Review Article

Current Status and Future Perspectives of Artificial Intelligence in Magnetic Resonance Breast Imaging

Table 3

Detection of breast lesions in breast MRI using DL.

DL techniqueEvaluation resultsDatasetReferences

Model agnostic saliencyTPR = 80
FPs/image = 8
117 subjects
DCE-MRI and T1W images
[86]
U-netAcc = 94.267 MR images T1W, T2W, DWI, and DCE-MRI[87]
Patch-based analysis with ResNet50 backboneAUC = 0.817335 MR images of 17 different histological subtypes[65]
Deep Q-networkSn = 80
FPs/image = 3.2
117 DCE-MR and T1-weighted images[63]
Unsupervised saliency analysis and CNNAcc = 86 ± 2
AUC = 0.94 ± 0.01
193 DCE-MR images[88]
Two-level U-net and dual-stream CNNCPM = 64.29Training: 201 DCE-MR images
Testing: 160 DCE-MR images
[64]