From:  Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosis

 Model evaluation metrics

MetricDescription
AccuracyMeasures the proportion of correct predictions to the total predictions.
PrecisionProportion of true positive predictions out of all positive predictions.
Recall (sensitivity)Proportion of true positive predictions out of all actual positives.
F1-scoreHarmonic means of precision and recall are used to balance both metrics.