-0432.CCR-03-0039
PubMed Web of Science® Google Scholar
7Xie Y, Zhang J, Xia Y, Shen C. A mutual bootstrapping model for automated skin lesion segmentation and classification[J]. IEEE Trans Med Imaging. 2020; 39(7): 2482-2493.
10.1109/TMI.2020.2972964
PubMed Web of Science® Google Scholar
8Canny J. A computational approach to edge detection[J]. IEEE Trans Pattern Anal Mach Intell. 1986; 6: 679-698.
10.1109/TPAMI.1986.4767851
Web of Science® Google Scholar
9Mumford DB, Shah J. Optimal approximations by piecewise smooth functions and associated variational problems[J]. Communications on Pure and Applied Mathematics. 1989; 42: 577-685.
10.1002/cpa.3160420503
Web of Science® Google Scholar
10Chan TF, Vese LA. Active contours without edges[J]. IEEE Trans Image Process. 2001; 10(2): 266-277.
10.1109/83.902291
CAS PubMed Web of Science® Google Scholar
11Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Trans Syst Man Cybern. 1979; 9(1): 62-66.
10.1109/TSMC.1979.4310076
Web of Science® Google Scholar
12Emre Celebi M, Wen Q, Hwang S, Iyatomi H, Schaefer G. Lesion border detection in dermoscopy images using ensembles of thresholding methods[J]. Skin Res Technol. 2013; 19(1): e252-e258.
10.1111/j.1600-0846.2012.00636.x
CAS PubMed Web of Science® Google Scholar
13Kass M, Witkin A, Terzopoulos D. Snakes: active contour models[J]. International Journal of Computer Vision. 1988; 1(4): 321-331.
10.1007/BF00133570
Web of Science® Google Scholar
14Xu C, Prince JL. Snakes, shapes, and gradient vector flow[J]. IEEE Trans Image Process. 1998; 7(3): 359-369.
10.1109/83.661186
CAS PubMed Web of Science® Google Scholar
15Melli R, Grana C, Cucchiara R. Comparison of color clustering algorithms for segmentation of dermatological images[C]. Medical Imaging 2006: Image Processing. Vol 6144. International Society for Optics and Photonics; 2006: 61443S.
10.1117/12.652061
Google Scholar
16Zhou H, Schaefer G, Sadka AH, Celebi ME. Anisotropic mean shift based fuzzy c-means segmentation of dermoscopy images[J]. IEEE Journal of Selected Topics in Signal Processing. 2009; 3(1): 26-34.
10.1109/JSTSP.2008.2010631
Web of Science® Google Scholar
17Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[C]. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer; 2015: 234-241.
10.1007/978-3-319-24574-4_28
Google Scholar
18Bi L, Kim J, Ahn E, Kumar A, Fulham M, Feng D. Dermoscopic image segmentation via multistage fully convolutional networks[J]. IEEE Transactions on Biomedical Engineering. 2017; 64(9): 2065-2074.
10.1109/TBME.2017.2712771
PubMed Web of Science® Google Scholar
19Vesal S, Ravikumar N, Maier A. Skinnet: a deep learning framework for skin lesion segmentation[C]. 2018 IEEE nuclear science symposium and medical imaging conference proceedings (NSS/MIC). IEEE; 2018: 1-3.
10.1109/NSSMIC.2018.8824732
Google Scholar
20Norouzi A, Rahim MSM, Altameem A, et al. Medical image segmentation methods, algorithms, and applications[J]. IETE Technical Review. 2014; 31(3): 199-213.
10.1080/02564602.2014.906861
Web of Science® Google Scholar
21Oktay O, Schlemper J, Folgoc L L, et al. Attention u-Net: learning where to look for the pancreas[J]. arXiv Preprint arXiv:1804.03999, 2018.
Google Scholar
22Sun J, Darbehani F, Zaidi M, et al. Saunet: shape attentive u-Net for interpretable medical image segmentation[C]. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer; 2020: 797-806.
10.1007/978-3-030-59719-1_77
Google Scholar
23Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2018: 7132-7141.
10.1109/CVPR.2018.00745
Google Scholar
24Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2017: 4700-4708.
10.1109/CVPR.2017.243
Google Scholar
25Codella NCF, Gutman D, Celebi ME, et al. Skin lesion analysis toward melanoma detection: a challenge at the 2017 International symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic)[C]. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). IEEE; 2018: 168-172.
Google Scholar
26Mendonça T, Ferreira PM, Marques JS, et al. PH 2-a dermoscopic image database for research and benchmarking[C]. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE; 2013: 5437-5440.
10.1109/EMBC.2013.6610779
