Prediction of melanoma metastasis using dermatoscopy deep features: an international multicentre cohort study

Whether dermatoscopy deep features could serve as biomarker for the prediction of melanoma metastasis remains an underexplored area in medical research. In this cohort of 712 patients from 10 centres in 3 continents, a support vector machine classifier that analysed deep features on dermatoscopic im...

Full description

Saved in:
Bibliographic Details
Published in:British journal of dermatology (1951) 2024-10, Vol.191 (5), p.847-848
Main Authors: Lallas, Konstantinos, Spyridonos, Panagiota, Kittler, Harald, Tschandl, Philipp, Liopyris, Konstantinos, Argenziano, Giuseppe, Bakos, Renato, Braun, Ralph, Cabo, Horacio, Dika, Emi, Malvehy, Josep, Marghoob, Ash, Puig, Susana, Scope, Alon, Stolz, Wilhelm, Tanaka, Masaru, Thomas, Luc, Apalla, Zoe, Vakirlis, Efstratios, Zalaudek, Iris, Lallas, Aimilios
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Whether dermatoscopy deep features could serve as biomarker for the prediction of melanoma metastasis remains an underexplored area in medical research. In this cohort of 712 patients from 10 centres in 3 continents, a support vector machine classifier that analysed deep features on dermatoscopic images demonstrated similar prognostic performance for metastasis in terms of AUC and true positive rate to current benchmarks of melanoma staging, namely Breslow thickness and ulceration. Deep features derived from dermatoscopy could predict early-stage melanomas with high metastatic potential, tailoring further treatment strategies.
ISSN:0007-0963
1365-2133
1365-2133
DOI:10.1093/bjd/ljae281