Table 1 R2 score and mean absolute error performance across model architectures.

From: Attention-guided deep learning for gestational age prediction using fetal brain MRI

  1. R2 scores and corresponding MAE (days) are shown for each model architecture. ResNet-50 was used as the backbone. The Basic Network analyzes the entire image as input without attention masking. For each column, the best performance based on R2 score and mean absolute error is colored in blue. The highest performing architecture across all tested permutations is in red.
Back to article page