Skip to main content
SpringerLink
Log in

A radiomics approach for lung nodule detection in thoracic CT images based on the dynamic patterns of morphological variation

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

Abstract

Objectives

To propose and evaluate a set of radiomic features, called morphological dynamics features, for pulmonary nodule detection, which were rooted in the dynamic patterns of morphological variation and needless precise lesion segmentation.

Materials and methods

Two datasets were involved, namely, university hospital (UH) and LIDC datasets, comprising 72 CT scans (360 nodules) and 888 CT scans (2230 nodules), respectively. Each nodule was annotated by multiple radiologists. Denoted the category of nodules identified by at least k radiologists as ALk. A nodule detection algorithm, called CAD-MD algorithm, was proposed based on the morphological dynamics radiomic features, characterizing a lesion by ten sets of the same features with different values extracted from ten different thresholding results. Each nodule candidate was classified by a two-level classifier, including ten decision trees and a random forest, respectively. The CAD-MD algorithm was compared with a deep learning approach, the N-Net, using the UH dataset.

Results

On the AL1 and AL2 of the UH dataset, the AUC of the AFROC curves were 0.777 and 0.851 for the CAD-MD algorithm and 0.478 and 0.472 for the N-Net, respectively. The CAD-MD algorithm achieved the sensitivities of 84.4% and 91.4% with 2.98 and 3.69 FPs/scan and the N-Net 74.4% and 80.7% with 3.90 and 4.49 FPs/scan, respectively. On the LIDC dataset, the CAD-MD algorithm attained the sensitivities of 87.6%, 89.2%, 92.2%, and 95.0% with 4 FPs/scan for AL1-AL4, respectively.

Conclusion

The morphological dynamics radiomic features might serve as an effective set of radiomic features for lung nodule detection.

Key Points

• Texture features varied with such CT system settings as reconstruction kernels of CT images, CT scanner models, and parameter settings, and so on.

• Shape and first-order statistics were shown to be the most robust features against variation in CT imaging parameters.

• The morphological dynamics radiomic features, which mainly characterized the dynamic patterns of morphological variation, were shown to be effective for lung nodule detection.

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

AFROC:

Alternative free-response receiver operating characteristic curves

AFROC-AUC:

AUC of an AFROC curve

AL:

Agreement level

AUC:

Area under the curve

BN:

Branch number

CADe :

Computer-aided detection

CAD-MD :

The computer-aided detection algorithm based on morphological dynamics

CI:

Confidence interval

CT :

Computed tomography

ESM:

Erosion size map

FP :

False positive

HU:

Hounsfield unit

IDRI:

Image Database Resource Initiative

LIDC :

Lung Image Database Consortium

LUNA16:

Lung Nodule Analysis 2016

MHU:

Mean of Hounsfield unit

MS:

Morphological size

NC-ESM:

Erosion size map of nodule candidate

NC-VOI:

Volume of interest of nodule candidate

PFP:

The probability of detecting a false-positive in an image

SC:

Shape coefficient

SD:

Size difference

UH :

University hospital

VOI:

Volume of interest

References

  1. Zhang G, Jiang S, Yang Z et al (2018) Automatic nodule detection for lung cancer in CT images: a review. Comput Biol Med 103:287–300

    Article  PubMed  Google Scholar 

  2. Pehrson LM, Nielsen MB, Ammitzbøl Lauridsen C (2019) Automatic pulmonary nodule detection applying deep learning or machine learning algorithms to the LIDC-IDRI database: a systematic review. Diagnostics (Basel) 9(1). doi: https://doi.org/10.3390/diagnostics9010029

  3. Valente IR, Cortez PC, Neto EC et al (2016) Automatic 3D pulmonary nodule detection in CT images: a survey. Comput Methods Programs Biomed 124:91–107

    Article  PubMed  Google Scholar 

  4. Jacobs C, van Rikxoort EM, Twellmann T et al (2014) Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images. Med Image Anal 18:374–384

    Article  PubMed  Google Scholar 

  5. Shaukat F, Raja G, Gooya A et al (2017) Fully automatic detection of lung nodules in CT images using a hybrid feature set. Med Phys 44(7):3615–3629

