Multiple studies have compared the performance of artificial intelligence (AI)-based models for automated skin cancer classification to human experts, thus setting the cornerstone for a successful translation of AI-based tools into clinicopathological practice.
The objective of the study was to systematically analyse the current state of research on reader studies involving melanoma and to assess their potential clinical relevance by evaluating three main aspects: test set characteristics (holdout/out-of-distribution data set, composition), test setting (experimental/clinical, inclusion of metadata) and representativeness of participating clinicians.
PubMed, Medline and ScienceDirect were screened for peer-reviewed studies published between 2017 and 2021 and dealing with AI-based skin cancer classification involving melanoma. The search terms skin cancer classification, deep learning, convolutional neural network (CNN), melanoma (detection), digital biomarkers, histopathology and whole slide imaging were combined. Based on the search results, only studies that considered direct comparison of AI results with clinicians and had a diagnostic classification as their main objective were included.
A total of 19 reader studies fulfilled the inclusion criteria. Of these, 11 CNN-based approaches addressed the classification of dermoscopic images; 6 concentrated on the classification of clinical images, whereas 2 dermatopathological studies utilised digitised histopathological whole slide images.
All 19 included studies demonstrated superior or at least equivalent performance of CNN-based classifiers compared with clinicians. However, almost all studies were conducted in highly artificial settings based exclusively on single images of the suspicious lesions. Moreover, test sets mainly consisted of holdout images and did not represent the full range of patient populations and melanoma subtypes encountered in clinical practice.
Copyright © 2021 The Author(s). Published by Elsevier Ltd.. All rights reserved.
About The Expert
Sarah Haggenmüller
Roman C Maron
Achim Hekler
Jochen S Utikal
Catarina Barata
Raymond L Barnhill
Helmut Beltraminelli
Carola Berking
Brigid Betz-Stablein
Andreas Blum
Stephan A Braun
Richard Carr
Marc Combalia
Maria-Teresa Fernandez-Figueras
Gerardo Ferrara
Sylvie Fraitag
Lars E French
Frank F Gellrich
Kamran Ghoreschi
Matthias Goebeler
Pascale Guitera
Holger A Haenssle
Sebastian Haferkamp
Lucie Heinzerling
Markus V Heppt
Franz J Hilke
Sarah Hobelsberger
Dieter Krahl
Heinz Kutzner
Aimilios Lallas
Konstantinos Liopyris
Mar Llamas-Velasco
Josep Malvehy
Friedegund Meier
Cornelia S L Müller
Alexander A Navarini
Cristián Navarrete-Dechent
Antonio Perasole
Gabriela Poch
Sebastian Podlipnik
Luis Requena
Veronica M Rotemberg
Andrea Saggini
Omar P Sangueza
Carlos Santonja
Dirk Schadendorf
Bastian Schilling
Max Schlaak
Justin G Schlager
Mildred Sergon
Wiebke Sondermann
H Peter Soyer
Hans Starz
Wilhelm Stolz
Esmeralda Vale
Wolfgang Weyers
Alexander Zink
Eva Krieghoff-Henning
Jakob N Kather
Christof von Kalle
Daniel B Lipka
Stefan Fröhling
Axel Hauschild
Harald Kittler
Titus J Brinker
References
PubMed