Skip to main content

Table 2 Pulmonary nodule detection. The datasets, assessment measures, and detection results are provided in each column, respectively

From: Computer-aided detection in chest radiography based on artificial intelligence: a survey

Study

Datasets

Assessment measures

Results

Wei et al. [70]

JSRT

AUC

85%

Schiham et al. [67]

JSRT

Average sensitivity under FP/image

2 FP/image: 51%; 4 FP/image: 67%

Shiraishi et al. [71]

Custom (924)

Average sensitivity under FP/image

5.05 FP/image: 70.1%;

Chen et al. [65]

JSRT

Custom (48)

Average sensitivity under FP/image

5 FP/image: JSRT, 78.6%; Custom, 83.3%

2 FP/image: JSRT, 71.4%; Custom, 77.1%

Hardie et al. [72]

Custom (167)

JSRT

Average sensitivity under FP/image

4 FP/image: sensitivity 78.1%

Ogul et al. [73]

JSRT

Custom (300)

Average sensitivity under FP/image

JSRT: 6.4 FP/image, 80%

Custom: 6.7 FP/image, 76%

Bush. [76]

JSRT

Sensitivity and specificity

Sensitivity: 92%; specificity: 86%

Wang et al. [77]

JSRT

Average sensitivity and specificity under FP/image

1.19 FP/image: sensitivity 69.27%; specificity 96.02%;

  1. FP/image means specific false positives per image. AUC denotes area under the receiver operating characteristic curve