Improving artificial intelligence−based diagnosis on pediatric skin lesions Journal Article


Authors: Mehta, P. P.; Sun, M.; Betz-Stablein, B.; Halpern, A.; Soyer, H. P.; Weber, J.; Kose, K.; Rotemberg, V.
Article Title: Improving artificial intelligence−based diagnosis on pediatric skin lesions
Abstract: Artificial intelligence algorithms to classify melanoma are dependent on their training data, which limits generalizability. The objective of this study was to compare the performance of an artificial intelligence model trained on a standard adult-predominant dermoscopic dataset before and after the addition of additional pediatric training images. The performances were compared using held-out adult and pediatric test sets of images. We trained two models: one (model A) on an adult-predominant dataset (37,662 images from the International Skin Imaging Collaboration) and the other (model A+P) on an additional 1,536 pediatric images. We compared performance between the two models on adult and pediatric held-out test images separately using the area under the receiver operating characteristic curve. We then used Gradient-weighted Class Activation Maps and background skin masking to understand the contributions of the lesion versus background skin to algorithm decision making. Adding images from a pediatric population with different epidemiological and visual patterns to current reference standard datasets improved algorithm performance on pediatric images without diminishing performance on adult images. This suggests a way that dermatologic artificial intelligence models can be made more generalizable. The presence of background skin was important to the pediatric-specific improvement seen between models. Our study highlights the importance of carefully curated and labeled data from diverse inputs to improve the generalizability of AI models for dermatology, in this case applied to dermoscopic images of adult and pediatric lesions to improve melanoma detection. © 2023 The Authors
Keywords: adult; child; controlled study; melanoma; skin neoplasms; pathology; epiluminescence microscopy; skin; standard; skin tumor; algorithm; artificial intelligence; diagnosis; skin disease; decision making; skin diseases; receiver operating characteristic; humans; human; article; masking
Journal Title: Journal of Investigative Dermatology
Volume: 143
Issue: 8
ISSN: 0022-202X
Publisher: Elsevier Science, Inc.  
Date Published: 2023-08-01
Start Page: 1423
End Page: 1429.e1
Language: English
DOI: 10.1016/j.jid.2022.08.058
PUBMED: 36804150
PROVIDER: scopus
PMCID: PMC10431965
DOI/URL:
Notes: Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PDF -- MSK corresponding author is Paras Mehta -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Allan C Halpern
    396 Halpern
  2. Kivanc Kose
    82 Kose
  3. Jochen Weber
    16 Weber
  4. Paras Mehta
    14 Mehta
  5. Mary Sun
    10 Sun