Research Article

Evaluation of a Nonrigid Motion Compensation Technique Based on Spatiotemporal Features for Small Lesion Detection in Breast MRI

Table 2

Areas under the ROC curves for contour features using FLDA. The rows represent the motion compensation as given in Table 1. Numbers in boldface show the best results.

Feature typeArea under the ROC curve (%)
010203040506070809

Radius min.70.285.1 79.072.963.980.366.874.471.2
Radius max.83.4 76.381.784.084.280.780.079.683.4
Radius mean83.2 80.083.083.479.881.176.782.684.2
Radius st. dev.82.470.476.180.380.776.979.275.076.9
Radius entropy83.076.779.684.074.879.675.080.780.9

Azimuth entropy80.781.977.779.677.581.979.078.479.6
Compactness69.577.1 73.775.667.968.968.771.465.8