Rofo 2022; 194(03): 296-305
DOI: 10.1055/a-1656-9834
Chest

Accuracy and Reproducibility of a Software Prototype for Semi-Automated Computer-Aided Volumetry of the solid and subsolid Components of part-solid Pulmonary Nodules

Genauigkeit und Reproduzierbarkeit eines Software-Prototypen zur halbautomatischen computergestützten Volumetrie der soliden und subsoliden Komponenten von teilsoliden Lungenrundherden
1   Radiology, University Hospitals Tübingen, Tübingen, Germany
,
Regina Gast
1   Radiology, University Hospitals Tübingen, Tübingen, Germany
,
Rainer Grimmer
2   Medical Imaging, Siemens Healthineers AG, Erlangen, Germany
,
Andreas Wimmer
3   Siemens Healthcare GmbH, Forchheim, Germany
,
Marius Horger
1   Radiology, University Hospitals Tübingen, Tübingen, Germany
› Author Affiliations

Abstract

Purpose To test the accuracy and reproducibility of a software prototype for semi-automated computer-aided volumetry (CAV) of part-solid pulmonary nodules (PSN) with separate segmentation of the solid part.

Materials and Methods 66 PSNs were retrospectively identified in 34 thin-slice unenhanced chest CTs of 19 patients. CAV was performed by two medical students. Manual volumetry (MV) was carried out by two radiology residents. The reference standard was determined by an experienced radiologist in consensus with one of the residents. Visual assessment of CAV accuracy was performed. Measurement variability between CAV/MV and the reference standard as a measure of accuracy, CAV inter- and intra-rater variability as well as CAV intrascan variability between two recontruction kernels was determined via the Bland-Altman method and intraclass correlation coefficients (ICC).

Results Subjectively assessed accuracy of CAV/MV was 77 %/79 %–80 % for the solid part and 67 %/73 %–76 % for the entire nodule. Measurement variability between CAV and the reference standard ranged from –151–117 % for the solid part and –106–54 % for the entire nodule. Interrater variability was –16–16 % for the solid part (ICC 0.998) and –102–65 % for the entire nodule (ICC 0.880). Intra-rater variability was –70–49 % for the solid part (ICC 0.992) and –111–31 % for the entire nodule (ICC 0.929). Intrascan variability between the smooth and the sharp reconstruction kernel was –45–39 % for the solid part and –21–46 % for the entire nodule.

Conclusion Although the software prototype delivered satisfactory results when segmentation is evaluated subjectively, quantitative statistical analysis revealed room for improvement especially regarding the segmentation accuracy of the solid part and the reproducibility of measurements of the nodule’s subsolid margins.

Key points:

  • Assessed visually CAV delivers similar accuracy compared to manual volumetry

  • Accuracy of CAV was higher for the entire nodule

  • Reproducibility was better for the solid part

  • Variability between the kernels was higher for the solid part

Zusammenfassung

Ziel Untersuchung der Genauigkeit und Reproduzierbarkeit eines Software-Prototypen zur semiautomatischen computergestützten Volumetrie (CAV) von teilsoliden Lungenrundherden (PSN) mit separater Segmentierung des soliden Anteils.

Material und Methoden 66 PSN wurden retrospektiv in 34 nativen Dünnschicht-Thorax-CTs von 19 Patienten identifiziert. Die CAV wurde von 2 Medizinstudenten durchgeführt, eine manuelle Volumetrie (MV) von 2 radiologischen Assistenzärzten. Der Referenzstandard wurde von einem erfahrenen Radiologen im Konsens mit einem der Assistenzärzte festgelegt. Die Genauigkeit der CAV wurde visuell beurteilt. Die Messvariabilität zwischen CAV/MV und dem Referenzstandard als Maß für die Genauigkeit, die Inter- und Intrarater-Variabilität der CAV sowie die Intrascan-Variabilität der CAV zwischen 2 Rekonstruktionskernels wurden mittels der Bland-Altman-Methode und dem Intraclass-Korrelationskoeffizienten (ICC) bestimmt.

