Identifying melanoma among benign simulators: is there a role for deep learning convolutional neural networks? (MelSim Study)
Importance - Early detection of cutaneous melanoma (CM) is crucial for patient survival, yet avoiding overdiagnosis remains essential. Differentiating CM from benign melanoma simulators (MelSim) is challenging due to overlapping features. Deep learning convolutional neural networks (DL-CNNs) have de...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
10 August 2025
|
| In: |
European journal of cancer
Year: 2025, Jahrgang: 227, Pages: 115706$p1-8 |
| ISSN: | 1879-0852 |
| DOI: | 10.1016/j.ejca.2025.115706 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1016/j.ejca.2025.115706 Verlag, kostenfrei, Volltext: https://www.sciencedirect.com/science/article/pii/S0959804925004885 
|
| Verfasserangaben: | A. S. Vollmer, J. K. Winkler, K. S. Kommoss, A. Blum, W. Stolz, A. Enk, H. A. Haenssle |
| Zusammenfassung: | Importance - Early detection of cutaneous melanoma (CM) is crucial for patient survival, yet avoiding overdiagnosis remains essential. Differentiating CM from benign melanoma simulators (MelSim) is challenging due to overlapping features. Deep learning convolutional neural networks (DL-CNNs) have demonstrated dermatologist-level accuracy in identifying CM. We hypothesized that support from DL-CNN could increase dermatologists’ accuracy in differentiating CM from MelSim. - Methods - This cross-sectional reader study analyzed the diagnostic performance of a DL-CNN and 27 dermatologists for 200 skin lesions (100 CM, 100 MelSim). The DL-CNN assigned malignancy scores ranging from 0 to 1 (> 0.5 indicating malignancy). Dermatologists assessed lesions across three levels: (I) dermoscopy only, (II) full case information (dermoscopy, close-up images, metadata), and (III) full case information plus DL-CNN scores. Primary outcomes were sensitivity, specificity, and ROC-AUC of dermatologists with or without DL-CNN-support (level-II versus -III). - Results - The DL-CNN and dermatologists in level-II showed a comparable sensitivity (95% CI) of 90.0% (82.6-94.5%) and 90.1% (86.9-93.2%, p=0.153), respectively. However, the DL-CNN’s specificity (67.0% (57.3-75.4%) versus 73.2% (69.1-77.3%)) and ROC-AUC (0.889 (0.845-0.932) versus 0.951 (0.920-0.982)) were significantly lower than for dermatologists (all p<0.01). When dermatologists integrated DL-CNN predictions (level-III) their sensitivity increased to 91.4% (88.3-94.5%, p<0.001) without markedly changing specificity (74.2% (70.6-77.7%, p=0.435)) or ROC-AUC (0.954 (0.927-0.982, p=0.581)). - Conclusion - Collaboration with a DL-CNN slightly improved dermatologists’ diagnostic accuracy in a mixed CM and MelSim dataset, by increasing sensitivity without a loss of specificity. The DL-CNN’s level of sensitivity in this difficult-to-diagnose dataset underlines the potential as an assistant diagnostic tool. |
|---|---|
| Beschreibung: | Gesehen am 22.01.2026 |
| Beschreibung: | Online Resource |
| ISSN: | 1879-0852 |
| DOI: | 10.1016/j.ejca.2025.115706 |