Skip to main content

Advertisement

SpringerLink
Log in

Quantitative CT texture and shape analysis: Can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer?

  • Computed Tomography
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objective

To assess the accuracy of CT texture and shape analysis in the differentiation of benign and malignant mediastinal nodes in lung cancer.

Methods

Forty-three patients with biopsy-proven primary lung malignancy with pathological mediastinal nodal staging and unenhanced CT of the thorax were studied retrospectively. Grey-level co-occurrence and run-length matrix textural features, as well as morphological features, were extracted from 72 nodes. Differences between benign and malignant features were assessed using Mann-Whitney U tests. Receiver operating characteristic (ROC) curves for each were constructed and the area under the curve (AUC) calculated with histopathology diagnosis as outcome. Combinations of features were also entered as predictors in logistic regression models and optimal threshold criteria were used to estimate sensitivity and specificity.

Results

Using optimum-threshold criteria, the combined textural and shape features identified malignant mediastinal nodes with 81 % sensitivity and 80 % specificity (AUC = 0.87, P < 0.0001). Using this combination, 84 % malignant and 71 % benign nodes were correctly classified.

Conclusions

Quantitative CT texture and shape analysis has the potential to accurately differentiate malignant and benign mediastinal nodes in lung cancer.

Key Points

• Mediastinal nodal staging is crucial in the management of lung cancer

• Mediastinal nodal metastasis affects prognosis and suitability for surgical treatment

• Computed tomography (CT) is limited for mediastinal nodal staging

• Texture analysis measures tissue heterogeneity not perceptible to human vision

• CT texture analysis may accurately differentiate malignant and benign mediastinal nodes

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Abbreviations

CTDI:

Computed tomography dose index

VATS:

Video-assisted thoracoscopic surgery

GLNU:

Gray-level non-uniformity

RLNU:

Run-length non-uniformity

SVM:

Support vector machine

References

  1. McLoud TC, Bourgouin PM, Greenberg RW et al (1992) Bronchogenic carcinoma: analysis of staging in the mediastinum with CT by correlative lymph node mapping and sampling. Radiology 182:319–323

    Article  CAS  PubMed  Google Scholar 

  2. Webb WR, Gatsonis C, Zerhouni EA et al (1991) CT and MR imaging in staging non-small cell bronchogenic carcinoma: report of the Radiologic Diagnostic Oncology Group. Radiology 178:705–713

    Article  CAS  PubMed  Google Scholar 

  3. Gupta NC, Graeber GM, Bishop HA (2000) Comparative efficacy of positron emission tomography with fluorodeoxyglucose in evaluation of small (<1 cm), intermediate (1 to 3 cm), and large (>3 cm) lymph node lesions. Chest 117:773–778

    Article  CAS  PubMed  Google Scholar 

  4. Patz EF Jr, Lowe VJ, Goodman PC, Herndon J (1995) Thoracic nodal staging with PET imaging with 18FDG in patients with bronchogenic carcinoma. Chest 108:1617–1621

    Article  PubMed  Google Scholar 

  5. Kassner A, Thornhill RE (2010) Texture analysis: a review of neurologic MR imaging applications. AJNR Am J Neuroradiol 31:809–816

    Article  CAS  PubMed  Google Scholar 

  6. Tourassi GD (1999) Journey toward computer-aided diagnosis: role of image texture analysis. Radiology 213:317–320

    Article  CAS  PubMed  Google Scholar 

  7. Ganeshan B, Goh V, Mandeville HC, Ng QS, Hoskin PJ, Miles KA (2013) Non-small cell lung cancer: histopathologic correlates for texture parameters at CT. Radiology 266:326–336

    Article  PubMed  Google Scholar 

  8. Ganeshan B, Panayiotou E, Burnand K, Dizdarevic S, Miles K (2012) Tumour heterogeneity in non-small cell lung carcinoma assessed by CT texture analysis: a potential marker of survival. Eur Radiol 22:796–802

    Article  PubMed  Google Scholar 

  9. Miles KA, Ganeshan B, Griffiths MR, Young RC, Chatwin CR (2009) Colorectal cancer: texture analysis of portal phase hepatic CT images as a potential marker of survival. Radiology 250:444–452

    Article  PubMed  Google Scholar 

  10. Ng F, Ganeshan B, Kozarski R, Miles KA, Goh V (2013) Assessment of primary colorectal cancer heterogeneity by using whole-tumor texture analysis: contrast-enhanced CT texture as a biomarker of 5-year survival. Radiology 266:177–184

    Article  PubMed  Google Scholar 

  11. Ravanelli M, Farina D, Morassi M et al (2013) Texture analysis of advanced non-small cell lung cancer (NSCLC) on contrast-enhanced computed tomography: prediction of the response to the first-line chemotherapy. Eur Radiol 23:3450–3455

    Article  PubMed  Google Scholar 

  12. Collewet G, Strzelecki M, Mariette F (2004) Influence of MRI acquisition protocols and image intensity normalization methods on texture classification. Magn Reson Imaging 22:81–91

