Advertisement

U-Net Based Segmentation and Multiple Feature Extraction of Dermascopic Images for Efficient Diagnosis of Melanoma

  • D. Roja RamaniEmail author
  • S. Siva Ranjani
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 31)

Abstract

Skin cancer is found to be one of the most common types of deadly cancers among human beings in recent years. Computational-based techniques are developed to support the dermatologists for the early diagnosis of skin cancer. Computational analysis of the skin lesions in the dermascopic images is a challenging task due to the difficulties such as low-level of contrast between the lesion and surrounding skin regions, irregular and vague lesion borders, artifacts and poor imaging conditions. This paper presents a U-Net based segmentation and multiple feature extraction of the dermascopic images for the efficient diagnosis of skin cancer. The input dermascopic image is preprocessed to remove the noise and hair in the skin image. Fast Independent Component Analysis (FastICA) is applied to the skin images for obtaining the melanin and hemoglobin components. The U-net segmentation is applied to the dermascopic image to separate the cancer region from the background of the skin image. Different features such as vascular features, color features, texture features, RGB features, and depth features are extracted from the segmented image. RVM classification is applied to classify the normal and abnormal images. With the efficient segmentation and extraction of multiple features, our proposed work yields better performance than the existing segmentation and feature extraction techniques.

Keywords

Melanoma Independent component analysis U-Net segmentation Vascular features 

References

  1. 1.
    Sumithra R, Suhil M, Guru D (2015) Segmentation and classification of skin lesions for disease diagnosis. Procedia Comput Sci 45:76–85CrossRefGoogle Scholar
  2. 2.
    A. C. Society (2018) Key statistics for melanoma skin cancer. https://www.cancer.org/cancer/melanoma-skin-cancer/about/key-statistics.html
  3. 3.
  4. 4.
    Oliveira RB, Marranghello N, Pereira AS, Tavares JMR (2016) A computational approach for detecting pigmented skin lesions in macroscopic images. Expert Syst Appl 61:53–63CrossRefGoogle Scholar
  5. 5.
    Korotkov K, Garcia R (2012) Computerized analysis of pigmented skin lesions: a review. Artif Intell Med 56:69–90CrossRefGoogle Scholar
  6. 6.
    Smith L, MacNeil S (2011) State of the art in non-invasive imaging of cutaneous melanoma. Skin Res Technol 17:257–269CrossRefGoogle Scholar
  7. 7.
    Abbas Q, Celebi ME, Garcia I (2012) A novel perceptually-oriented approach for skin tumor segmentation. Int J Innov Comput Inf Control 8:1837–1848Google Scholar
  8. 8.
    Schaefer G, Rajab MI, Celebi ME, Iyatomi H (2011) Colour and contrast enhancement for improved skin lesion segmentation. Comput Med Imaging Graph 35:99–104CrossRefGoogle Scholar
  9. 9.
    Abbas Q, Garcia IF, Emre Celebi M, Ahmad W, Mushtaq Q (2013) A perceptually oriented method for contrast enhancement and segmentation of dermoscopy images. Skin Res Technol 19CrossRefGoogle Scholar
  10. 10.
    Ganster H, Pinz P, Rohrer R, Wildling E, Binder M, Kittler H (2001) Automated melanoma recognition. IEEE Trans Med Imaging 20:233–239CrossRefGoogle Scholar
  11. 11.
    Celebi ME, Kingravi HA, Uddin B, Iyatomi H, Aslandogan YA, Stoecker WV et al (2007) A methodological approach to the classification of dermoscopy images. Comput Med Imaging Graph 31:362–373CrossRefGoogle Scholar
  12. 12.
    Yuan Y, Chao M, Lo Y-C (2017) Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Trans Med Imaging 36:1876–1886CrossRefGoogle Scholar
  13. 13.
    Cavalcanti PG, Scharcanski J (2013) Macroscopic pigmented skin lesion segmentation and its influence on lesion classification and diagnosis. In: Color medical image analysis. Springer, pp 15–39Google Scholar
  14. 14.
    Majumder SK, Ghosh N, Gupta PK (2005) Relevance vector machine for optical diagnosis of cancer. Lasers Surg Med 36:323–333CrossRefGoogle Scholar
  15. 15.
    Benazzi C, Al-Dissi A, Chau C, Figg W, Sarli G, de Oliveira J et al (2014) Angiogenesis in spontaneous tumors and implications for comparative tumor biology. Sci World J 2014Google Scholar
  16. 16.
    Kharazmi P, AlJasser MI, Lui H, Wang ZJ, Lee TK (2017) Automated detection and segmentation of vascular structures of skin lesions seen in dermoscopy, with an application to basal cell carcinoma classification. IEEE J Biomed Health Inform 21:1675–1684CrossRefGoogle Scholar
  17. 17.
    Emre Celebi M, Wen Q, Hwang S, Iyatomi H, Schaefer G (2013) Lesion border detection in dermoscopy images using ensembles of thresholding methods. Skin Res Technol 19CrossRefGoogle Scholar
  18. 18.
    Peruch F, Bogo F, Bonazza M, Cappelleri V-M, Peserico E (2014) Simpler, faster, more accurate melanocytic lesion segmentation through meds. IEEE Trans Biomed Eng 61:557–565CrossRefGoogle Scholar
