Skip to main content
SpringerLink
Log in

CT-based quantification of trachea shape to detect invasion by thyroid cancer

  • Head and Neck
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objective

This study aims to develop a CT-based method for quantifying tracheal shape and evaluating its ability to distinguish between cases with or without tracheal invasion in patients with thyroid carcinoma.

Methods

A total of 116 quantitative shape features, including 56 geometric moments and 60 bounding shape features, were defined. The tracheal lumen was semi-automatically defined with a CT threshold of less than − 500 HU. Three contiguous slices with the 1st, 2nd, and 3rd smallest trachea lumen areas were contiguously selected, and the appropriate number of slices to be included was determined. Fifty-six patients with differentiated thyroid carcinoma (DTC) invading the trachea and 22 patients with DTC but without invasion were retrospectively included. A receiver operating characteristic (ROC) curve was applied to select the representative shape features and determine the optimal threshold.

Results

23.3%, 25.9%, and 24.1% of the features displayed an area under the ROC curve (AUC) ≥ 0.800 when derived from 1, 2, and 3 slices, respectively. Calculating feature values from two slices with the 1st and 2nd smallest tracheal lumen area were considered appropriate. Six final features, including 3 geometric moments and 3 bounding shape features, were selected to determine the tracheal invasion status of DTC and displayed AUCs of 0.875–0.918, accuracies of 0.821–0.891, sensitivities of 0.813–0.893, and specificities of 0.818–0.932, outperforming the visual evaluation results.

Conclusions

Geometric moments and bounding shape features can quantify the tracheal shape and are reliable for identifying DTC tracheal invasion. The selected features quantified the extent of tracheal deformity in DTC patients with and without tracheal invasion.

Clinical relevance statement

Six geometric features provide a non-invasive, semi-automated evaluation of the tracheal invasion status of thyroid cancer.

Key Points

• A novel method for quantifying tracheal shape using 56 geometric moments and 60 bounding shape features was developed.

• Six features identify tracheal invasion by thyroid carcinoma.

• The selected features quantified the extent of tracheal deformity in differentiated thyroid carcinoma patients with and without tracheal invasion.

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
Fig. 4
Fig. 5

Similar content being viewed by others

Abbreviations

ATA:

American Thyroid Association

AUC:

Area under the receiver operating characteristics curve

CT:

Computed tomography

DTC:

Differentiated thyroid carcinoma

MRI:

Magnetic resonance imaging

PET:

Positron emission tomography

ROC:

Receiver operating characteristics

TNM:

Tumor, lymph node, metastasis staging system

References

  1. Ito Y, Fukushima M, Yabuta T et al (2009) Local prognosis of patients with papillary thyroid carcinoma who were intra-operatively diagnosed as having minimal invasion of the trachea: a 17-year experience in a single institute. Asian J Surg 32:102–108

    Article  PubMed  Google Scholar 

  2. Kim H, Jung HJ, Lee SY et al (2016) Prognostic factors of locally invasive well-differentiated thyroid carcinoma involving the trachea. Eur Arch Otorhinolaryngol 273:1919–1926

    Article  PubMed  Google Scholar 

  3. Avenia N, Vannucci J, Monacelli M et al (2016) Thyroid cancer invading the airway: diagnosis and management. Int J Surg 28(Suppl 1):S75–S78

    Article  PubMed  Google Scholar 

  4. Kanazawa Y, Takeuchi M, Tateya I, Omori K, Kawakami K (2017) Clinical epidemiology of tracheal invasion from thyroid cancer in Japanese population: Functional outcomes and effect of aging. Cancer Epidemiol 50:107–112

    Article  PubMed  Google Scholar 

  5. Perrier ND, Brierley JD, Tuttle RM (2018) Differentiated and anaplastic thyroid carcinoma: major changes in the American Joint Committee on Cancer eighth edition cancer staging manual. CA Cancer J Clin 68:55–63

    Article  PubMed  Google Scholar 

  6. Matsumoto F, Ikeda K (2021) Surgical management of tracheal invasion by well-differentiated thyroid cancer. Cancers (Basel):13

