Perceptual motion scoring: An algorithm for automated detection and grading of MRI motion artifacts
Rafael Brada1, Michael Rotman1, Sangtae Ahn2, and Christopher J. Hardy2
1GE Reserach, Herzliya, Israel, 2GE Research, Niskayuna, NY, United States
Using the k-space data of two coil array elements a
motion-artifact severity score that matches human perception can be calculated.
The motion score was tested on nine T1-FLAIR FSE brain series against human
observers’ score, obtaining an R2 value of 0.91.
Figure 4. a) Correlation
between the calculated motion score and the user score for the development set.
b) Correlation between the calculated motion score and the user score for the
test set, with an R2 value of 0.91
Figure 5. Sample images taken from each of the nine series in
the test set. U = The user assigned
score. A = The algorithm assigned score