Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task
Recent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
10 April 2019
|
| In: |
European journal of cancer
Year: 2019, Volume: 113, Pages: 47-54 |
| ISSN: | 1879-0852 |
| DOI: | 10.1016/j.ejca.2019.04.001 |
| Online Access: | Resolving-System, Volltext: https://doi.org/10.1016/j.ejca.2019.04.001 Verlag: http://www.sciencedirect.com/science/article/pii/S0959804919302217 
|
| Author Notes: | Titus J. Brinker, Achim Hekler, Alexander H. Enk, Joachim Klode, Axel Hauschild, Carola Berking, Bastian Schilling, Sebastian Haferkamp, Dirk Schadendorf, Tim Holland-Letz, Jochen S. Utikal, Christof von Kalle, collaborators |
| Summary: | Recent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm trained by open-source images exclusively is compared to a large number of dermatologists covering all levels within the clinical hierarchy. |
|---|---|
| Item Description: | Gesehen am 15.10.2019 |
| Physical Description: | Online Resource |
| ISSN: | 1879-0852 |
| DOI: | 10.1016/j.ejca.2019.04.001 |