Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists

2018 Annals of Oncology 1,435 citations

Abstract

This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; https://www.drks.de/drks_web/).

Keywords

MedicineConvolutional neural networkReceiver operating characteristicArtificial intelligenceMedical diagnosisDiagnostic accuracyArea under curveDeep learningMelanomaPattern recognition (psychology)Machine learningRadiologyComputer scienceInternal medicine

MeSH Terms

Clinical CompetenceCross-Sectional StudiesDeep LearningDermatologistsDermoscopyHumansImage ProcessingComputer-AssistedInternational CooperationMelanomaROC CurveRetrospective StudiesSkinSkin Neoplasms

Affiliated Institutions

Related Publications

ROC Methodology in Radiologic Imaging

If the performance of a diagnostic imaging system is to be evaluated objectively and meaningfully, one must compare radiologists' image-based diagnoses with actual states of dis...

1986 Investigative Radiology 1632 citations

Publication Info

Year
2018
Type
article
Volume
29
Issue
8
Pages
1836-1842
Citations
1435
Access
Closed

Citation Metrics

1435
OpenAlex
39
Influential
1187
CrossRef

Cite This

Holger A. Haenssle, Christine Fink, Roland Schneiderbauer et al. (2018). Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Annals of Oncology , 29 (8) , 1836-1842. https://doi.org/10.1093/annonc/mdy166

Identifiers

DOI
10.1093/annonc/mdy166
PMID
29846502

Data Quality

Data completeness: 86%