Ergebnisse Die subjektiv bewertete Genauigkeit der CAV/MV lag bei 77 %/79 %–80 % für den soliden Anteil und bei 67 %/73 %–76 % für den gesamten Rundherd. Die Messvariabilität zwischen CAV und dem Referenzstandard reichte von –151–117 % für den soliden Anteil und –106–54 % für den gesamten Rundherd. Die Interrater-Variabilität betrug –16–16 % für den soliden Anteil (ICC 0,998) und –102–65 % für den gesamten Rundherd (ICC 0,880). Die Intrarater-Variabilität betrug –70–49 % für den soliden Anteil (ICC 0,992) und –111–31 % für den gesamten Rundherd (ICC 0,929). Die Intrarater-Variabilität zwischen dem weichen und scharfen Rekonstruktionskernel betrug –45–39 % für den soliden Anteil und –21–46 % für den gesamten Rundherd.

Schlussfolgerung Obwohl der Software-Prototyp bei der subjektiven Bewertung der Segmentierung zufriedenstellende Ergebnisse lieferte, zeigte die quantitative statistische Analyse Potenzial für Verbesserungen, insbesondere hinsichtlich der Segmentierungsgenauigkeit des soliden Teils und der Reproduzierbarkeit der Messung der subsoliden Ränder des Rundherdes.

Kernaussagen:

  • Visuell beurteilt liefert die CAV eine ähnliche Genauigkeit wie die manuelle Volumetrie.

  • Die Genauigkeit der CAV war für den gesamten Knoten höher.

  • Die Reproduzierbarkeit war für den soliden Anteil besser.

  • Die Variabilität zwischen den Rekonstruktionskernels war für den soliden Anteil höher.

Citation Format

  • Werner S, Gast R, Grimmer R et al. Genauigkeit und Reproduzierbarkeit eines Software-Prototypen zur halbautomatischen computergestützten Volumetrie der soliden und subsoliden Komponenten von teilsoliden Lungenrundherden. Fortschr Röntgenstr 2022; 194: 296 – 305