Google Scholar
27Long J, Shelhamer E, Darrell T. Fully Convolutional Networks for Semantic Segmentation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2015: 3431-3440.
10.1109/CVPR.2015.7298965
Google Scholar
28Wang Q, Wu B, Zhu P, et al. ECA-net: efficient channel attention for deep convolutional neural networks. 2020 IEEE[C]/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2020.
10.1109/CVPR42600.2020.01155
Google Scholar
29Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design F[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE; 2021: 13713-13722.
10.1109/CVPR46437.2021.01350
Google Scholar
30Woo S, Park J, Lee JY, et al. Cbam: convolutional block attention module[C]. Proceedings of the European Conference on Computer Vision (ECCV). Springer; 2018: 3-19.
10.1007/978-3-030-01234-2_1
Google Scholar
31Shu Y, Zhang J, Xiao B, Li W. Medical image segmentation based on active fusion-transduction of multi-stream features[J]. Knowledge-Based Systems. 2021; 220:106950.
10.1016/j.knosys.2021.106950
Web of Science® Google Scholar
32Wang SH, Fernandes S, Zhu Z, Zhang YD. AVNC: attention-based VGG-style network for COVID-19 diagnosis by CBAM[J]. IEEE Sensors Journal. 2021; 1.
Google Scholar
33Zhang YD, Zhang Z, Zhang X, Wang SH. MIDCAN: a multiple input deep convolutional attention network for Covid-19 diagnosis based on chest CT and chest X-ray[J]. Pattern Recognition Letters. 2021; 150: 8-16.
10.1016/j.patrec.2021.06.021
PubMed Web of Science® Google Scholar
34Tong X, Wei J, Sun B, Su S, Zuo Z, Wu P. ASCU-net: attention gate, spatial and channel attention U-net for skin lesion segmentation[J]. Diagnostics. 2021; 11(3): 501.
10.3390/diagnostics11030501
PubMed Web of Science® Google Scholar
35Abraham N, Khan NM. A novel focal tversky loss function with improved attention u-net for lesion segmentation[C]. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI). Vol 2019. IEEE; 2019: 683-687.
10.1109/ISBI.2019.8759329
Google Scholar
36He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2016: 770-778.
10.1109/CVPR.2016.90
Google Scholar
37Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks[C]. International Conference on Machine Learning. PMLR; 2019: 6105-6114.
Google Scholar
38Al-Masni MA, Al-Antari MA, Choi MT, et al. Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks[J]. Comput Methods Programs Biomed. 2018; 162: 221-231.
10.1016/j.cmpb.2018.05.027
PubMed Web of Science® Google Scholar
39Sarker MMK, Rashwan HA, Akram F, et al. SLSDeep: skin lesion segmentation based on dilated residual and pyramid pooling networks[C]. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer; 2018: 21-29.
10.1007/978-3-030-00934-2_3
Google Scholar
40Tu W, Liu X, Hu W, Pan Z. Dense-residual network with adversarial learning for skin lesion segmentation[J]. IEEE Access. 2019; 7: 77037-77051.
10.1109/ACCESS.2019.2921815
Web of Science® Google Scholar
41Bi L, Kim J, Ahn E, Kumar A, Feng D, Fulham M. Step-wise integration of deep class-specific learning for dermoscopic image segmentation[J]. Pattern Recognition. 2019; 85: 78-89.
10.1016/j.patcog.2018.08.001
Web of Science® Google Scholar
42Goyal M, Oakley A, Bansal P, Dancey D, Yap MH. Skin lesion segmentation in dermoscopic images with ensemble deep learning methods[J]. IEEE Access. 2019; 8: 4171-4181.
10.1109/ACCESS.2019.2960504
Web of Science® Google Scholar
43Tang Y, Fang Z, Yuan S, et al. Imscgnet: iterative multi-scale context-guided segmentation of skin lesion in dermoscopic images[J]. IEEE Access. 2020; 8: 39700-39712.
10.1109/ACCESS.2020.2974512
Web of Science® Google Scholar

Citing Literature

Volume32, Issue6

November 2022

Pages 2066-2079

This article also appears in:

Skin cancer and melanoma

Dense and shuffle attention U-Net for automatic skin lesion segmentation

Abstract

CONFLICT OF INTEREST

Open Research

DATA AVAILABILITY STATEMENT

REFERENCES

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Dense and shuffle attention U-Net for automatic skin lesion segmentation

Abstract

CONFLICT OF INTEREST

Open Research

DATA AVAILABILITY STATEMENT

REFERENCES

Citing Literature

References

Related

Information