Table 4 Performance comparison between SegFormer and DeepLabV3 on the TA test dataset.

From: Development of an artificial intelligence powered software for automated analysis of skeletal muscle ultrasonography

Backbone architecture

Decoder architecture

TA CSA ICC*

TA mT ICC*

TA EI ICC*

TA CSA adjusted R2

TA mT adjusted R2

TA EI adjusted R2

ResNet-50

DeepLabV3

0.96 (0.94–0.97)

0.96 (0.95–0.98)

0.99 (0.98–0.995)

0.85

0.87

0.96

MIT-B2

SegFormer

0.93 (0.89–0.95)

0.95 (0.93–0.97)

0.99 (0.98–0.99)

0.75

0.83

0.95

  1. TA = tibialis anterior. CSA = anatomical cross-sectional area. mT = muscle thickness. EI = echo intensity. ICC = intraclass correlation coefficient.
  2. *Two-way random effect model for consistency.
Back to article page