Software performance in segmenting ground-glass and solid components of subsolid nodules in pulmonary adenocarcinomas

Eur Radiol. 2016 Dec;26(12):4465-4474. doi: 10.1007/s00330-016-4317-3. Epub 2016 Apr 5.

Abstract

Objective: To evaluate the performance of software in segmenting ground-glass and solid components of subsolid nodules in pulmonary adenocarcinomas.

Method: Seventy-three pulmonary adenocarcinomas manifesting as subsolid nodules were included. Two radiologists measured the maximal axial diameter of the ground-glass components on lung windows and that of the solid components on lung and mediastinal windows. Nodules were segmented using software by applying five (-850 HU to -650 HU) and nine (-130 HU to -500 HU) attenuation thresholds. We compared the manual and software measurements of ground-glass and solid components with pathology measurements of tumour and invasive components.

Results: Segmentation of ground-glass components at a threshold of -750 HU yielded mean differences of +0.06 mm (p = 0.83, 95 % limits of agreement, 4.51 to 4.67) and -2.32 mm (p < 0.001, -8.27 to 3.63) when compared with pathology and manual measurements, respectively. For solid components, mean differences between the software (at -350 HU) and pathology measurements and between the manual (lung and mediastinal windows) and pathology measurements were -0.12 mm (p = 0.74, -5.73 to 5.55]), 0.15 mm (p = 0.73, -6.92 to 7.22), and -1.14 mm (p < 0.001, -7.93 to 5.64), respectively.

Conclusion: Software segmentation of ground-glass and solid components in subsolid nodules showed no significant difference with pathology.

Key points: • Software can effectively segment ground-glass and solid components in subsolid nodules. • Software measurements show no significant difference with pathology measurements. • Manual measurements are more accurate on lung windows than on mediastinal windows.

Keywords: Adenocarcinoma; Lung cancer; Segmentation; Solitary pulmonary nodule; Subsolid nodule.

MeSH terms

  • Adenocarcinoma / diagnostic imaging*
  • Adenocarcinoma of Lung
  • Adult
  • Aged
  • Female
  • Humans
  • Image Processing, Computer-Assisted / methods*
  • Lung / diagnostic imaging*
  • Lung Neoplasms / diagnostic imaging*
  • Male
  • Mediastinum / diagnostic imaging*
  • Middle Aged
  • Radiologists
  • Retrospective Studies
  • Software*
  • Solitary Pulmonary Nodule / diagnostic imaging*
  • Tomography, X-Ray Computed