体育赛事投注记录

advertisement

Skin Lesion Analyser: An Efficient Seven-Way Multi-class Skin Cancer Classification Using MobileNet

  • Saket S. ChaturvediEmail author
  • Kajol Gupta
  • Prakash S. Prasad
Conference paper
  • 76 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1141)

Abstract

Skin cancer is an emerging global health problem with 123,000 melanoma and 3,000,000 non-melanoma cases worldwide each year. The recent studies have reported excessive exposure to ultraviolet rays as a major factor in developing skin cancer. The most effective solution to control the death rate for skin cancer is a timely diagnosis of skin lesions as the five-year survival rate for melanoma patients is 99% when diagnosed and screened at the early stage. Considering an inability of dermatologists for accurate diagnosis of skin cancer, there is a need to develop an automated efficient system for the diagnosis of skin cancer. This study explores an efficient automated method for skin cancer classification with better evaluation metrics as compared to previous studies or expert dermatologists. We utilized a MobileNet model pretrained on approximately 1,280,000 images from 2014 ImageNet Challenge and finetuned on 10,015 dermoscopy images of HAM10000 dataset employing transfer learning. The model used in this study achieved an overall accuracy of 83.1% for seven classes in the dataset, whereas top2 and top3 accuracies of 91.36% and 95.34%, respectively. Also, the weighted average of precision, weighted average of recall, and weighted average of f1-score were found to be 89%, 83%, and 83%, respectively. This method has the potential to assist dermatology specialists in decision making at critical stages. We have deployed our deep learning model at 体育赛事投注记录 as Web application.

