Expert Agreement on the Presence and Spatial Localization of Melanocytic Features in Dermoscopy

Konstantinos Liopyris, Cristian Navarrete-Dechent, Michael A. Marchetti, Veronica Rotemberg, Zoe Apalla, Giuseppe Argenziano, Andreas Blum, Ralph P. Braun, Cristina Carrera, Noel C.F. Codella, Marc Combalia, Stephen W. Dusza, David A. Gutman, Brian Helba, Rainer Hofmann-Wellenhof, Natalia Jaimes, Harald Kittler, Kivanc Kose, Aimilios Lallas, Caterina LongoJosep Malvehy, Scott Menzies, Kelly C. Nelson, John Paoli, Susana Puig, Harold S. Rabinovitz, Ayelet Rishpon, Teresa Russo, Alon Scope, H. Peter Soyer, Jennifer A. Stein, Willhelm Stolz, Dimitrios Sgouros, Alexander J. Stratigos, David L. Swanson, Luc Thomas, Philipp Tschandl, Iris Zalaudek, Jochen Weber, Allan C. Halpern, Ashfaq A. Marghoob

Research output: Contribution to journalArticlepeer-review

Abstract

Dermoscopy aids in melanoma detection; however, agreement on dermoscopic features, including those of high clinical relevance, remains poor. In this study, we attempted to evaluate agreement among experts on exemplar images not only for the presence of melanocytic-specific features but also for spatial localization. This was a cross-sectional, multicenter, observational study. Dermoscopy images exhibiting at least 1 of 31 melanocytic-specific features were submitted by 25 world experts as exemplars. Using a web-based platform that allows for image markup of specific contrast-defined regions (superpixels), 20 expert readers annotated 248 dermoscopic images in collections of 62 images. Each collection was reviewed by five independent readers. A total of 4,507 feature observations were performed. Good-to-excellent agreement was found for 14 of 31 features (45.2%), with eight achieving excellent agreement (Gwet's AC >0.75) and seven of them being melanoma-specific features. These features were peppering/granularity (0.91), shiny white streaks (0.89), typical pigment network (0.83), blotch irregular (0.82), negative network (0.81), irregular globules (0.78), dotted vessels (0.77), and blue–whitish veil (0.76). By utilizing an exemplar dataset, a good-to-excellent agreement was found for 14 features that have previously been shown useful in discriminating nevi from melanoma. All images are public (www.isic-archive.com) and can be used for education, scientific communication, and machine learning experiments.

Original languageEnglish (US)
Pages (from-to)531-539.e13
JournalJournal of Investigative Dermatology
Volume144
Issue number3
DOIs
StatePublished - Mar 2024
Externally publishedYes

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Dermatology
  • Cell Biology

Fingerprint

Dive into the research topics of 'Expert Agreement on the Presence and Spatial Localization of Melanocytic Features in Dermoscopy'. Together they form a unique fingerprint.

Cite this