Table 1 The demographic variables and imaging protocols of the recruited seven centers including internal cohorts from Hong Kong, and external cohorts from Mainland China and Germany.

From: Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study

Cohorts

Internal-

Set-1

Internal-

Set-2

Internal-

Set-3

External-

Set-1

External-

Set-2

External-

Set-3

External-

Set-4

Demographic variables

Number

7

65

3

10

35

10

2

Female

5

25

2

4

13

7

0

Male

2

40

1

6

22

3

2

Age (years)

32.7 (15–59)

47.7 (12–80)

67.0 (51–91)

47.1 (32–64)

60.9 (27–88)

54.5 (16–70)

60.0 (57–63)

Imaging protocols

Axial resolution (mm)

0.64 (0.63–0.7)

0.64 (0.51–0.78)

0.69 (0.66–0.75)

0.72 (0.68–0.81)

0.73 (0.57–0.91)

0.71 (0.64–0.78)

0.73 (0.66–0.79)

Slice thickness (mm)

0.625

1.25

0.7

1.0 (7 cases) 1.5 (3 cases)

3.0

0.625 (4 cases)

1.0 (5 cases)

1.25 (1 case)

1.25

Manufactor

GE Medical Systems; Milwaukee, WI, USA

GE Medical Systems; Milwaukee, WI, USA

SIEMENS

Healthineers; Forchheim, Germany

n/a

Philips Healthcare, Cleveland, OH, USA

TOSHIBA, Canon Medical Systems, Tochigi, Japan/Anke High-tech Co., Ltd., Shenzhen, China

GE Medical Systems; Milwaukee, WI, United States

Manufacturer’s Model

LightSpeed VCT

LightSpeed Pro 32

SOMATOM Definition AS+

n/a

iCT 256

Aquilion/ANATOM 64 Precision

Optima CT680 Series

Tube voltage (kvp)

120

120

120

n/a

120

120

120

Tube current (mA)

120–200

50–502

229–399

n/a

30–347

180–350

209–401

Patient position

Feet

First-Supine

Feet

First-Supine

Feet

First-Supine

n/a

Head First-Supine

Head First

-Supine

Head First-Supine

Intravenous contrast

Non-contrast

Non-contrast

Non-contrast

Non-contrast

Non-contrast

Non-contrast

Non-contrast

Inspiration

Inspiratory

Inspiratory

Inspiratory

Inspiratory

Inspiratory

Inspiratory

Inspiratory

  1. The numbers (including age, axial resolution) are presented as average (range). In imaging protocol, the slice thickness is presented as a specific number (number of cases), and the tube current is presented in range. The n/a stands for that the protocol parameters are missing from the anonymized public cohort.