  19. 19.
    Zhou H, Li X, Schaefer G, Celebi ME, Miller P (2013) Mean shift based gradient vector flow for image segmentation. Comput Vis Image Underst 117:1004–1016CrossRefGoogle Scholar
  20. 20.
    Sadri AR, Zekri M, Sadri S, Gheissari N, Mokhtari M, Kolahdouzan F (2013) Segmentation of dermoscopy images using wavelet networks. IEEE Trans Biomed Eng 60:1134–1141CrossRefGoogle Scholar
  21. 21.
    Xie F, Bovik AC (2013) Automatic segmentation of dermoscopy images using self-generating neural networks seeded by genetic algorithm. Pattern Recognit 46:1012–1019CrossRefGoogle Scholar
  22. 22.
    Celebi ME, Wen Q, Iyatomi H, Shimizu K, Zhou H, Schaefer G (2015) A state-of-the-art survey on lesion border detection in dermoscopy images. Dermoscopy Image Anal 97–129Google Scholar
  23. 23.
    Nasr-Esfahani E, Samavi S, Karimi N, Soroushmehr SMR, Jafari MH, Ward K et al (2016) Melanoma detection by analysis of clinical images using convolutional neural network. In: 2016 IEEE 38th annual international conference of the engineering in medicine and biology society (EMBC), pp 1373–1376Google Scholar
  24. 24.
    Esteva A, Kuprel B, Thrun S (2015) Deep networks for early stage skin disease and skin cancer classification. Project report, Stanford UniversityGoogle Scholar
  25. 25.
    Jafari MH, Nasr-Esfahani E, Karimi N, Soroushmehr S, Samavi S, Najarian K (2016) Extraction of skin lesions from non-dermoscopic images using deep learning. arXiv:1609.02374
  26. 26.
    Jafari MH, Karimi N, Nasr-Esfahani E, Samavi S, Soroushmehr SMR, Ward K et al (2016) Skin lesion segmentation in clinical images using deep learning. In: 23rd international conference on pattern recognition (ICPR), pp 337–342Google Scholar
  27. 27.
    Li Y, Shen L (2018) Skin lesion analysis towards melanoma detection using deep learning network. Sensors 18:556CrossRefGoogle Scholar
  28. 28.
    Kawahara J, Hamarneh G (2017) Fully convolutional networks to detect clinical dermoscopic features. arXiv:1703.04559
  29. 29.
    Jaleel JA, Salim S, Aswin R (2013) Computer aided detection of skin cancer. In: International conference on circuits, power and computing technologies (ICCPCT), pp 1137–1142Google Scholar
  30. 30.
    Gutman D, Codella NC, Celebi E, Helba B, Marchetti M, Mishra N et al (2016) Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC). arXiv:1605.01397
  31. 31.
    Tsumura N, Haneishi H, Miyake Y (1999) Independent-component analysis of skin color image. JOSA A 16:2169–2176CrossRefGoogle Scholar
  32. 32.
    Agrawal P, Shriwastava S, Limaye S (2010) MATLAB implementation of image segmentation algorithms. In: 2010 3rd IEEE international conference on computer science and information technology (ICCSIT), pp 427–431Google Scholar
  33. 33.
    Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440Google Scholar
  34. 34.
    Kavitha J, Suruliandi A (2016) Texture and color feature extraction for classification of melanoma using SVM. In: International conference on computing technologies and intelligent data engineering (ICCTIDE), pp 1–6Google Scholar
  35. 35.
    Chen Y, Wang JZ (2004) Image categorization by learning and reasoning with regions. J Mach Learn Res 5:913–939MathSciNetGoogle Scholar
  36. 36.
    Gersho A (1979) Asymptotically optimal block quantization. IEEE Trans Inf Theory 25:373–380MathSciNetCrossRefGoogle Scholar
  37. 37.
    Zhang G, Shu X, Liang Z, Liang Y, Chen S, Yin J (2012) Multi-instance learning for skin biopsy image features recognition. In: 2012 IEEE international conference on bioinformatics and biomedicine (BIBM), pp 1–6Google Scholar
  38. 38.
    Levin A, Lischinski D, Weiss Y (2008) A closed-form solution to natural image matting. IEEE Trans Pattern Anal Mach Intell 30:228–242CrossRefGoogle Scholar
  39. 39.
    Satheesha T, Satyanarayana D, Prasad MG, Dhruve KD (2017) Melanoma is skin deep: a 3D reconstruction technique for computerized dermoscopic skin lesion classification. IEEE J Trans Eng Health Med 5:1–17CrossRefGoogle Scholar
  40. 40.
    Ripley BD (1996) Pattern recognition via neural networks. A volume of Oxford graduate lectures on neural networks, title to be decided. Oxford University Press. http://www.stats.ox.ac.uk/ripley/papers.html
  41. 41.
    Wei L, Yang Y, Nishikawa RM, Wernick MN, Edwards A (2005) Relevance vector machine for automatic detection of clustered microcalcifications. IEEE Trans Med Imaging 24:1278–1285CrossRefGoogle Scholar
  42. 42.
    Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39:2481–2495CrossRefGoogle Scholar
  43. 43.
    Bozorgtabar B, Sedai S, Roy PK, Garnavi R (2017) Skin lesion segmentation using deep convolution networks guided by local unsupervised learning. IBM J Res Dev 61:6: 1–6:8Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Information TechnologySethu Institute of TechnologyPulloorIndia

Personalised recommendations