Advertisement

Automatic Skin Lesion Segmentation and Melanoma Detection: Transfer Learning Approach with U-Net and DCNN-SVM

Conference paper
Part of the Algorithms for Intelligent Systems book series (AIS)

Abstract

Industrial pollution resulting in ozone layer depletion has influenced increased UV radiation in recent years which is a major environmental risk factor for invasive skin cancer, melanoma, and other keratinocyte cancers. The incidence of deaths from melanoma has risen worldwide in the past two decades. Deep learning has been employed successfully for dermatologic diagnosis. In this work, we present a deep learning-based scheme to automatically segment skin lesions and detect melanoma from dermoscopy images. U-Net was used for segmenting out the lesion from surrounding skin. The limitation of utilizing deep neural networks with limited medical data was solved with data augmentation and transfer learning. In our experiments, U-Net was used with spatial dropout to solve the problem of overfitting, and different augmentation effects were applied to the training images to increase data samples. The model was evaluated on two different datasets. It achieved a mean dice score of 0.87 and a mean Jaccard index of 0.80 on ISIC 2018 dataset. The trained model was assessed on PH2 dataset where it achieved a mean dice score of 0.93 and a mean Jaccard index of 0.87 with transfer learning. For classification of malignant melanoma, a DCNN-SVM model was used where we compared state-of-the-art deep nets as feature extractors to find the applicability of transfer learning in dermatologic diagnosis domain. Our best model achieved a mean accuracy of 92% on PH2 dataset. The findings of this study are expected to be useful in cancer diagnosis research.

Keywords

Dermoscopy image Skin cancer Segmentation Deep learning Augmentation Melanoma classification Transfer learning 

References

  1. 1.
    Pham TC, Luong CM, Visani M, Hoang VD (2018) Deep CNN and data augmentation for skin lesion classification. Lecture Notes in Computer Science, pp 573–582.  https://doi.org/10.1007/978-3-319-75420-8_54CrossRefGoogle Scholar
  2. 2.
    Salido JAA, De La Salle University, Philippines, Ruiz C Jr (2018) Using deep learning for melanoma detection in dermoscopy images. Int J Mach Learn Comput 8:61–68.  https://doi.org/10.18178/ijmlc.2018.8.1.664CrossRefGoogle Scholar
  3. 3.
    Kohli JS, Tolomio E, Frigerio S, Maurichi A, Rodolfo M, Bennett DC (2017) Common delayed senescence of melanocytes from multiple primary melanoma patients. J Invest Dermatol 137:766–768.  https://doi.org/10.1016/j.jid.2016.10.026CrossRefGoogle Scholar
  4. 4.
    Ahmed HM, Al-azawi RJ, Abdulhameed AA (2018) Evaluation methodology between globalization and localization features approaches for skin cancer lesions classification. J Phys: Conf Ser 1003:012029.  https://doi.org/10.1088/1742-6596/1003/1/012029CrossRefGoogle Scholar
  5. 5.
    Glazer AM, Winkelmann RR, Farberg AS, Rigel DS (2016) Analysis of trends in US melanoma incidence and mortality. JAMA Dermatol.  https://doi.org/10.1001/jamadermatol.2016.4512CrossRefGoogle Scholar
  6. 6.
    Thao LT, Quang NH (2017) Automatic skin lesion analysis towards melanoma detection. In: 2017 21st Asia Pacific symposium on intelligent and evolutionary systems (IES).  https://doi.org/10.1109/iesys.2017.8233570
  7. 7.
    Venkatesh GM, Naresh YG, Little S, O’Connor NE (2018) A deep residual architecture for skin lesion segmentation. Lecture Notes in Computer Science, pp 277–284.  https://doi.org/10.1007/978-3-030-01201-4_30Google Scholar
  8. 8.
    Frid-Adar M, Diamant I, Klang E, Amitai M, Goldberger J, Greenspan H (2018) GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing. 321:321–331.  https://doi.org/10.1016/j.neucom.2018.09.013CrossRefGoogle Scholar
  9. 9.
    D Bloice, M., Bloice MD, Stocker C, Holzinger A (2017) Augmentor: an image augmentation library for machine learning. J Open Source Softw 2:432.  https://doi.org/10.21105/joss.00432CrossRefGoogle Scholar
  10. 10.
    Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. Lecture Notes in Computer Science, pp 234–241.  https://doi.org/10.1007/978-3-319-24574-4_28Google Scholar
  11. 11.
    Chollet F (2015) Keras. https://github.com/fchollet/keras
  12. 12.
    Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big Data 3.  https://doi.org/10.1186/s40537-016-0043-6
  13. 13.
    Wiatowski T, Bolcskei H (2018) A mathematical theory of deep convolutional neural networks for feature extraction. IEEE Trans Inf Theor 64:1845–1866.  https://doi.org/10.1109/TIT.2017.2776228MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Mallat S (2012) Group invariant scattering. Commun Pure Appl Math 65:1331–1398.  https://doi.org/10.1002/cpa.21413MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Garcia-Gasulla D, Parés F, Vilalta A, Moreno J, Ayguadé E, Labarta J, Cortés U, Suzumura T (2018) On the behavior of convolutional nets for feature extraction. J Artif Intell Res 61:563–592.  https://doi.org/10.1613/jair.5756MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Corrigendum: dermatologist-level classification of skin cancer with deep neural networks. Nature 546:686.  https://doi.org/10.1038/nature21056CrossRefGoogle Scholar
  17. 17.
    Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR).  https://doi.org/10.1109/cvpr.2017.243
  18. 18.
    ISIC (2018) Skin lesion analysis towards melanoma detectionGoogle Scholar
  19. 19.
    Codella NC, Gutman D, Celebi MEEA (2017) 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). arXiv:1710.05006,  https://doi.org/10.1109/isbi.2018.8363547
  20. 20.
    Li X, Chen H, Qi X, Dou Q, Fu C-W, Heng P-A (2018) H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE Trans Med Imag.  https://doi.org/10.1109/tmi.2018.2845918CrossRefGoogle Scholar
  21. 21.
    Mendonca T, Ferreira PM, Marques JS, Marcal ARS, Rozeira J (2013) PH2 – a dermoscopic image database for research and benchmarking. In: 35th annual international conference of the IEEE engineering in medicine and biology society (EMBC), pp 5437–5440.  https://doi.org/10.1109/embc.2013.6610779

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringKhulna University of Engineering and TechnologyKhulnaBangladesh

Personalised recommendations