Prediction of melanoma metastasis using dermatoscopy deep features: an international multicentre cohort study Journal Article
| Authors: | Lallas, K.; Spyridonos, P.; Kittler, H.; Tschandl, P.; Liopyris, K.; Argenziano, G.; Bakos, R.; Braun, R.; Cabo, H.; Dika, E.; Malvehy, J.; Marghoob, A.; Puig, S.; Scope, A.; Stolz, W.; Tanaka, M.; Thomas, L.; Apalla, Z.; Vakirlis, E.; Zalaudek, I.; Lallas, A. |
| Article Title: | Prediction of melanoma metastasis using dermatoscopy deep features: an international multicentre cohort study |
| Abstract: | 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. |
| Journal Title: | British Journal of Dermatology |
| ISSN: | 0007-0963 |
| Publisher: | Blackwell Publishing |
| Publication status: | Online ahead of print |
| Date Published: | 2024-01-01 |
| Online Publication Date: | 2024-01-01 |
| Language: | English |
| ACCESSION: | WOS:001294484300001 |
| DOI: | 10.1093/bjd/ljae281 |
| PROVIDER: | wos |
| Notes: | Article; Early Access -- Source: Wos |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work