    Article  PubMed  Google Scholar 

  6. Naqi SM, Sharif M, Yasmin M (2018) Multistage segmentation model and SVM-ensemble for precise lung nodule detection. Int J Comput Assist Radiol Surg 13:1083–1095

    Article  PubMed  Google Scholar 

  7. Shaukat F, Raja G, Ashraf R, Khalid S, Ahmad M, Ali A (2019) Artificial neural network based classification of lung nodules in CT images using intensity, shape and texture features. J Ambient Intell Humaniz Comput 10:4135–4149

    Article  Google Scholar 

  8. Naqi SM, Sharif M, Lali IU (2019) A 3D nodule candidate detection method supported by hybrid features to reduce false positives in lung nodule detection. Multimed Tools Appl 78:26287–26311

    Article  Google Scholar 

  9. Khan SA, Nazir M, Khan MA et al (2019) Lungs nodule detection framework from computed tomography images using support vector machine. Microsc Res Tech 82:1256–1266

    Article  PubMed  Google Scholar 

  10. Khan SA, Hussain S, Yang S et al (2019) Effective and reliable framework for lung nodules detection from CT scan images. Sci Rep 9:4989

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  11. Gu Y, Lu X, Zhang B et al (2019) Automatic lung nodule detection using multiscale dot nodule-enhancement filter and weighted support vector machines in chest computed tomography. PLoS One 14(1):e0210551

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Saba T (2019) Automated lung nodule detection and classification based on multiple classifiers voting. Microsc Res Tech 82:1601–1609

    Article  PubMed  Google Scholar 

  13. Huidrom R, Chanu YJ, Singh KM (2019) Pulmonary nodule detection on computed tomography using neuro-evolutionary scheme. Signal Image Video Process 13:53–60

    Article  Google Scholar 

  14. He L, Huang Y, Ma Z et al (2016) Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule. Sci Rep 6:34921

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Setio AA, Ciompi F, Litjens G et al (2016) Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans Med Imaging 35(5):1160–1169

    Article  PubMed  Google Scholar 

  16. Dou Q, Chen H, Yu L et al (2017) Multilevel contextual 3-d CNNs for false positive reduction in pulmonary nodule detection. IEEE Trans Biomed Eng 64(7):1558–1567

    Article  PubMed  Google Scholar 

  17. Zhang J, Xia Y, Zeng H et al (2018) NODULe: Combining constrained multi-scale LoG filters with densely dilated 3D deep convolutional neural network for pulmonary nodule detection. Neurocomputing 317:159–167

    Article  Google Scholar 

  18. Ali I, Gregory R. Hart GR, Gunabushanam G, et al (2018) Lung nodule detection via deep reinforcement learning. Front Oncol 8:Article 108

  19. Nasrullah N, Sang J, Alam MS et al (2019) Automated lung nodule detection and classification using deep learning combined with multiple strategies. Sensors (Basel) 19(17):3722. https://doi.org/10.3390/s19173722

    Article  Google Scholar 

  20. Xie H, Yang D, Sun N et al (2019) Automated pulmonary nodule detection in CT images using deep convolutional neural networks. Pattern Recognit 85:109–119

    Article  Google Scholar 

  21. Ardila D, Kiraly AP, Bharadwaj S et al (2019) End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med 25(6):954–961

    Article  CAS  PubMed  Google Scholar 

  22. Liao F, Liang M, Li Z et al (2019) Evaluate the malignancy of pulmonary nodules using the 3-D deep leaky noisy-OR network. IEEE Trans Neural Netw Learn Syst 30(11):3484–3495

    Article  PubMed  Google Scholar 

  23. Winkels M, Cohen TS (2019) Pulmonary nodule detection in CT scans with equivariant CNNs. Med Image Anal 55:15–26

    Article  PubMed  Google Scholar 

  24. Wang J, Wang J, Wen Y et al (2019) Pulmonary nodule detection in volumetric chest CT scans using CNNs-based nodule-size-adaptive detection and classification. IEEE Access 7:46033–46044

    Article  Google Scholar 

  25. Zheng S, Guo J, Cui X et al (2020) Automatic pulmonary nodule detection in CT scans using convolutional neural networks based on maximum intensity projection. IEEE Trans Med Imaging 39(3):797–805

