Rethinking Skin Lesion Segmentation in a Convolutional Classifier


Melanoma is a fatal form of skin cancer when left undiagnosed. Computer-aided diagnosis systems powered by convolutional neural networks (CNNs) can improve diagnostic accuracy and save lives. CNNs have been successfully used in both skin lesion segmentation and classification. For reasons heretofore unclear, previous works have found image segmentation to be, conflictingly, both detrimental and beneficial to skin lesion classification. We investigate the effect of expanding the segmentation border to include pixels surrounding the target lesion. Ostensibly, segmenting a target skin lesion will remove inessential information, non-lesion skin, and artifacts to aid in classification. Our results indicate that segmentation border enlargement produces, to a certain degree, better results across all metrics of interest when using a convolutional based classifier built using the transfer learning paradigm. Consequently, preprocessing methods which produce borders larger than the actual lesion can potentially improve classifier performance, more than both perfect segmentation, using dermatologist created ground truth masks, and no segmentation altogether.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3


  1. 1.

    Siegel RL, Miller KD, Jemal A: Cancer statistics, 2016. CA: Cancer J Clin 66(1):7–30, 2016

  2. 2.

    Guy GP, Machlin SR, Ekwueme DU, Yabroff KR: Prevalence and costs of skin cancer treatment in the US, 2002- 2006 and 2007- 2011. Am J Prev Med 48(2):183–187, 2015

  3. 3.

    Guy GP Jr, Ekwueme DU: Years of potential life lost and indirect costs of melanoma and non-melanoma skin cancer. Pharmacoeconomics 29(10):863–874, 2011

  4. 4.

    Nachbar F, Stolz W, Merkle T, Cognetta AB, Vogt T, Landthaler M, Bilek P, Braun Falco O, Plewig G: The ABCD rule of dermatoscopy: high prospective value in the diagnosis of doubtful melanocytic skin lesions. J Am Acad Dermatol 30(4):551–559, 1994

    Article  PubMed  CAS  Google Scholar 

  5. 5.

    Argenziano G, Fabbrocini G, Carli P, De Giorgi V, Sammarco E, Delfino M: Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions: comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis. Arch Dermatol 134(12):1563–1570, 1998

    Article  PubMed  CAS  Google Scholar 

  6. 6.

    Henning JS, Dusza SW, Wang SQ, Marghoob AA, Rabinovitz HS, Polsky D, Kopf AW: The CASH (color, architecture, symmetry, and homogeneity) algorithm for dermoscopy. J Am Acad Dermatol 56(1):45–52, 2007

    Article  PubMed  Google Scholar 

  7. 7.

    Argenziano G, Soyer HP: Dermoscopy of pigmented skin lesions–a valuable tool for early diagnosis of melanoma. Lancet Oncol 2(7):443–449, 2001

    Article  PubMed  CAS  Google Scholar 

  8. 8.

    Kittler H, Pehamberger H, Wolff K, Binder M: Diagnostic accuracy of dermoscopy. Lancet Oncol 3(3):159–165, 2002

    Article  PubMed  CAS  Google Scholar 

  9. 9.

    Vestergaard M, Macaskill P, Holt P, Menzies S: Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta-analysis of studies performed in a clinical setting. Brit J Dermatol 159(3):669–676, 2008

    CAS  Google Scholar 

  10. 10.

    Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118, 2017

    Article  PubMed  CAS  Google Scholar 

  11. 11.

    Marques O: Morphological image processing. In: Practical image and video processing using MATLAB. Wiley - IEEE, chap. 13, 2011, pp 299–334

  12. 12.

    Oliveira RB, Mercedes Filho E, Ma Z, Papa JP, Pereira AS, Tavares JMR: Computational methods for the image segmentation of pigmented skin lesions: a review. Comput Methods Programs Biomed 131: 127–141, 2016

    Article  PubMed  Google Scholar 

  13. 13.

    Burdick J, Marques O, Romero Lopez A, Giró Nieto X, Weinthal J: The impact of segmentation on the accuracy and sensitivity of a melanoma classifier based on skin lesion images. In: SIIM (Society for Imaging Informatics in Medicine) 2017 annual meeting. Pittsburgh, 2017, pp 1–6

  14. 14.