Keywords

Skin cancer Dermoscopy Classification Convolutional neural network 

References

  1. 1.
    Stewart, B.W., Wild, C.: International Agency for Research on Cancer, and World Health Organization. World cancer report (2014)
  2. 2.
    Cakir, B.O., Adamson, P., Cingi, C.: Epidemiology and economic burden of nonmelanoma skin cancer. Facial Plast. Surg. Clin. North Am. 20(4), 419–422 (2012).  
  3. 3.
    Rogers, H.W., Weinstock, M.A., Feldman, S.R., Coldiron, B.M.: Incidence estimate of nonmelanoma skin cancer (Keratinocyte carcinomas) in the U.S. population, 2012. JAMA Dermatol. 151(10), 1081–1086 (2015).  
  4. 4.
    Stern, R.S.: Prevalence of a history of skin cancer in 2007: results of an incidence-based model. Arch. Dermatol. 146(3), 279–282 (2010).  
  5. 5.
    WHO: Skin cancers WHO (2017)
  6. 6.
    Koh, H.K., Geller, A.C., Miller, D.R., Grossbart, T.A., Lew, R.A.: Prevention and early detection strategies for melanoma and skin cancer current status. Arch. Dermatol. 132(4), 436–443 (1996).  
  7. 7.
    Parkin, D.M., Mesher, D., Sasieni, P.: Cancers attributable to solar (ultraviolet) radiation exposure in the UK in 2010. Br. J. Cancer 105(2), S66–S69 (2011).  
  8. 8.
    Canadian Cancer Society. Risk factors for melanoma skin cancer (2018). . Accessed 31 Mar 2019
  9. 9.
    Cancer facts & figures 2016. Atlanta, American Cancer Society (2016). . Accessed 31 Mar 2019
  10. 10.
    Siegel, R.L., Miller, K.D., Jemal, A.: Cancer statistics, 2017. CA Cancer J. Clin. 67(1), 7–30 (2017).  
  11. 11.
    Neville, J.A., Welch, E., Leffell, D.J.: Management of nonmelanoma skin cancer in 2007. Nat. Clin. Pract. Oncol. 4(8), 462–469 (2007).  
  12. 12.
    Morton, C.A., Mackie, R.M.: Clinical accuracy of the diagnosis of cutaneous malignant melanoma. Br. J. Dermatol. 138(2), 283–287 (1998).  
  13. 13.
    Binder, M., Schwarz, M., Winkler, A., et al.: Epiluminescence microscopy. A useful tool for the diagnosis of pigmented skin lesions for formally trained dermatologists. Arch. Dermatol. 131(3), 286–291 (1995).  
  14. 14.
    Piccolo, D., Ferrari, A., Peris, K., Daidone, R., Ruggeri, B., Chimenti, S.: Dermoscopic diagnosis by a trained clinician vs. a clinician with minimal dermoscopy training vs. computer-aided diagnosis of 341 pigmented skin lesions: a comparative study. Br. J. Dermatol. 147(3), 481–486 (2002).  
  15. 15.
    Argenziano, G., et al.: Dermoscopy of pigmented skin lesions: results of a consensus meeting via the Internet. J. Am. Acad. Dermatol. 48(5), 679–693 (2003).  
  16. 16.
    Kittler, H., Pehamberger, H., Wolff, K., Binder, M.: Diagnostic accuracy of dermoscopy. Lancet. Oncol. 3(3), 159–165 (2002).  
  17. 17.
    Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484–489 (2016).  
  18. 18.
    Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).  
  19. 19.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015).  
  20. 20.
    Vestergaard, M.E., Macaskill, P., Holt, P.E., Menzies, S.W.: Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta-analysis of studies performed in a clinical setting. Br. J. Dermatol. 159(3), 669–676 (2008).  
  21. 21.
    Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115–118 (2017).  
  22. 22.
    Rogers, H.W., Weinstock, M.A., Feldman, S.R., Coldiron, B.M.: Incidence estimate of nonmelanoma skin cancer (Keratinocyte carcinomas) in the US population. JAMA Dermatol. 151(10), 1081 (2015).  
  23. 23.
    Stern, R.S.: Prevalence of a history of skin cancer in 2007. Arch. Dermatol. 146(3), 279–282 (2010).  
  24. 24.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015).  
  25. 25.
    Arbib, M.A.: The Handbook of Brain Theory and Neural Networks. MIT Press (1998)
  26. 26.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017).  
  27. 27.
    Liu, L., Yan, R.J., Maruvanchery, V., Kayacan, E., Chen, I.M., Tiong, L.K.: Transfer learning on convolutional activation feature as applied to a building quality assessment robot. Int. J. Adv. Robot. Syst. 14(3), 172988141771262 (2017).  
  28. 28.
    Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015).  
  29. 29.
    Ding, P., Zhang, Y., Deng, W.J., Jia, P., Kuijper, A.: A light and faster regional convolutional neural network for object detection in optical remote sensing images. ISPRS J. Photogramm. Remote Sens. 141, 208–218 (2018).  
  30. 30.
    Masood, A., Al-Jumaily, A.A.: Computer aided diagnostic support system for skin cancer: a review of techniques and algorithms. Int. J. Biomed. Imaging 323268 (2013).
  31. 31.
    Khosla, A., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015).  
  32. 32.
    Rosado, B., et al.: Accuracy of computer diagnosis of melanoma: a quantitative meta-analysis. Arch. Dermatol. 139(3), 361–367 (2003).  
  33. 33.
    Burroni, M., et al.: Melanoma computer-aided diagnosis: reliability and feasibility study. Clin. Cancer Res. 10(6), 1881–1886 (2004).  
  34. 34.
    Kawahara, J., Hamarneh, G.: Multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers. In: Wang, L., Adeli, E., Wang, Q., Shi, Y., Suk, H.I. (eds.) Machine Learning in Medical Imaging. MLMI 2016. Lecture Notes in Computer Science, p. 10019 (2016).  
  35. 35.
    Milton, M.A.A.: Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge (2019)
  36. 36.
    Hardie, R.C., Ali, R., De Silva, M.S., Kebede, T.M.: Skin Lesion Segmentation and Classification for ISIC 2018 Using Traditional Classifiers with Hand-Crafted Features.
  37. 37.
    Howard, A.G., et al.: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (2017).
  38. 38.
    Tschandl, P., Rosendahl, C., Kittler, H.: The HAM10000 dataset, a large collection of multi-sources dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 (2018).  
  39. 39.
    Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big Data 3(1), 1345–1359 (2016).  
  40. 40.
    Image Preprocessing—Keras Documentation. Keras (2019). . Accessed 31 Mar 2019
  41. 41.
    Pandas: Working with missing data—pandas 0.22.0 documentation (2019). . Accessed 31 Mar 2019
  42. 42.
    Mikolajczyk, A., Grochowski, M.: Data augmentation for improving deep learning in image classification problem. In: International Interdisciplinary Ph.D. Workshop (IIPhDW), pp. 117–122 (2018).  
  43. 43.
    Kaggle: Your Home for Data Science. . Accessed 31 Mar 2019

Copyright information

© Springer Nature Singapore Pte Ltd. 2021

Authors and Affiliations

  • Saket S. Chaturvedi
    • 1
    Email author
  • Kajol Gupta
    • 1
  • Prakash S. Prasad
    • 1
  1. 1.Department of Computer Science & EngineeringPriyadarshini Institute of Engineering & TechnologyNagpurIndia

Personalised recommendations