|
| DL technique | Evaluation results | Dataset | Reference |
|
| 3D CNN from scratch | AUC = 0.739 (2D)
AUC = 0.801 (3D) | 143 DCE-MR cases (M: 77, B: 66) | [35] |
| CNN (ResNet50) fine-tuned | AUC = 0.97–0.99 | Training: 33 patients with 153 lesions (M: 91, B: 62)
Testing: 74 patients with 74 lesions (M: 48, B: 26) | [90] |
| Cross-modal DL (mammography and MR), trained from scratch | Acc = 94
AUC = 0.98 | 123 DCE-MR + T1W 282 mammography images | [91] |
| Dense convolutional LSTM | Acc = 0.847
Precision = 78.2
Sn = 81.5 | 72 lesions (M: 27, B: 45) DCE-MRI and DWI-MRI | [92] |
| DenseNet | AUC = 0.811 | 576 lesions (M: 368, B: 149, FU: 59)
Ultrafast DCE-MRI, T2, and DWI | [93] |
| CNN (AlexNet) fine-tuned from ImageNet on the second postcontrast frame, LSTM model for final prediction | Acc = 76
AUC = 0.76 | 42 DCE-MR images, 67 lesions (M: 42, B: 25) 10-fold cross-validation | [59] |
| CNN (ResNet34) fine-tuned best three inputs out of 85 combinations | AUC = 0.88 (95% confidence interval: 0.86–0.89) | 447 patients, 1294 lesions (M: 787, B: 507) multiparametric DCE-MR + T2W
10-fold cross-validation | [94] |
| MIP + off-the-shelf CNN (VGG) + SVM | AUC = 0.88 ± 0.01 | 690 DCE-MR cases (M: 478, B: 212)
5-fold cross-validation | [32] |
| Multiscale 3D CNN (trained from scratch) inputs: five timepoints T1W DCE-MR and T2W | AUC = 0.89 ± 0.01 | 408 patients (M: 305, B: 103) multiparametric
DCE-MR
5-fold cross-validation | [95] |
| Off-the-shelf CNN (VGG) + SVM target: different molecular subtypes | AUC = 0.65 (pretrained)
AUC = 0.58 (from scratch) | 270 DCE-MR images (90 luminal A, 180 other 3 subtypes)
10-fold cross-validation | [96] |
| 3TP-CNN pretrained on ImageNet | Acc = 74
AUC = 0.81
F1 = 0.78 | 39 lesions (M: 36, B: 22)
DCE-MRI sequences
10-fold cross-validation | [97] |
| Three-channel (pre- and postcontrast) CNN (VGG) fine-tuned for classification | AUC = 0.88
(CNN + LSTM)
AUC = 0.84 (CNN-only) | 703 DCE-MR dataset (M: 482, B: 221)
80% training + validation, 20% testing | [58] |
| 3D ResNet trained from scratch with ad hoc embedding loss weakly supervised localization with feature correlation attention map | Acc = 85.5
AUC = 0.902 | 1715 subjects (M: 1137, B: 578)
Training: 1204 subjects
Testing: 346 subjects | [98] |
|
