Advertisement

hautnah dermatologie

, Volume 35, Issue 2, pp 38–44 | Cite as

Deep Learning

Melanomdiagnose mithilfe künstlicher Intelligenz

  • Julia K. Winkler
  • Christine Fink
  • Ferdinand Toberer
  • Alexander Enk
  • Holger A. HänßleEmail author
Fortbildung
  • 50 Downloads

Für den praktizierenden Dermatologen ebenso wie für seine Patienten ist die Früherkennung des malignen Melanoms von zentraler Bedeutung. Der Patient setzt dabei großes Vertrauen in den diagnostischen Blick des Hautarztes. Ein erstes, zur klinischen Anwendung zugelassenenes Deep-Learning-Netzwerk kann dabei wertvolle Unterstützung leisten.

Literaur

  1. 1.
    Garbe C et al. Diagnosis and treatment of melanoma. European consensus-based interdisciplinary guideline.Update. 2016; Eur J Cancer. 2016; 63: 201–17PubMedGoogle Scholar
  2. 2.
    Balch CM et al. Final version of the American Joint Committee on Cancer staging system for cutaneous melanoma. J Clin Oncol. 2001; 19: 3635–48CrossRefGoogle Scholar
  3. 3.
    Yamashita R et al. Convolutional neural networks: an overview and application in radiology. Insights Imaging. 2018; 9: 611–29CrossRefGoogle Scholar
  4. 4.
    Du XL et al. Application of artificial intelligence in ophthalmology. Int J Ophthalmol. 2018; 11: 1555–61PubMedPubMedCentralGoogle Scholar
  5. 5.
    Sun J et al. Comparison of deep learning architectures for H&E histopathology images. IEEE Conference on Big Data and Analytics (ICBDA). 2017; http://doi.org/czz5Google Scholar
  6. 6.
    Tschandl P et al. Diagnostic accuracy of content]based dermatoscopic image retrieval with deep classification features. Br J Dermatol. 2018; http://doi.org/czz3Google Scholar
  7. 7.
    Grob J et al. The ‘ugly duckling’ sign: identification of the common characteristics of nevi in an individual as a basis for -melanoma screening. Arch Dermatol. 1998; 134: 103–4CrossRefGoogle Scholar
  8. 8.
    Friedman RJ et al. Early detection of malignant melanoma: the role of physician examination and self-examination of the skin. CA Cancer J Clin. 1985; 35: 130–51CrossRefGoogle Scholar
  9. 9.
    Abbasi et al. Early diagnosis of cutaneous melanoma: revisiting the ABCD criteria. JAMA. 2004; 292: 2771–6CrossRefGoogle Scholar
  10. 10.
    Blum et al. The status of dermoscopy in Germany.results of the cross]sectional Pan]Euro]Dermoscopy Study. J Dtsch Dermatol Ges. 2018; 16: 174–81PubMedGoogle Scholar
  11. 11.
    Bafounta et al. Is dermoscopy (epiluminescence microscopy) useful for the diagnosis of melanoma?: Results of a meta-analysis using techniques adapted to the evaluation of diagnostic tests. Arch Dermatol. 2001; 137: 1343–50CrossRefGoogle Scholar
  12. 12.
    Vestergaard et al. 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. 2008; 159: 669–76PubMedGoogle Scholar
  13. 13.
    Pehamberger H et al. In vivo epiluminescence microscopy of pigmented skin lesions. I. Pattern analysis of pigmented skin lesions. J Am Acad Dermatol. 1987. 17: 571–83CrossRefGoogle Scholar
  14. 14.
    Stolz W. ABCD rule of dermatoscopy: a new practical method for early recognition of malignant melanoma. Eur J Dermatol. 1994; 4: 521–7Google Scholar
  15. 15.
    Menzies SW et al. Dermoscopic evaluation of nodular melanoma. JAMA. 2013; 149: 699–709Google Scholar
  16. 16.
    Argenziano G. et al. 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. 1998; 134: 1563–70CrossRefGoogle Scholar
  17. 17.
    Menzies SW et al. Frequency and morphologic characteristics of invasive melanomas lacking specific surface microscopic features. Arch Dermatol. 1996; 132: 1178–82CrossRefGoogle Scholar
  18. 18.
    Argenziano G et al. Seven-point checklist of dermoscopy revisited. Br J Dermatol. 2011; 164: 785–90CrossRefGoogle Scholar
  19. 19.
    Fink C et al. Strategien zur nichtinvasiven Diagnostik des Melanoms/ Strategies for the noninvasive diagnosis of melanoma. Der Hautarzt. 2016; 67: 519–28CrossRefGoogle Scholar
  20. 20.
    Okur E et al. A survey on automated melanoma detection. Eng Appl Artif Intell. 2018; 73: 50–67CrossRefGoogle Scholar
  21. 21.
    Dick V et al. Bildbasierte Computerdiagnose des Melanoms. Der Hautarzt. 2018; 69: 591–601CrossRefGoogle Scholar
  22. 22.
    Nasr-Esfahani E et al. Melanoma detection by analysis of clinical images using convolutional neural network. 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2016; http://doi.org/gcgk97Google Scholar
  23. 23.
    Codella NCF et al. 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). IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). 2018; http://doi.org/czz6Google Scholar
  24. 24.
    Tschandl P et al. The HAM10000 Dataset: A Large Collection of Multi-Source Dermatoscopic Images of Common Pigmented Skin Lesions. Sci Data. 2018; 5: 180161CrossRefGoogle Scholar
  25. 25.
    Brinker TJ et al. Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review. J Med Internet Res. 2018; 20: e11936CrossRefGoogle Scholar
  26. 26.
    Esteva A et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542: 115–8CrossRefGoogle Scholar
  27. 27.
    Haenssle HA et al. Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol. 2018; 29: 1836–42CrossRefGoogle Scholar
  28. 28.
    The International Skin Imaging Collaboration (ISIC): Melanoma Project. https://www.isic-archive.com (zuletzt aufgerufen am 25.01.2019)

Copyright information

© Springer Medizin Verlag GmbH, ein Teil von Springer Nature 2019

Authors and Affiliations

  • Julia K. Winkler
    • 1
  • Christine Fink
    • 1
  • Ferdinand Toberer
    • 1
  • Alexander Enk
    • 1
  • Holger A. Hänßle
    • 1
    Email author
  1. 1.Universitätshautklinik HeidelbergHeidelbergDeutschland

Personalised recommendations