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 3,4.
- 1. Garry Choy, Omid Khalilzadeh, Mark Michalski, Synho Do, Anthony E. Samir, Oleg S. Pianykh, J. Raymond Geis, Pari V. Pandharipande, James A. Brink, Keith J. Dreyer. Current Applications and Future Impact of Machine Learning in Radiology. (2018) Radiology. 288 (2): 318-328. doi:10.1148/radiol.2018171820 - Pubmed
- 2. Martin J. Willemink, Wojciech A. Koszek, Cailin Hardell, Jie Wu, Dominik Fleischmann, Hugh Harvey, Les R. Folio, Ronald M. Summers, Daniel L. Rubin, Matthew P. Lungren. Preparing Medical Imaging Data for Machine Learning. (2020) Radiology. 295 (1): 4-15. doi:10.1148/radiol.2020192224 - Pubmed
- 3. Prastawa M, Bullitt E, Gerig G. Synthetic ground truth for validation of brain tumor MRI segmentation. (2005) Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 8 (Pt 1): 26-33. doi:10.1007/11566465_4 - Pubmed
- 4. Sevenster M, Buurman J, Liu P, Peters JF, Chang PJ. Natural Language Processing Techniques for Extracting and Categorizing Finding Measurements in Narrative Radiology Reports. (2015) Applied clinical informatics. 6 (3): 600-110. doi:10.4338/ACI-2014-11-RA-0110 - Pubmed