Prospective Performance Evaluation of the Deep Learning Reconstruction Method at 1.5T: A Multi-Anatomy and Multi-Reader Study
Hung Do1, Mo Kadbi1, Dawn Berkeley1, Brian Tymkiw1, and Erin Kelly1
1Canon Medical Systems USA, Inc., Tustin, CA, United States
In this randomized blinded multi-reader study, Deep Learning Reconstruction (DLR) was
shown to be well generalized to data prospectively acquired from 16 anatomies. Specifically, DLR was scored similar or statistically higher than the 3
conventional reconstruction methods compared.
Figure 5: Force-ranking summary. DLR’s average force-ranking score is
consistently higher than the other methods in all pairwise comparisons and in
all anatomy groups. DLR was rated statistically higher than the 3 counterparts
in 15/18 pairwise comparisons (p < 0.012) except the three instances annotated
by as NS (non-significance).
Figure 4: Average readers’ scores for 6 anatomy groups. DLR’s average
scores are consistently higher than those of the 3 other methods in 143/144 pairwise
comparisons (6 anatomy group x 8 criteria x 3 pairwise comparisons) except 1
instance, where DLR’s average score is smaller than that of GA53 by a margin less
than 1% (i.e. 4.63 for DLR vs. 4.67 for GA53). DLR is rated statistically
higher all other three methods (p < 0.017) in 134/144 pairwise
comparisons.