Table 1 Dataset characteristics.

From: Limited generalizability of single deep neural network for surgical instrument segmentation in different surgical environments

 

Number of videos

Number of annotated images

Laparoscopic recording system

Recognition target surgical instruments

Type of surgery

Training set

85

4788

Olympus

T1, T2, T3

LCRR

Validation set

9

345

Test set 1

10

369

Test set 2

5

103

 

T1, T2, T3

LCRR

Sub test set 2.1

2

40

Stryker

  

Sub test set 2.2

3

63

Karl Storz

Test set 3

3

124

  

LCRR

Sub test set 3.1

1

31

Olympus

T4

 

Sub test set 3.2

1

74

T5

Sub test set 3.3

1

19

T6

Test set 4

16

223

 

T1, T2, T3

 

Sub test set 4.1

5

65

Olympus

 

LDG

Sub test set 4.2

5

81

 

LC

Sub test set 4.3

6

77

 

LPH

  1. T1 harmonic shears, T2 endoscopic surgical electrocautery, T3 Aesculap AdTec atraumatic universal forceps, T4 Maryland, T5 Croce-Olmi, T6 needle holder; LCRR laparoscopic colorectal resection, LDG laparoscopic distal gastrectomy, LC laparoscopic cholecystectomy, LPH laparoscopic partial hepatectomy.
Back to article page