    Article  PubMed  Google Scholar 

  26. Kim H, Park CM, Lee M et al (2016) Impact of reconstruction algorithms on CT radiomic features of pulmonary tumors: analysis of intra- and inter-reader variability and inter-reconstruction algorithm variability. PLoS One 11:e0164924

  27. Lo P, Young S, Kim HJ et al (2016) Variability in CT lung-nodule quantification: effects of dose reduction and reconstruction methods on density and texture based features. Med Phys 43:4854

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Shafiq-ul-Hassan M, Zhang GG, Hunt DC et al (2018) Accounting for reconstruction kernel-induced variability in CT radiomic features using noise power spectra. J Med Imaging (Bellingham) 5:011013

    Google Scholar 

  29. Mackin D, Fave X, Zhang L et al (2015) Measuring computed tomography scanner variability of radiomics features. Invest Radiol 50:757–765

    Article  PubMed  PubMed Central  Google Scholar 

  30. Zhao W, Zhang W, Sun Y et al (2019) Convolution kernel and iterative reconstruction affect the diagnostic performance of radiomics and deep learning in lung adenocarcinoma pathological subtypes. Thorac Cancer 10(10):1893–1903

    Article  PubMed  PubMed Central  Google Scholar 

  31. Geirhos R, Rubisch P, Michaelis C, et al (2018) ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231

  32. Baker N, Lu H, Erlikhman G et al (2018) Deep convolutional networks do not classify based on global object shape. PLoS Comput Biol 14(12):e1006613

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  33. Hermann KL, Kornblith S (2019) Exploring the origins and prevalence of texture bias in convolutional neural networks. arXiv preprint arXiv:1911.09071

  34. Mackin D, Ger R, Gay S et al (2019) Matching and homogenizing convolution kernels for quantitative studies in computed tomography. Invest Radiol 54:288–295

    Article  PubMed  PubMed Central  Google Scholar 

  35. Yang Y, Feng X, Chi W et al (2018) Deep learning aided decision support for pulmonary nodules diagnosing: a review. J Thorac Dis 10(Suppl 7):S867–S875

    Article  PubMed  PubMed Central  Google Scholar 

  36. Kim M, Yun J, Cho Y et al (2019) Deep learning in medical imaging. Neurospine 16(4):657–668

    Article  PubMed  PubMed Central  Google Scholar 

  37. Reiazi R, Abbas E, Famiyeh P et al (2021) The impact of the variation of imaging parameters on the robustness of computed tomography radiomic features: a review. Comput Biol Med 133:104400. https://doi.org/10.1016/j.compbiomed.2021.104400

    Article  PubMed  Google Scholar 

  38. Zhao B, Tan Y, Tsai WY et al (2016) Reproducibility of radiomics for deciphering tumor phenotype with imaging. Sci Rep 6:23428

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  39. Berenguer R, Pastor-Juan MDR, Canales-Vázquez J et al (2018) Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters. Radiology 288(2):407–415

    Article  PubMed  Google Scholar 

  40. Kim H, Park CM, Lee M et al (2016) Impact of reconstruction algorithms on CT radiomic features of pulmonary tumors: analysis of intra- and inter-reader variability and inter-reconstruction algorithm variability. PLoS One 11:e0164924

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  41. Lu L, Ehmke RC, Schwartz LH et al (2016) Assessing agreement between radiomic features computed for multiple CT imaging settings. PLoS One 11:e0166550

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  42. Mackin D, Ger R, Dodge C et al (2018) Effect of tube current on computed tomography radiomic features. Sci Rep 8:2354

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  43. Zhao YR, Ooijen, Dorrius PMAMD van et al (2014) Comparison of three software systems for semi-automatic volumetry of pulmonary nodules on baseline and follow-up CT examinations. Acta Radiol 55(6):691–698

    Article  PubMed  Google Scholar 

  44. Kalpathy-Cramer J, Zhao B, Goldgof D et al (2016) A comparison of lung nodule segmentation algorithms: methods and results from a multi-institutional study. J Digit Imaging 29:476–487

    Article  PubMed  PubMed Central  Google Scholar 

  45. Balagurunathan Y, Beers A, Kalpathy-Cramer J et al (2018) Semi-automated pulmonary nodule interval segmentation using the NLST data. Med Phys 45(3):1093–1107

    Article  PubMed  Google Scholar 

  46. Brochu F. (2019) Increasing shape bias in ImageNet-trained networks using transfer learning and domain-adversarial methods. arXiv preprint arXiv:1907.12892

