Table 1 Overview of the characteristics of all included studies
From: Are deep models in radiomics performing better than generic models? A systematic review
- If multiple outcomes were analysed in a study, only the outcome with the highest area under the curve was reported. Note that Li (2020), Astaraki (2021), Caballo (2021), Chen + Lin (2021), Li (2021), Lin (2021), and Xuan (2021) used data from external sites; however, the data were merged and randomly split before modeling. Therefore, the results were considered to be internally validated, not externally.
yes,
no, 3D-BED Three-dimensional biologically effective dose, COVID-19 Coronavirus disease 2019, CV Cross-validation, CT Computed tomography, DBT Digital breast tomosynthesis, LOO-CV Leave-on-out-cross-validation, MRI Magnetic resonance imaging, PET Positron emission tomography
yes,
no, 3D-BED Three-dimensional biologically effective dose, COVID-19 Coronavirus disease 2019, CV Cross-validation, CT Computed tomography, DBT Digital breast tomosynthesis, LOO-CV Leave-on-out-cross-validation, MRI Magnetic resonance imaging, PET Positron emission tomography