Home > Journals > Italian Journal of Dermatology and Venereology > Past Issues > Italian Journal of Dermatology and Venereology 2021 June;156(3) > Italian Journal of Dermatology and Venereology 2021 June;156(3):289-99

CURRENT ISSUE
 

JOURNAL TOOLS

eTOC
To subscribe PROMO
Submit an article
Recommend to your librarian
 

ARTICLE TOOLS

Publication history
Reprints
Permissions
Cite this article as
Share

 

REVIEW  MELANOMA DIAGNOSIS AND MANAGEMENT Freefree

Italian Journal of Dermatology and Venereology 2021 June;156(3):289-99

DOI: 10.23736/S2784-8671.20.06753-X

Copyright © 2020 EDIZIONI MINERVA MEDICA

language: English

Artificial intelligence for melanoma diagnosis

Philipp TSCHANDL

Department of Dermatology, Medical University of Vienna, Vienna, Austria



Convolutional neural networks (CNN) have shown unprecedented accuracy in digital image analysis, which can be harnessed for melanoma recognition through automated evaluation of clinical and dermatoscopic images. In experimental studies, modern CNN architectures perform single image analysis at the level of dermatologists and domain-experts, also for multiclass predictions including a multitude of possible diagnoses. This may not necessarily translate to good clinical performance, and reliable randomized controlled prospective clinical trials for modern CNNs are essentially missing. Weaknesses of CNNs are that limitations of available training image datasets propagate to limitations of CNN predictions, and they cannot provide a reliable estimate of uncertainty. Recent research focuses on human-computer collaboration, where gains in accuracy were measured even with imperfect CNNs. With missing academic and clinical agreement on equivocal melanocytic lesions, fully automating histologic assessment of them with CNNs appear problematic, and applications in the near future are probably limited to supporting, referencing or recommendation roles.


KEY WORDS: Melanoma; Diagnosis; Dermoscopy; Artificial intelligence; Neural networks, computer; Machine learning

top of page