A deep learning algorithm for automated adrenal gland segmentation on non-contrast CT images

BMC Medical Imaging

Table 1 Comparison of patient demographics characteristics between groups

n		Training set and test set (n = 1200)	Independent test set (n = 81)	Inter-observer set (n = 20)	large-scale normal adrenal glands set (n = 2000)
Patient age^*		49.0 [40.0,58.0]	47.0 [35.0,58.0]	50.5 [42.0,55.8]	49.0 [40.0,58.0]
Patient sex^†	F	387 (32.25%)	27 (33.33%)	3 (15.00%)	672 (33.60%)
Patient sex^†	M	813 (67.75%)	54 (66.67%)	17 (85.00%)	1328 (66.40%)

^*Data are medians with interquartile ranges (IQRs) in brackets. Age values in the dataset were recorded as integers (e.g., 49.0 years), and decimals in the inter-observer set (e.g., 50.5) result from median calculation. ^† Data in parentheses are percentages

ISSN: 1471-2342