Review Article

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

Table 1

Brief overview of common data-driven techniques used in breast MRI.

TechniqueAdvantagesDisadvantagesReferences

Supervised learning
Ensemble of decision treesDecision using branches
Variable significance and feature selection are included
Prone to overfitting[1214]
[15, 16]
Random forestHigh performance
Compared to decision trees
Prone to overfitting[14, 17, 18]
[19]
Support vector machinesTransforms nonlinear classification problem into linear one
High accuracy
Difficult computation in high-dimensional data space[20, 21]
[22, 23]
[24]
Neural networksWeights need to be adapted for training
Multiclass classification
No strategy to determine network structure[2527]
[28, 29]
[30, 31]
Deep learningState-of-the-art in image-derived featuresComputationally intensive
Hard to interpret
[32, 33]
[3436]
[3739]

Unsupervised learning
Clustering (k-means)Brief training durationNumber of clusters must be known in advance[40, 41]
Topological data analysisInterpretable data mapping
Discovery of variable relationships
Divided clusters due to mapping[28, 42, 43]