Skip to main content

Table 3 Performance metrics of the convolutional neural network (CNN) algorithm for the localization and segmentation of the median nerve in images without anatomical variants (i.e., bifid median nerve or prominent persistent median artery)

From: Development of a convolutional neural network for the identification and the measurement of the median nerve on ultrasound images acquired at carpal tunnel level

 

Prec

Rec

mAP

DSC

43 testing images

0.96 ± 0.18

0.98 ± 0.15

0.98 ± 0.15

0.88 ± 0.19

  1. Results are expressed as mean ± standard deviation
  2. DSC Dice similarity coefficient, mAP mean average precision, Prec precision, Rec recall