Skip to main content

Table 3 Mean values and standard deviation for the subjective reading

From: Reconstruction of 3D knee MRI using deep learning and compressed sensing: a validation study on healthy volunteers

 

Standard

SENSE

CS 10/

CS-AI 10

CS 13/

CS-AI 13

CS 15/

CS-AI 15

CS 17/

CS-AI 17

Cartilage

Standard

4.93 ± 0.18

    

CS

 

4.08 ± 0.18 − /*

3.28 ± 0.38 */*

2.90 ± 0.38 */*

2.48 ± 0.41 */*

CS-AI

 

4.48 ± 0.20 − /*

3.93 ± 0.47 */*

3.53 ± 0.41 */*

3.03 ± 0.26 */*

ACL

Standard

4.90 ± 0.18

    

CS

 

3.50 ± 0.34 */*

3.00 ± 0.36 */*

2.20 ± 0.50 */*

1.80 ± 0.38 */*

CS-AI

 

4.10 ± 0.34 − /*

3.50 ± 0.50 */*

2.90 ± 0.35 */*

2.70 ± 0.37 */*

PCL

Standard

4.90 ± 0.29

    

CS

 

3.30 ± 0.37 */*

2.70 ± 0.44 */*

2.00 ± 0.49 */*

1.50 ± 0.43 */*

CS-AI

 

3.90 ± 0.34 − /*

3.30 ± 0.44 */*

2.80 ± 0.47 */*

2.40 ± 0.43 */*

Menisci

Standard

4.90 ± 0.33

    

CS

 

4.00 ± 0.30 − /*

3.20 ± 0.41 */*

2.90 ± 0.45 */*

2.40 ± 0.45 */*

CS-AI

 

4.40 ± 0.29 − /*

3.90 ± 0.35 */*

3.50 ± 0.34 */*

3.00 ± 0.30 */*

Bone

Standard

4.70 ± 0.41

    

CS

 

3.60 ± 0.46 − /*

2.80 ± 0.41 */*

2.10 ± 0.34 */*

1.80 ± 0.41 */*

CS-AI

 

4.20 ± 0.33 − /*

3.40 ± 0.34 */*

2.80 ± 0.30 */*

2.50 ± 0.30 */*

Artifacts

Standard

4.60 ± 0.50

    

CS

 

3.30 ± 0.34 − /*

2.60 ± 0.41 */*

2.00 ± 0.20 */*

1.80 ± 0.30 */*

CS-AI

 

3.80 ± 0.38 − /*

3.00 ± 0.46 */*

2.60 ± 0.39 */*

2.20 ± 0.44 */*

Overall image impression

Standard

4.90 ± 0.28

    

CS

 

3.50 ± 0.41 */*

2.90 ± 0.35 */*

2.30 ± 0.34 */*

1.90 ± 0.32 */*

CS-AI

 

4.10 ± 0.28 − /*

3.50 ± 0.38 */*

3.10 ± 0.35 */*

2.70 ± 0.24 */*

  1. ACL Anterior cruciate ligament, PCL Posterior cruciate ligament, CS Compressed sensing, CS-AI Compressed sensing combined with a deep learning-based algorithm
  2. */*denotes statistically significant differences (p ≤ 0.034) compared to the standard sequence (*before diagonal slash) or the corresponding reconstruction with the same acceleration level (CS versus CS-AI) (*after diagonal slash)