  7. Shimamoto K, Satake H, Sawaki A, Ishigaki T, Funahashi H, Imai T (1998) Preoperative staging of thyroid papillary carcinoma with ultrasonography. Eur J Radiol 29:4–10

    Article  CAS  PubMed  Google Scholar 

  8. Tomoda C, Uruno T, Takamura Y et al (2005) Ultrasonography as a method of screening for tracheal invasion by papillary thyroid cancer. Surg Today 35:819–822

    Article  PubMed  Google Scholar 

  9. Lee JY, Kim JH, Yeon EK et al (2022) Computed tomography complements ultrasound for the differential diagnosis of traumatic neuroma from recurrent tumor in patients with postoperative thyroid cancer. Eur Radiol 32:2760–2768

    Article  PubMed  Google Scholar 

  10. Chung SR, Baek JH, Choi YJ et al (2022) Risk factors for metastasis in indeterminate lymph nodes in preoperative patients with thyroid cancer. Eur Radiol 32:3863–3868

    Article  CAS  PubMed  Google Scholar 

  11. Lin Y, Lai S, Wang P et al (2022) Performance of current ultrasound-based malignancy risk stratification systems for thyroid nodules in patients with follicular neoplasms. Eur Radiol 32:3617–3630

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Seo YL, Yoon DY, Lim KJ et al (2010) Locally advanced thyroid cancer: can CT help in prediction of extrathyroidal invasion to adjacent structures? AJR Am J Roentgenol 195:W240–W244

    Article  PubMed  Google Scholar 

  13. Griscom NT (1982) Computed tomographic determination of tracheal dimensions in children and adolescents. Radiology 145:361–364

    Article  CAS  PubMed  Google Scholar 

  14. Griscom NT (1991) CT measurement of the tracheal lumen in children and adolescents. AJR Am J Roentgenol 156:371–372

    Article  CAS  PubMed  Google Scholar 

  15. De Wever W, Vandecaveye V, Lanciotti S, Verschakelen JA (2004) Multidetector CT-generated virtual bronchoscopy: an illustrated review of the potential clinical indications. Eur Respir J 23:776–782

    Article  PubMed  Google Scholar 

  16. Beigelman-Aubry C, Brillet PY, Grenier PA (2009) MDCT of the airways: technique and normal results. Radiol Clin N Am 47:185–201

    Article  PubMed  Google Scholar 

  17. Bradski G (2000) The OpenCV library. Dr Dobb’s J Softw Tools 25:120–125

    Google Scholar 

  18. Coelho LP (2013) Mahotas: open source software for scriptable computer vision. J Open Res Softw 1:e3

    Article  Google Scholar 

  19. Hu M (1962) Visual pattern recognition by moment invariants. IEEE Transac Inform Theory 8:179–187

    Article  Google Scholar 

  20. Khotanzad A, Hong YH (1990) Invariant image recognition by Zernike moments. IEEE Transac Patt Analy Machine Intel 12:489–497

    Article  Google Scholar 

  21. Kong Z, Jiang C, Liu D et al (2021) Quantitative features from CHO PET distinguish the WHO grades of primary diffuse glioma. Clin Nucl Med 46:103–110

    Article  PubMed  Google Scholar 

  22. Kong Z, Zhang Y, Liu D et al (2021) Role of traditional CHO PET parameters in distinguishing IDH, TERT and MGMT alterations in primary diffuse gliomas. Ann Nucl Med 35:493–503

    Article  CAS  PubMed  Google Scholar 

  23. Liu L, Klein SA, Xue F, Zhang JY, Yu C (2009) Using geometric moments to explain human letter recognition near the acuity limit. J Vis 9(26):21–18

    CAS  Google Scholar 

  24. Hickman MS (2011) Geometric moments and their invariants. J Math Imaging Vis 44:223–235

    Article  Google Scholar 

  25. Mo H, Hao H, Li H (2021) Geometric moment invariants to spatial transform and N-fold symmetric blur. Pattern Recogn 115:107887

