Skip to main content

Table 1 Results for deep learning radiomics models and radiologist in accuracy to detect lymph node metastasis

From: Artificial intelligence for pre-operative lymph node staging in colorectal cancer: a systematic review and meta-analysis

First author

TP

FP

TN

FN

PPV, %

NPV, %

Sensitivity, %

Specificity, %

Accuracy, %

AUROC

95%CI

Standard Error c

Deep learning

 Per-patient

  Ding [12]

–

–

–

–

–

–

–

–

–

0.920

0.876–0.964

0.0224

  Wang [11]

40

4

58

5

90.9

92.1

88.9

93.5

91.6

0.912 c

0.842–0.958

0.0296

  Glaser [25] a

–

–

–

–

–

–

–

–

–

0.860

–

–

 Per-node

  Lu [28]

–

–

–

–

–

–

–

–

–

0.912

–

–

  Li [29]

–

–

–

–

–

–

–

–

94.4

–

–

–

Radiomics

 Per-patient

  Eresen [20]

29 c

6 c

33 c

10 c

82.8 c

76.7 c

74.36

84.62

79.49

0.825

0.778–0.872

0.0240

  Li [21]

69 c

44 c

128 c

67 c

61.06

65.64

50.74

74.42

63.96

0.650

0.583–0.713

0.0331

  Yang [22]

13 c

5 c

21 c

2 c

73.2 c

90.5 c

85.0

82.0

83.0

0.780

0.630–0.920

0.0740

  Nakanishi [23]

–

–

–

–

–

–

–

–

–

0.900

0.800–0.990

0.0485

  Zhou [24]

24 c

27 c

74 c

5 c

47.1

93.7

82.8

73.3

75.4

0.818

0.731–0.905

0.0444

  Meng [26]

46 c

36 c

47 c

17 c

56.1 c

73.4 c

73.0

56.6

63.7

0.697

0.612–0.781

0.0431

  Chen [30]

–

–

–

–

–

–

–

–

–

0.857

0.726–0.989

0.0671

  Huang [31]

–

–

–

–

–

–

–

–

–

0.788

0.779–0.797

0.0046

 Per-node

  Zhu [27]

18 c

21 c

32 c

1 c

46.2

97.0

94.7

60.4

69.4 c

0.812

0.703–0.895

0.0490

  Cai [32]

–

–

–

–

–

–

89

82

88

–

–

–

  Tse [34]

–

–

–

–

–

–

–

–

91.0

–

–

–

  Cui [33]

111 c

17 c

78 c

14 c

86.7 c

85.0 c

89

82

88

0.855 c

0.801–0.898 c

0.0247

Radiologist

 Per-patient

  Li [21] d

94 c

63 c

109 c

42 c

59.9

72.2

69.1

63.4

65.9

0.708

0.645–0.765

0.0306

  Eresen [20]

33 c

23 c

16 c

6 c

58.9 c

72.7 c

84.6

41.0

62.8

0.772

0.718–0.825

0.0273

  Yang [22]

41

41

43

14

50.0

75.4

74.6

51.2

60.4

0.629 c

0.543–0.709 c

0.0423

  Nakanishi [23] b

71

0

147

29

100.0

83.5

71.0

100.0

88.3 c

0.855 c

0.805–0.896 c

0.0232

  Zhou [24] b

49

89

215

38

35.5

85.0

56.3

70.7

67.5

0.635

0.585–0.683

0.0250

  Meng [26] b

88 c

96 c

124 c

37 c

47.8 c

77.0 c

55.9

70.4

61.3

0.632 c

0.578–0.683 c

0.0268

  Chen [30]

–

–

–

–

–

–

–

–

–

0.671

0.511–0.831

0.0816

  Huang [31]

58 c

30 c

69 c

43 c

65.9 c

61.6 c

57.4 c

69.7 c

63.5 c

0.636 c

0.565–0.702 c

0.0349

 Per-node

  Cui [33]

39 c

101 c

52 c

36 c

27.7 c

59.1 c

52 c

34 c

39.9 c

0.430 c

0.365–0.497 c

0.0337

  1. a Values extracted from training set
  2. b Values extracted from total cohort
  3. c Manually derived/reconstructed values using formulas from Additional file 1: Table S2
  4. d Values extracted from clinical models
  5. FN, false negative; FP, false positive; TN, true negative and TP, true positive; PPV, positive predictive value; NPV, negative predictive value; AUROC, area under the receiver operating characteristic; CI, confidence interval
Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us