Skip to main content

Table 1 Summary of the study cohort and image features

From: Identifying factors that may influence the classification performance of radiomics models using contrast-enhanced mammography (CEM) images

Characteristics Benign lesions
(n = 47)
Malignant lesions
(n = 114)
P value
Age (year) a 46.0 ± 7.9 50.7 ± 9.2 0.002
Lesion size (mm) a 17.1 ± 10.3 28.8 ± 15.6 <  0.001
Breast density    0.004
 a-b 4/47 (8.5) 33/114 (28.9)  
 c-d 43/47 (91.5) 81/114 (71.1)  
Degree of BPE    <  0.001
 Minimal or Mild 20/47 (42.6) 86/114 (75.4)  
 Moderate or Marked 27/47 (57.4) 28/114 (24.5)  
Rim Artifacts    1.000
 Absent 42/47 (89.3) 100/114 (87.7)  
 Present 5/47 (10.7) 14/114 (12.3)  
Ripple Artifacts    0.005
 Absent 36/47 (76.6) 60/114 (52.6)  
 Present 11/47 (23.4) 54/114 (47.4)  
Vascular Artifacts    0.042
 Absent 41/47 (87.2) 82/114 (71.9)  
 Present 6/47 (12.8) 32/114 (28.1)  
Air Trapping Artifacts    0.104
 Absent 43/47 (87.2) 92/114 (71.9)  
 Present 4/47 (12.8) 22/114 (28.1)  
SNRa 183.2 ± 134.0 359.7 ± 141.9 <  0.001
CNRa 194.5 ± 153.0 431.7 ± 193.1 <  0.001
BCRa 108.6 ± 84.4 230.2 ± 103.2 <  0.001
  1. BPE background parenchymal enhancement, SNR signal-to-noise ratio, CNR contrast-to-noise ratio, BCR background contrast ratio
  2. a Data are shown as the mean values ± standard deviations. Other data are shown as proportions with percentages in parentheses