Suspicous Birads 45 No Suspicous Birads 123

Métriques

AUC

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
WCCNet DenseNet-121	0.947	WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification
RGP DenseNet-169	0.934	Deep Neural Networks With Region-Based Pooling Structures for Mammographic Image Classification
WCCNet ResNet-50	0.931	WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification
WCCNet ResNet-101	0.926	WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification
WCCNet ResNet-34	0.923	WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification
GGP DenseNet-169	0.922	Deep Neural Networks With Region-Based Pooling Structures for Mammographic Image Classification
WCCNet VGG16	0.915	WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification
WCCNet ResNet-18	0.913	WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification
AlexNet+Sparse MIL INbr. Auto.	0.89	Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
WCCNet AlexNet	0.870	WDCCNet: Weighted Double-Classifier Constraint Neural Network for Mammographic Image Classification
Avg pooling DenseNet-169	0.862	Deep Neural Networks With Region-Based Pooling Structures for Mammographic Image Classification
AlexNet+Label Assign. MIL INbr. Auto.	0.84	Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
Max pooling DenseNet-169	0.837	Deep Neural Networks With Region-Based Pooling Structures for Mammographic Image Classification
AlexNet+Max Pooling MIL	0.83	Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
AlexNet	0.79	Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
Pretrained CNN + Random Forest	0.76	Automated mass detection in mammograms using cascaded deep learning and random forests,

0 of 16 row(s) selected.

Suspicous Birads 45 No Suspicous Birads 123 | SOTA | HyperAI