Skip to main content

Advertisement

SpringerLink
Log in

Classification of pulmonary lesion based on multiparametric MRI: utility of radiomics and comparison of machine learning methods

  • Magnetic Resonance
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

We develop and validate a radiomics model based on multiparametric magnetic resonance imaging (MRI) in the classification of the pulmonary lesion and identify optimal machine learning methods.

Materials and methods

This retrospective analysis included 201 patients (143 malignancies, 58 benign lesions). Radiomics features were extracted from multiparametric MRI, including T2-weighted imaging (T2WI), T1-weighted imaging (TIWI), and apparent diffusion coefficient (ADC) map. Three feature selection methods, including recursive feature elimination (RFE), t test, and least absolute shrinkage and selection operator (LASSO), and three classification methods, including linear discriminate analysis (LDA), support vector machine (SVM), and random forest (RF) were used to distinguish benign and malignant pulmonary lesions. Performance was compared by AUC, sensitivity, accuracy, precision, and specificity. Analysis of performance differences in three randomly drawn cross-validation sets verified the stability of the results.

Results

For most single MR sequences or combinations of multiple MR sequences, RFE feature selection method with SVM classifier had the best performance, followed by RFE with RF. The radiomics model based on multiple sequences showed a higher diagnostic accuracy than single sequence for every machine learning method. Using RFE with SVM, the joint model of T1WI, T2WI, and ADC showed the highest performance with AUC = 0.88 ± 0.02 (sensitivity 83%; accuracy 82%; precision 91%; specificity 79%) in test set.

Conclusion

Quantitative radiomics features based on multiparametric MRI have good performance in differentiating lung malignancies and benign lesions. The machine learning method of RFE with SVM is superior to the combination of other feature selection and classifier methods.

Key Points

• Radiomics approach has the potential to distinguish between benign and malignant pulmonary lesions.

• Radiomics model based on multiparametric MRI has better performance than single-sequence models.

• The machine learning methods RFE with SVM perform best in the current cohort.

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
Fig. 6

Similar content being viewed by others

Abbreviations

ADC:

Apparent diffusion coefficient

AUC:

Area under curve

CI:

Confidence interval

CT:

Computed tomography

DWI:

Diffusion-weighted imaging

ICC:

Intra-class correlation coefficient

LASSO:

Least absolute shrinkage and selection operator

LDA:

Linear discriminate analysis

ML:

Machine learning

MRI:

Magnetic resonance imaging

NEX:

Number of excitations

NSA:

Number of signals averaged

RF:

Random forest

RFE:

Recursive feature elimination

ROC:

Receiver operating characteristic

SAVR:

Surface area to volume ratio

SPIR:

Spectral pre-saturation inversion recovery

SVM:

Support vector machine

T1WI:

T1-weighted imaging

T2WI:

T2-weighted imaging

VOI:

Volume of interest

References

  1. Siegel RL, Miller KD, Jemal A (2018) Cancer statistics, 2018. CA Cancer J Clin 68:7–30

    Article  Google Scholar 

  2. Wan Q, Deng YS, Lei Q et al (2019) Differentiating between malignant and benign solid solitary pulmonary lesions: are intravoxel incoherent motion and diffusion kurtosis imaging superior to conventional diffusion-weighted imaging? Eur Radiol 29:1607–1615

    Article  Google Scholar 

  3. Meier-Schroers M, Homsi R, Gieseke J, Schild HH, Thomas D (2019) Lung cancer screening with MRI: evaluation of MRI for lung cancer screening by comparison of LDCT- and MRI-derived lung-RADS categories in the first two screening rounds. Eur Radiol 29:898–905

    Article  Google Scholar 

  4. Brea TP, Ravina AR, Villamor JMC, Gomez AG, de Alegria AM, Valdes L (2019) Use of magnetic resonance imaging for N-staging in patients with non-small cell lung cancer. A systematic review. Arch Bronconeumol 55:9–16

    Article  Google Scholar 

  5. Guan HX, Pan YY, Wang YJ, Tang DZ, Zhou SC, Xia LM (2018) Comparison of various parameters of DWI in distinguishing solitary pulmonary nodules. Curr Med Sci 38:920–924