    Article  Google Scholar 

  26. Singh C, Mittal N, Walia E (2011) Face recognition using Zernike and complex Zernike moment features. Patt Recognit Image Anal 21:71–81

    Article  Google Scholar 

  27. Ren Y, Yang J, Zhang Q, Guo Z (2021) Ship recognition based on Hu invariant moments and convolutional neural network for video surveillance. Multimed Tools Appl 80:1343–1373

    Article  Google Scholar 

  28. Chen S, Xia R, Zhao J, Chen Y, Hu M (2017) A hybrid method for ellipse detection in industrial images. Pattern Recogn 68:82–98

    Article  Google Scholar 

  29. Cupec R, Vidović I, Filko D, Đurović P (2020) Object recognition based on convex hull alignment. Pattern Recogn 102:107199

    Article  Google Scholar 

  30. Ha T, Kim W, Cha J et al (2022) Differentiating pulmonary metastasis from benign lung nodules in thyroid cancer patients using dual-energy CT parameters. Eur Radiol 32:1902–1911

    Article  CAS  PubMed  Google Scholar 

  31. Haugen BR, Alexander EK, Bible KC et al (2016) 2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer. Thyroid 26:1–133

    Article  PubMed  PubMed Central  Google Scholar 

  32. Takashima S, Takayama F, Wang Q et al (2000) Differentiated thyroid carcinomas. Prediction of tumor invasion with MR imaging. Acta Radiol 41:377–383

    Article  CAS  PubMed  Google Scholar 

  33. Wang JC, Takashima S, Takayama F et al (2001) Tracheal invasion by thyroid carcinoma: prediction using MR imaging. AJR Am J Roentgenol 177:929–936

    Article  CAS  PubMed  Google Scholar 

  34. Kong Z, Li Z, Chen J et al (2022) Metabolic characteristics of [(18)F]fluoroboronotyrosine (FBY) PET in malignant brain tumors. Nuclear Med Bio 106-107:80–87

    Article  CAS  Google Scholar 

  35. Kong Z, Li Z, Chen J et al (2022) Larger (18)F-fluoroboronotyrosine (FBY) active volume beyond MRI contrast enhancement in diffuse gliomas than in circumscribed brain tumors. EJNMMI Res 12:22

    Article  CAS  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

The authors thank the American Journal Experts for providing language help.

Funding

This study was supported by the National Natural Science Foundation of China (Grant No. 32301152), the Beijing Natural Science Foundation (Grant No. 7232351), the Special Research Fund for Central Universities, Peking Union Medical College (Grant No. 3332022024 and 2019XK320073), the CAMS Initiative for Innovative Medicine (Grant No. 2021-I2M-1-015), and the Beijing Hope Run Special Fund of Cancer Foundation of China (Grant No. LC2017L04).

Author information

Author notes

  1. Ziren Kong, Jian Wang, and Song Ni contributed equally to this work.

Authors and Affiliations

  1. Department of Head and Neck Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No.17 Panjiayuannanli, Chaoyang District, Beijing, China

    Ziren Kong, Jian Wang, Song Ni, Yang Liu, Yiming Zhu & Shaoyan Liu

  2. Department of Diagnostic Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 17, Panjiayuannanli, Chaoyang District, Beijing, China

    Xinming Zhao & Lin Li

Authors
  1. Ziren Kong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jian Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Song Ni
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xinming Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yiming Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Lin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Shaoyan Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yiming Zhu, Lin Li or Shaoyan Liu.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Shaoyan Liu.

Conflict of interest

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.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained from all patients in this study.

Ethical approval

Institutional review board (Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College) approval was obtained.

Study subjects or cohorts overlap

No study subjects or cohorts have been previously reported.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

ESM 1

(PDF 716 kb)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kong, Z., Wang, J., Ni, S. et al. CT-based quantification of trachea shape to detect invasion by thyroid cancer. Eur Radiol (2023). https://doi.org/10.1007/s00330-023-10301-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00330-023-10301-2

Keywords

Search

Navigation