Publication History

Received: 15 May 2021

Accepted: 23 September 2021

Article published online:
21 October 2021

© 2021. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 
  • References

  • 1 Nakata M, Saeki H, Takata I. et al. Focal ground-glass opacity detected by low-dose helical CT. Chest 2002; 121: 1464-1467 DOI: 10.1378/chest.121.5.1464.
  • 2 Seidelman JL, Myers JL, Quint LE. Incidental, subsolid pulmonary nodules at CT: etiology and management. Cancer Imaging 2013; 13: 365-373
  • 3 Lee SM, Park CM, Goo JM. et al. Transient part-solid nodules detected at screening thin-section CT for lung cancer: comparison with persistent part-solid nodules. Radiology 2010; 255: 242-251
  • 4 Kim H, Park CM, Koh JM. et al. Pulmonary subsolid nodules: what radiologists need to know about the imaging features and management strategy. Diagn Interv Radiol 2014; 20: 47-57
  • 5 MacMahon H, Naidich DP, Goo JM. et al. Guidelines for Management of Incidental Pulmonary Nodules Detected on CT Images: From the Fleischner Society 2017. Radiology 2017; 284: 228-243
  • 6 Travis WD, Brambilla E, Noguchi M. et al. International association for the study of lung cancer/american thoracic society/european respiratory society international multidisciplinary classification of lung adenocarcinoma. J Thorac Oncol 2011; 6: 244-285
  • 7 American College of Radiology Committee on Lung-RADS® . Lung-RADS Assessment Categories version 1.1. . Available at (Accessed on September 2nd, 2021) https://www.acr.org/-/media/ACR/Files/RADS/Lung-RADS/LungRADSAssessmentCategoriesv1-1.pdf
  • 8 Travis WD, Asamura H, Bankier AA. et al. The IASLC Lung Cancer Staging Project: Proposals for Coding T Categories for Subsolid Nodules and Assessment of Tumor Size in Part-Solid Tumors in the Forthcoming Eighth Edition of the TNM Classification of Lung Cancer. J Thorac Oncol 2016; 11: 1204-1223
  • 9 van Klaveren RJ, Oudkerk M, Prokop M. et al. Management of lung nodules detected by volume CT scanning. N Engl J Med 2009; 361: 2221-2229
  • 10 Lee H, Um SW. Probability of lung cancer based on the size threshold and volume-doubling time for lung nodules detected in low-dose CT screening. Ann Transl Med 2015; 3: 21
  • 11 Horeweg N, van Rosmalen J, Heuvelmans MA. et al. Lung cancer probability in patients with CT-detected pulmonary nodules: a prespecified analysis of data from the NELSON trial of low-dose CT screening. Lancet Oncol 2014; 15: 1332-1341
  • 12 Heuvelmans MA, Walter JE, Vliegenthart R. et al. Disagreement of diameter and volume measurements for pulmonary nodule size estimation in CT lung cancer screening. Thorax 2018; 73: 779-781
  • 13 Devaraj A, van Ginneken B, Nair A. et al. Use of Volumetry for Lung Nodule Management: Theory and Practice. Radiology 2017; 284: 630-644
  • 14 Siegelman JW, Supanich MP, Gavrielides MA. Pulmonary nodules with ground-glass opacity can be reliably measured with low-dose techniques regardless of iterative reconstruction: results of a phantom study. Am J Roentgenol 2015; 204: 1242-1247
  • 15 Kim H, Park CM, Lee SM. et al. A comparison of two commercial volumetry software programs in the analysis of pulmonary ground-glass nodules: segmentation capability and measurement accuracy. Korean J Radiol 2013; 14: 683-691
  • 16 Doo KW, Kang EY, Yong HS. et al. Accuracy of lung nodule volumetry in low-dose CT with iterative reconstruction: an anthropomorphic thoracic phantom study. Br J Radiol 2014; 87: 20130644
  • 17 Xie X, Zhao Y, Snijder RA. et al. Sensitivity and accuracy of volumetry of pulmonary nodules on low-dose 16- and 64-row multi-detector CT: an anthropomorphic phantom study. Eur Radiol 2013; 23: 139-147
  • 18 Kim H, Park CM. Current perspectives for the size measurement of screening-detected lung nodules. J Thorac Dis 2018; 10: 1242-1244
  • 19 Moltz JH, Bornemann L, Kuhnigk J-M. et al. Advanced segmentation techniques for lung nodules, liver metastases, and enlarged lymph nodes in CT scans. IEEE Journal of selected topics in signal processing 2009; 3: 122-134
  • 20 Lassen B, Jacobs C, Kuhnigk J. et al. Robust semi-automatic segmentation of pulmonary subsolid nodules in chest computed tomography scans. Physics in Medicine & Biology 2015; 60: 1307
  • 21 Heckel F, Meine H, Moltz JH. et al. Segmentation-based partial volume correction for volume estimation of solid lesions in CT. IEEE Trans Med Imaging 2014; 33: 462-480
  • 22 Bland JM, Altman DG. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 1986; 1: 307-310
  • 23 Bland JM, Altman DG. Measuring agreement in method comparison studies. Stat Methods Med Res 1999; 8: 135-160
  • 24 Benzakoun J, Bommart S, Coste J. et al. Computer-aided diagnosis (CAD) of subsolid nodules: Evaluation of a commercial CAD system. Eur J Radiol 2016; 85: 1728-1734
  • 25 Charbonnier JP, Chung K, Scholten ET. et al. Automatic segmentation of the solid core and enclosed vessels in subsolid pulmonary nodules. Sci Rep 2018; 8: 646
  • 26 Kim H, Park CM, Woo S. et al. Pure and part-solid pulmonary ground-glass nodules: measurement variability of volume and mass in nodules with a solid portion less than or equal to 5 mm. Radiology 2013; 269: 585-593
  • 27 Park CM, Goo JM, Lee HJ. et al. Persistent pure ground-glass nodules in the lung: interscan variability of semiautomated volume and attenuation measurements. Am J Roentgenol 2010; 195: W408-W414
  • 28 Scholten ET, de Jong PA, Jacobs C. et al. Interscan variation of semi-automated volumetry of subsolid pulmonary nodules. Eur Radiol 2015; 25: 1040-1047
  • 29 Scholten ET, de Hoop B, Jacobs C. et al. Semi-automatic quantification of subsolid pulmonary nodules: comparison with manual measurements. PLoS One 2013; 8: e80249
  • 30 Kamiya S, Iwano S, Umakoshi H. et al. Computer-aided Volumetry of Part-Solid Lung Cancers by Using CT: Solid Component Size Predicts Prognosis. Radiology 2018; 287: 1030-1040