Breast cancer histology images classification: Training from scratch or transfer learning?
We demonstrated the ability of transfer learning in comparison with the fully-trained network on the histopathological imaging modality by considering three pre-trained networks: VGG16, VGG19, and ResNet50 and analyzed their behavior for magnification independent breast cancer classification. Concur...
Gespeichert in:
| Veröffentlicht in: | ICT express Jg. 4; H. 4; S. 247 - 254 |
|---|---|
| Hauptverfasser: | , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier
01.12.2018
한국통신학회 |
| Schlagworte: | |
| ISSN: | 2405-9595, 2405-9595 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Zusammenfassung: | We demonstrated the ability of transfer learning in comparison with the fully-trained network on the histopathological imaging modality by considering three pre-trained networks: VGG16, VGG19, and ResNet50 and analyzed their behavior for magnification independent breast cancer classification. Concurrently, we examined the effect of training–testing data size on the performance of considered networks. A fine-tuned pre-trained VGG16 with logistic regression classifier yielded the best performance with 92.60% accuracy, 95.65% area under ROC curve (AUC), and 95.95% accuracy precision score (APS) for 90%–10% training–testing data splitting. Layer-wise fine-tuning and different weight initialization schemes can be a future aspect of this study. Keywords: Breast cancer, Histopathological images, Convolutional neural network, Full training, Transfer learning |
|---|---|
| ISSN: | 2405-9595 2405-9595 |
| DOI: | 10.1016/j.icte.2018.10.007 |