. 2020 Jul 22;11:3673. doi: 10.1038/s41467-020-17478-w

Table 2.

Types of sample selection.

Type	Causation	Examples of selection processes	Resulting bias
Random	None	Uniform random sampling	None
Image	X → S	Visual phenotype selection (e.g. anatomical traits, lesions)	Population shift
		Image quality control (QC; e.g. noise, low contrast, artefacts)	Acquisition shift
Target	Y → S	Hospital admission, filtering by disease, annotation QC, learning strategies (e.g. class balancing, patch selection)	Prevalence shift
Joint	X → S ← Y	Combination of the above (e.g. curated benchmark dataset)	Selection bias³⁰