Skip to main content
European Radiology Experimental

Table 1 Datasets used to train semantic segmentation models

From: Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem

Abbreviation

Name

Number of volumes

Number of slices-L

Total number of slices

R-36

Routine

36

3,393

3,393

VISC-36

VISCERAL

36

3,393

3,393

LTRC-36

LTRC

36

3,393

3,393

LCTSC-36

LCTSC

36

3,393

3,393

R-231

Routine 231 cases

231

62,224

108,248

  1. The number of volumes, the number of slices that showed the lung (slices-L), and the total number of slices are listed. Visceral, LTRC, and LCTSC are public datasets; R-36 and R-231 are images from the routine database of a radiology department
Back to article page