Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017 Journal Article


Authors: Marchetti, M. A.; Liopyris, K.; Dusza, S. W.; Codella, N. C. F.; Gutman, D. A.; Helba, B.; Kalloo, A.; Halpern, A. C.; for the International Skin Imaging Collaboration
Article Title: Computer algorithms show potential for improving dermatologists' accuracy to diagnose cutaneous melanoma: Results of the International Skin Imaging Collaboration 2017
Abstract: Background: Computer vision has promise in image-based cutaneous melanoma diagnosis but clinical utility is uncertain. Objective: To determine if computer algorithms from an international melanoma detection challenge can improve dermatologists' accuracy in diagnosing melanoma. Methods: In this cross-sectional study, we used 150 dermoscopy images (50 melanomas, 50 nevi, 50 seborrheic keratoses) from the test dataset of a melanoma detection challenge, along with algorithm results from 23 teams. Eight dermatologists and 9 dermatology residents classified dermoscopic lesion images in an online reader study and provided their confidence level. Results: The top-ranked computer algorithm had an area under the receiver operating characteristic curve of 0.87, which was higher than that of the dermatologists (0.74) and residents (0.66) (P <. 001 for all comparisons). At the dermatologists' overall sensitivity in classification of 76.0%, the algorithm had a superior specificity (85.0% vs. 72.6%, P = .001). Imputation of computer algorithm classifications into dermatologist evaluations with low confidence ratings (26.6% of evaluations) increased dermatologist sensitivity from 76.0% to 80.8% and specificity from 72.6% to 72.8%. Limitations: Artificial study setting lacking the full spectrum of skin lesions as well as clinical metadata. Conclusion: Accumulating evidence suggests that deep neural networks can classify skin images of melanoma and its benign mimickers with high accuracy and potentially improve human performance. © 2019 American Academy of Dermatology, Inc.
Keywords: major clinical study; cancer diagnosis; diagnostic accuracy; sensitivity and specificity; melanoma; image analysis; skin cancer; epiluminescence microscopy; resident; seborrheic keratosis; cross-sectional study; physician attitude; computer vision; cutaneous melanoma; dermatologist; diagnostic test accuracy study; pigmented nevus; machine learning; human; priority journal; article; deep learning; computer algorithm; international symposium on biomedical imaging; reader study; international skin imaging collaboration; automated melanoma diagnosis
Journal Title: Journal of the American Academy of Dermatology
Volume: 82
Issue: 3
ISSN: 0190-9622
Publisher: Mosby Elsevier  
Date Published: 2020-03-01
Start Page: 622
End Page: 627
Language: English
DOI: 10.1016/j.jaad.2019.07.016
PUBMED: 31306724
PROVIDER: scopus
PMCID: PMC7006718
DOI/URL:
Notes: Article -- Export Date: 2 March 2020 -- Source: Scopus
Altmetric
Citation Impact
MSK Authors
  1. Allan C Halpern
    330 Halpern
  2. Stephen Dusza
    203 Dusza
  3. Michael Armando Marchetti
    100 Marchetti
  4. Aadi Kalloo
    4 Kalloo