Skip to main content

Table 4 Performance of proposed system and other algorithms on CBIS-DDSM dataset

From: A YOLO-based AI system for classifying calcifications on spot magnification mammograms

Methods (single view)

AUC

Sen %

Spec %

Acc %

PPV %

Proposed AI system

0.847

68.2

86.8

79.5

77.2

YOLOv4-baseline

0.76

66.8

75.1

71.8

63.7

AlexNet

0.711

53.5

75.1

66.6

58.5

VGG-16

0.713

58.9

75.6

69.0

61.3

CSPDarknet53

0.660

41.1

82.7

66.3

60.9

CSPDarknet53 + AMDF

0.759

51.2

85.8

72.1

70.2

  1. AUC, areas under the receiver operating characteristics curve; Sen, sensitivity; Spec, specificity; Acc, accuracy; PPV, positive predictive value; YOLOv4, You Only Look Once version 4