Table 2 Model performance. Precision, recall and F1 scores are standard validation metrics for classification, which are here computed as one class versus all. SP = Standard plane, NSP = non-standard plane.

From: Clinical validation of explainable AI for fetal growth scans through multi-level, cross-institutional prospective end-user evaluation

 

Precision

Recall

F1 score

Femur SP

0.92

0.97

0.95

Transabdominal SP

0.73

0.87

0.79

Transthalamic SP

0.57

0.96

0.72

Femur NSP

0.97

0.91

0.94

Transabdominal NSP

0.95

0.90

0.92

Transthalamic NSP

0.99

0.88

0.93

Other

1

1

1