Ground truth

Radiopaedia • CC-by-nc-sa 3.0 • de

Ground truth is a term used in statistics and machine learning to refer to data assumed to be correct. In the case of data for machine learning algorithms in radiology, ground truth for image labeling has often been acquired from pathology or lab results. In some cases labels created by radiological diagnoses can be used as ground truth. In the computing informatics literature the term ground truth can be sometimes used to imply any data presumed to be correctly labeled, and thus it is possible to create synthetic ground truth .