Abstract
Melanoma is one of the most dangerous forms of skin cancer with an apace increase in death rates each year. One major problem in Artificial Intelligence and Machine Learning is the issue of racial disparities. This leads to myriad problems in association with medical image analysis as the data fed to these algorithms are biased. Accurate and concise segmentation is an imperative requirement when developing a computer assisted diagnostic support system. In order to surmount the problems caused by the lack of a diverse set of images, we look at initially segmenting lesions, using the GrabCut method, from the surrounding skin. This lets us focus on the skin lesion and remove potential colour confusion associated with the mixture of the lesion colour and skin tones. Thereafter, we make use of 14 pre-trained transfer learning models. The experimental results achieve the following: Dice index 0.93, Jaccard index 0.88, Matthew Correlation Coefficient 0.87, Sensitivity 0.92, Specificity 0.95 and an Accuracy rate of 0.93.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
American Cancer Society: About Melanoma Skin Cancer. https://www.cancer.org/cancer/melanoma-skin-cancer/about/what-is-melanoma.html. Accessed 7 Sep 2019
Skin Cancer Foundation. https://www.skincancer.org/skin-cancer-information/melanoma/. Accessed 7 Sep 2019
World Health Organization. https://www.who.int/uv/faq/skincancer/en/index1.html. Accessed 7 Sep 2019
Pillay, V., Viriri, S.: Skin cancer detection from macroscopic images. In: Conference on Information Communications Technology and Society, pp. 1–9 (ICTAS) (2019)
Applications of Computer Vision in Healthcare. https://medium.com/optima-ai/applications-of-computer-vision-in-healthcare-5651208b3539. Accessed 7 Sep 2019
Zhou, H., Zheng, J., Wei, L.: Texture aware image segmentation using graph cuts and active contours. Pattern Recogn. 46, 1719–1733 (2013)
Kulkarni, M., Nicolls, F.: Interactive image segmentation using graph cuts. In: Proceedings of 20th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA2009), Stellenbosch, South Africa (2009)
Raghunandanan, P., John, L.: A Review on Various Graph Cut Based Image Segmentation Schemes (2013)
Graph cuts in computer vision. https://en.wikipedia.org/wiki/Graph_cuts_in_computer_vision. Accessed 27 July 2019
Reynolds, D.: Gaussian Mixture Models, pp. 1–5 (2009)
Carsten, R., Vladimir, K., Andrew, B.: GrabCut: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309–314 (2004)
Yang, W., Cai, J., Zheng, J., Luo, J.: User-friendly interactive image segmentation through unified combinatorial user inputs. IEEE Trans. Image Process. 19, 2470–2479 (2010). https://doi.org/10.1109/TIP.2010.2048611. A publication of the IEEE Signal Processing Society
Kolmogorov, V., Ramin, Z.: What energy functions can be minimized via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 26, 147–59 (2004). https://doi.org/10.1109/TPAMI.2004.1262177
Yi, F., Moon, I.: Image segmentation: a survey of graph-cut methods. In: 2012 International Conference on Systems and Informatics (ICSAI2012), pp. 1936–1941 (2012). https://doi.org/10.1109/ICSAI.2012.6223428
Ford, L., Fulkerson, D.: Flows in Networks. Princeton University Press, Princeton (1962)
Franke, Markus: Color Image Segmentation Based on an Iterative Graph Cut Algorithm Using Time-of-Flight Cameras. In: Mester, Rudolf, Felsberg, Michael (eds.) DAGM 2011. LNCS, vol. 6835, pp. 462–467. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23123-0_49
Nammalwar, P., Ghita, O., Whelan, P.F.: Segmentation of Skin Cancer Images. Vision Systems Group. Centre for Image Processing and Analysis. School of Electronic Engineering. Dublin City University. Ireland (2009)
Camilus, K., Govindan, V.K.: A review on graph based segmentation. Int. J. Image Graph. Signal Process. 4 (2012). https://doi.org/10.5815/ijigsp.2012.05.01
Oyebode, K.O., Du, S., Wyk, B.J., Djouani, K.: Investigating the relevance of graph cut parameter on interactive and automatic cell segmentation. Comp. Math. Methods Med. (2018)
Ünver, H., Ayan, E.: Skin lesion segmentation in dermoscopic images with combination of YOLO and GrabCut algorithm. Diagnostics 9, 72 (2019). https://doi.org/10.3390/diagnostics9030072
Jafari, M.H., et al.: Skin lesion segmentaion in clinical images using deep learning. In: IEEE International Conference on Pattern Recognition (ICPR), Cancun, Mexico (2016)
Cavalcanti, P.G., Scharcanski, J.: Automated pre-screening of pigmented skin lesions using standard cameras. Comput. Med. Imaging Graph. 6, 481–491 (2011)
Bi, L., Kim, J., Ahn, E., Feng, D.: Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks. arXiv arXiv:1703.04197 (2017)
Cavalcanti, P., Yari, Y., Scharcanski, J.: Pigmented skin lesion segmentation on macroscopic images. In: Proceedings 25th International Conference on Image Vision Computing, pp. 1–7 (2010)
Li, Y., Shen, L.: Skin lesion analysis towards melanoma detection using deep learning network. Sensors 18, 556 (2018)
Chen, E.Z., Dong, X., Wu, J., Jiang, H., Li, X., Rong, R.: Lesion Attributes Segmentation for Melanoma Detection with Deep Learning. bioRxiv, p. 381855 (2018)
Maolood, I., Alsalhi, Y., Lu, S.: Thresholding for medical image segmentation for cancer using fuzzy entropy with level set algorithm. Open Med. 13, 374–383 (2018). https://doi.org/10.1515/med-2018-0056
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Pillay, V., Hirasen, D., Viriri, S., Gwetu, M.V. (2020). Macroscopic Skin Lesion Segmentation Using GrabCut. In: Nguyen, N.T., Hoang, B.H., Huynh, C.P., Hwang, D., Trawiński, B., Vossen, G. (eds) Computational Collective Intelligence. ICCCI 2020. Lecture Notes in Computer Science(), vol 12496. Springer, Cham. https://doi.org/10.1007/978-3-030-63007-2_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-63007-2_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63006-5
Online ISBN: 978-3-030-63007-2
eBook Packages: Computer ScienceComputer Science (R0)