    Codella N, Nguyen QB, Pankanti S, Gutman D, Helba B, Halpern A, Smith JR: Deep learning ensembles for melanoma recognition in dermoscopy images, arXiv:1610.04662, 2016

  15. 15.

    Kawahara J, BenTaieb A, Hamarneh G: Deep features to classify skin lesions. In: IEEE International symposium on biomedical imaging (IEEE ISBI). Prague, 2016, pp 1397–1400

  16. 16.

    Lopez AR, Giro-i Nieto X, Burdick J, Marques O: Skin lesion classification from dermoscopic images using deep learning techniques.. In: 13th IASTED International conference on biomedical engineering (BioMed). IEEE, Innsbruck, 2017, pp 49– 54

  17. 17.

    Yu L, Chen H, Dou Q, Qin J, Heng PA: Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans Med Imaging 36(4):994–1004, 2017

    Article  PubMed  Google Scholar 

  18. 18.

    Jaworek Korjakowska J, Kłeczek P: Automatic classification of specific melanocytic lesions using artificial intelligence. BioMed Res Int, 2016, p 17

  19. 19.

    Simonyan K, Zisserman A Very deep convolutional networks for large-scale image recognition. arXiv:abs/1409.1556, 2014

  20. 20.

    Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z: Rethinking theInception architecture for computer vision. arXiv:1512.00567, 2016, pp 2818–2826

  21. 21.

    Deng J, Dong W, Socher R, Li LJ, Li K, Fei Fei L: ImageNet: a large-scale hierarchical image database.. In: 2009 IEEE Conference on computer vision and pattern recognition. IEEE, MIami, 2009, pp 248–255

  22. 22.

    Applications - InceptionV3. [Online]., 2016. Accessed 01 Sept 2017

  23. 23.

    Yosinski J, Clune J, Bengio Y, Lipson H: How transferable are features in deep neural networks?. In: Advances in neural information processing systems. Curran Associates, Inc., New York, 2014, pp 3320–3328

  24. 24.

    Krizhevsky A, Sutskever I, Hinton GE: ImageNet classification with deep convolutional neural networks.. In: Advances in neural information processing systems, vol 25. Curran Associates, Inc., New York, 2012, pp 1097–1105

  25. 25.

    Python. [Online]., 2016. Accessed 01 Sept 2017

  26. 26.

    MathWorks: MATLAB. [Online]., 2016. Accessed 01 Sept 2017

  27. 27.

    Keras documentation. [Online]., 2016. Accessed 01 Sept 2017

  28. 28.

    Theano 0.8.2. documentation. [Online]., 2016. Accessed 01 Sept 2017

  29. 29.

    TensorFlow. [Online]., 2017. Accessed 01 Sept 2017

  30. 30.

    scikit-learn: machine learning in python. [Online]., 2016. Accessed 2017-09-01

  31. 31.

    Python Imaging Library (PIL). [Online]. Accessed 01 Sept 2017

  32. 32.

    CUDAm, Nvidia. [Online]. Accessed 01 Sept 2017

  33. 33.

    ISIC Archive - International skin imaging collaboration: melanoma project. [Online]., 2016. Accessed 01 Sept 2017

  34. 34.

    ISIC: ISBI 2016: Skin lesion analysis towards melanoma detection. [Online]., Accessed 2016. 31 Aug 2017

  35. 35.

    tf.train.RMSPropOptimizer. [Online]., 2017. Accessed 01 Sept 2017

Download references


The authors gratefully acknowledge funding from NSF Award No. 1464537, Industry/University Cooperative Research Center, Phase II under NSF 13-542. We are also thankful to the 33 corporations that are the members of the Center for their active participation and funding.

Author information



Corresponding author

Correspondence to Oge Marques.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Burdick, J., Marques, O., Weinthal, J. et al. Rethinking Skin Lesion Segmentation in a Convolutional Classifier. J Digit Imaging 31, 435–440 (2018).

Download citation


  • Medical decision support systems
  • Deep learning
  • Medical image analysis
  • Convolutional neural networks
  • Skin lesions
  • Machine learning