Skip to main content

Table 3 Characteristics of the patients and lesions

From: The efficacy of deep learning models in the diagnosis of endometrial cancer using MRI: a comparison with radiologists

 

Training data

Test data

Cancer

Non-cancer

All

Cancer

Non-cancer

All

Patients (n)

204

184

388

51

46

97

 Age

 Mean (y ± SD)

58 ± 11.50

46 ± 12.00

52 ± 13.00

60 ± 13.74

44 ± 12.53

53 ± 15.44

 Range (y)

28–83

22–81

22–83

30–91

21–71

21–91

Pathological type (n)

 Benign (n)

  Benign ovarian tumor

 

93

  

16

 

  Leiomyoma

 

71

  

24

 

  Endometrial hyperplasia

 

25

  

6

 

  Nabothian cyst

 

17

  

3

 

  Other

 

40

  

7

 

 Malignant (n)

  EC grade 1

118

  

30

  

  EC grade 2

51

  

11

  

  EC grade 3

20

  

9

  

  Other ECs

15

  

1

  

  Stage I

130

  

37

  

  Stage II

23

  

4

  

  Stage III

33

  

5

  

  Stage IV

18

  

5

  

Images (n)

 Axial (T2WI, ADC map, CE-T1WI)

1,471

1,434

2,905

51

46

97

 Sagittal (T2WI, CE-T1WI)

619

480

1,099

51

46

97

  1. SD, standard deviation; EC, Endometrioid carcinoma; T2WI, T2 weighted image; ADC, Apparent Diffusion Coefficient; CE-T1WI, contrast-enhanced T1 weighted image
Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us