Table 1 Performance of gauze EBL regression networks with three feature extraction backbones.

From: Automated deep learning model for estimating intraoperative blood loss using gauze images

 

Linear activation

ReLU activation

MAE

MSE

MAE

MSE

MAPE performance of the gauze EBL regression networks (%)

 EfficientNet-B5

8.6

9.5

11.2

13.2

 VGG16

10.5

11.1

12.3

13.2

 GoogLeNet

13.4

13.2

14.5

16.3

  1. EBL, Estimated blood loss; MAPE, Mean absolute percentage error; MAE, Mean absolute error; MSE, Mean squared error; ReLU, Rectified linear unit.
  2. Significant values are in bold.
Back to article page