TY - JOUR
T1 - Expert Agreement on the Presence and Spatial Localization of Melanocytic Features in Dermoscopy
AU - Liopyris, Konstantinos
AU - Navarrete-Dechent, Cristian
AU - Marchetti, Michael A.
AU - Rotemberg, Veronica
AU - Apalla, Zoe
AU - Argenziano, Giuseppe
AU - Blum, Andreas
AU - Braun, Ralph P.
AU - Carrera, Cristina
AU - Codella, Noel C.F.
AU - Combalia, Marc
AU - Dusza, Stephen W.
AU - Gutman, David A.
AU - Helba, Brian
AU - Hofmann-Wellenhof, Rainer
AU - Jaimes, Natalia
AU - Kittler, Harald
AU - Kose, Kivanc
AU - Lallas, Aimilios
AU - Longo, Caterina
AU - Malvehy, Josep
AU - Menzies, Scott
AU - Nelson, Kelly C.
AU - Paoli, John
AU - Puig, Susana
AU - Rabinovitz, Harold S.
AU - Rishpon, Ayelet
AU - Russo, Teresa
AU - Scope, Alon
AU - Soyer, H. Peter
AU - Stein, Jennifer A.
AU - Stolz, Willhelm
AU - Sgouros, Dimitrios
AU - Stratigos, Alexander J.
AU - Swanson, David L.
AU - Thomas, Luc
AU - Tschandl, Philipp
AU - Zalaudek, Iris
AU - Weber, Jochen
AU - Halpern, Allan C.
AU - Marghoob, Ashfaq A.
N1 - Publisher Copyright:
© 2023 The Authors
PY - 2024/3
Y1 - 2024/3
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85182659405&partnerID=8YFLogxK
U2 - 10.1016/j.jid.2023.01.045
DO - 10.1016/j.jid.2023.01.045
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 37689267
AN - SCOPUS:85182659405
SN - 0022-202X
VL - 144
SP - 531-539.e13
JO - Journal of Investigative Dermatology
JF - Journal of Investigative Dermatology
IS - 3
ER -