    Article  CAS  PubMed  Google Scholar 

  13. Mayerhoefer ME, Breitenseher MJ, Kramer J, Aigner N, Hofmann S, Materka A (2005) Texture analysis for tissue discrimination on T1-weighted MR images of the knee joint in a multicenter study: transferability of texture features and comparison of feature selection methods and classifiers. J Magn Reson Imaging 22:674–680

    Article  PubMed  Google Scholar 

  14. Galloway M (1975) Texture analysis using gray level run lenghts. Comp Graph Image Process 4:172–179

    Article  Google Scholar 

  15. Haralick RM, Shanmugan K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3:610–621

    Article  Google Scholar 

  16. Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143:29–36

    Article  CAS  PubMed  Google Scholar 

  17. Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27

    Article  Google Scholar 

  18. Witten IH, Frank E (2005) Data mining - practical machine learning tools and technique, 2nd edn. Elsevier, Burlington

    Google Scholar 

  19. Lunt SJ, Chaudary N, Hill RP (2009) The tumor microenvironment and metastatic disease. Clin Exp Metastasis 26:19–34

    Article  PubMed  Google Scholar 

  20. Davnall F, Yip CS, Ljungqvist G et al (2012) Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? Insights Imaging 3:573–589

    Article  PubMed Central  PubMed  Google Scholar 

  21. Spira D, Wecker M, Spira SM et al (2013) Does volume perfusion computed tomography enable differentiation of metastatic and non-metastatic mediastinal lymph nodes in lung cancer patients? A feasibility study. Cancer Imaging 13:323–331

    Article  PubMed Central  PubMed  Google Scholar 

  22. Thornhill RE, Shabana W, Kajal D (2012) Diameter-independent Computer-Aided Classification of Mesorectal Lymph Nodes in Rectal cancer: Preliminary Results - 20th Meeting International Society of Magnetic Resonance in Medicine, Melbourne, Australia, pp 3038

  23. Brown G, Richards CJ, Bourne MW et al (2003) Morphologic predictors of lymph node status in rectal cancer with use of high-spatial-resolution MR imaging with histopathologic comparison. Radiology 227:371–377

    Article  PubMed  Google Scholar 

  24. Nguyen P, Bashirzadeh F, Hundloe J et al (2012) Optical differentiation between malignant and benign lymphadenopathy by grey scale texture analysis of endobronchial ultrasound convex probe images. Chest 141:709–715

    Article  PubMed  Google Scholar 

  25. Fujiwara T, Yasufuku K, Nakajima T et al (2010) The utility of sonographic features during endobronchial ultrasound-guided transbronchial needle aspiration for lymph node staging in patients with lung cancer: a standard endobronchial ultrasound image classification system. Chest 138:641–647

    Article  PubMed  Google Scholar 

  26. Chen DR, Chang RF, Huang YL (1999) Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. Radiology 213:407–412

    Article  CAS  PubMed  Google Scholar 

  27. Chen SJ, Lin CH, Chang CY et al (2012) Characterizing the major sonographic textural difference between metastatic and common benign lymph nodes using support vector machine with histopathologic correlation. Clin Imaging 36:e352

    Google Scholar 

  28. Herlidou-Meme S, Constans JM, Carsin B et al (2003) MRI texture analysis on texture test objects, normal brain and intracranial tumors. Magn Reson Imaging 21:989–993

    Article  CAS  PubMed  Google Scholar 

  29. Sarunas JR, Anil JK (1991) Small sample size effects in statistical pattern recognition: recommendations for practioners. IEEE Trans Pattern Anal Mach Intell 13:252–264

    Article  Google Scholar 

Download references

Acknowledgements

The scientific guarantor of this publication is Carolina A. Souza. The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article. The authors state that this work has not received any funding. One of the authors has significant statistical expertise. Institutional Review Board approval was obtained. Written informed consent was waived by the Institutional Review Board. Methodology: retrospective, diagnostic or prognostic study, performed at one institution.

Author information

Authors and Affiliations

  1. Department of Medical Imaging, The Ottawa Hospital, University of Ottawa, The Ottawa Hospital Research Institute, 501 Smyth Road, Box 232, Ottawa, ON, Canada, K1H 8L6

    Hamid Bayanati, Rebecca E. Thornhill, Carolina A. Souza, Vineeta Sethi-Virmani, Ashish Gupta & Carole Dennie

  2. Department of Surgery – Division of Thoracic Surgery, The Ottawa Hospital, University of Ottawa, The Ottawa Hospital Research Institute, Ottawa, ON, Canada

    Donna Maziak

  3. Department of Respiratory Medicine, The Ottawa Hospital, University of Ottawa, The Ottawa Hospital Research Institute, Ottawa, ON, Canada

    Kayvan Amjadi

Authors
  1. Hamid Bayanati
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rebecca E. Thornhill
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Carolina A. Souza
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Vineeta Sethi-Virmani
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ashish Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Donna Maziak
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Kayvan Amjadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Carole Dennie
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Carolina A. Souza.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bayanati, H., E. Thornhill, R., Souza, C.A. et al. Quantitative CT texture and shape analysis: Can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer?. Eur Radiol 25, 480–487 (2015). https://doi.org/10.1007/s00330-014-3420-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-014-3420-6

Keywords

Search

Navigation