  47. Armato SG III, McLennan G, Bidaut L et al (2011) The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med Phys 38(2):915–931

    Article  PubMed  PubMed Central  Google Scholar 

  48. Opfer R, Wiemker R (2007) Performance analysis for computer-aided lung nodule detection on LIDC data. Proc. SPIE 6515, Medical imaging 2007: image perception, observer performance, and technology assessment, 65151C

  49. Setio AAA, Traverso A, de Bel T et al (2017) Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge. Med Image Anal 42:1–13

    Article  PubMed  Google Scholar 

  50. Reeves AP, Biancardi AM (2011) The Lung Image Database Consortium (LIDC) nodule size report. Release: 2011–10–27–2. http://www.via.cornell.edu/lidc/

  51. Armato SG III, Giger ML, MacMahon H (2001) Automated detection of lung nodules in CT scans: preliminary results. Med Phys 28(8):1552–1561

    Article  PubMed  Google Scholar 

  52. PH Chen CL, KL Lor, YC Chang, CM Chen (2014) Pulmonary lobe segmentation of 3D thoracic CT images: adaptive rolling ball and vector-based surface deformation. Quantitative CT Imaging of the Lung, Society of Thoracic Radiology. San Antonio, Texas, USA.

  53. Frangi AF, Niessen WJ, Vincken KL, et al (1998) Multiscale vessel enhancement filtering. International Conference on Medical Image Computing and Computer-Assisted Intervention: Springer, pp.130–137

  54. Breiman L (2001) Random Forests. Mach Learn 45:5–32

    Article  Google Scholar 

  55. Golosio B, Masala GL, Piccioli A et al (2009) A novel multithreshold method for nodule detection in lung CT. Med Phys 36(8):3607–3618

    Article  PubMed  Google Scholar 

  56. Riccardi A, Petkov TS, Ferri G, Masotti M, Campanini R (2011) Computer-aided detection of lung nodules via 3D fast radial transform, scale space representation, and Zernike MIP classification. Medi Phys 38(4):1962–1971

    Article  Google Scholar 

  57. Tan M, Deklerck R, Jansen B, Bister M, Cornelis J (2011) A novel computer-aided lung nodule detection system for CT images. Med Phys 38(10):5630–5645

    Article  PubMed  Google Scholar 

  58. Tan M, Deklerck R, Cornelis J et al (2013) Phased searching with NEAT in a time-scaled framework: experiments on a computer-aided detection system for lung nodules. Artif Intell Med 59(3):157–167

    Article  PubMed  Google Scholar 

  59. Chakraborty DP (1989) Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data. Med Phys 16(4):561–567

    Article  CAS  PubMed  Google Scholar 

  60. Chakraborty DP (2013) A brief history of FROC paradigm data analysis. Acad Radiol 20(7):915–919

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Funding

This work was supported by the Ministry of Science and Technology, Taiwan, under the grant number MOST107-2221-E-002–074-MY3.

Author information

Author notes

  1. Fan-Ya Lin and Yeun-Chung Chang contributed equally to this file.

Authors and Affiliations

  1. Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, No. 1, Sec. 1, Jen-Ai Road, Taipei, 100, Taiwan

    Fan-Ya Lin, Chia-Chen Li, Yi-Chang Chen & Chung-Ming Chen

  2. Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan

    Yeun-Chung Chang

  3. Department of Medical Imaging, Cardinal Tien Hospital, New Taipei City, Taiwan

    Yi-Chang Chen

  4. IOIP Taiwan CO., Ltd, Taipei, Taiwan

    Hsuan-Yu Huang

Authors
  1. Fan-Ya Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yeun-Chung Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hsuan-Yu Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chia-Chen Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yi-Chang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chung-Ming Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chung-Ming Chen.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Chung-Ming Chen, Department of Biomedical Engineering, National Taiwan University.

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 waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• observational

• 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

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 31 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lin, FY., Chang, YC., Huang, HY. et al. A radiomics approach for lung nodule detection in thoracic CT images based on the dynamic patterns of morphological variation. Eur Radiol 32, 3767–3777 (2022). https://doi.org/10.1007/s00330-021-08456-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-021-08456-x

Keywords

Search

Navigation