    Article  Google Scholar 

  6. Meier-Schroers M, Homsi R, Schild HH, Thomas D (2018) Lung cancer screening with MRI: characterization of nodules with different non-enhanced MRI sequences. Acta Radiol. https://doi.org/10.1177/0284185118778870:284185118778870

  7. Yuan M, Zhang YD, Zhu C et al (2016) Comparison of intravoxel incoherent motion diffusion-weighted MR imaging with dynamic contrast-enhanced MRI for differentiating lung cancer from benign solitary pulmonary lesions. J Magn Reson Imaging 43:669–679

    Article  Google Scholar 

  8. Le Bihan D, Iima M (2015) Diffusion magnetic resonance imaging: what water tells us about biological tissues. PLoS Biol 13:e1002203

    Article  Google Scholar 

  9. Shen G, Hu S, Deng H, Kuang A (2016) Performance of DWI in the nodal characterization and assessment of lung cancer: a meta-analysis. AJR Am J Roentgenol 206:283–290

    Article  Google Scholar 

  10. Shen G, Jia Z, Deng H (2016) Apparent diffusion coefficient values of diffusion-weighted imaging for distinguishing focal pulmonary lesions and characterizing the subtype of lung cancer: a meta-analysis. Eur Radiol 26:556–566

    Article  Google Scholar 

  11. Bi WL, Hosny A, Schabath MB et al (2019) Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin 69:127–157

    PubMed  PubMed Central  Google Scholar 

  12. van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107

    Article  Google Scholar 

  13. Kniep HC, Madesta F, Schneider T et al (2019) Radiomics of brain MRI: utility in prediction of metastatic tumor type. Radiology 290:479–487

    Article  Google Scholar 

  14. Lin M, Chen W, Zhao M et al (2018) Prostate lesion delineation from multiparametric magnetic resonance imaging based on locality alignment discriminant analysis. Med Phys 45:4607–4618

    Article  Google Scholar 

  15. Yang R, Wu J, Sun L et al (2019) Radiomics of small renal masses on multiphasic CT: accuracy of machine learning-based classification models for the differentiation of renal cell carcinoma and angiomyolipoma without visible fat. Eur Radiol. https://doi.org/10.1007/s00330-019-06384-5

  16. Yin P, Mao N, Zhao C et al (2019) Comparison of radiomics machine-learning classifiers and feature selection for differentiation of sacral chordoma and sacral giant cell tumour based on 3D computed tomography features. Eur Radiol 29:1841–1847

    Article  Google Scholar 

  17. Maniruzzaman M, Jahanur Rahman M, Ahammed B et al (2019) Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms. Comput Methods Programs Biomed 176:173–193

    Article  Google Scholar 

  18. Zhang Y, Cheng C, Liu Z et al (2019) Radiomics analysis for the differentiation of autoimmune pancreatitis and pancreatic ductal adenocarcinoma in (18) F-FDG PET/CT. Med Phys. https://doi.org/10.1002/mp.13733

  19. Zhang X, Yan LF, Hu YC et al (2017) Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features. Oncotarget 8:47816–47830

    Article  Google Scholar 

  20. Hamerla G, Meyer HJ, Schob S et al (2019) Comparison of machine learning classifiers for differentiation of grade 1 from higher gradings in meningioma: a multicenter radiomics study. Magn Reson Imaging. https://doi.org/10.1016/j.mri.2019.08.011

  21. Peng Y, Jiang Y, Antic T, Giger ML, Eggener SE, Oto A (2014) Validation of quantitative analysis of multiparametric prostate MR images for prostate cancer detection and aggressiveness assessment: a cross-imager study. Radiology 271:461–471

    Article  Google Scholar 

  22. Peng Y, Jiang Y, Yang C et al (2013) Quantitative analysis of multiparametric prostate MR images: differentiation between prostate cancer and normal tissue and correlation with Gleason score--a computer-aided diagnosis development study. Radiology 267:787–796

    Article  Google Scholar 

  23. Chatterjee S, Dey D, Munshi S (2019) Integration of morphological preprocessing and fractal based feature extraction with recursive feature elimination for skin lesion types classification. Comput Methods Programs Biomed 178:201–218

    Article  Google Scholar 

  24. Fan M, Liu Z, Xie S et al (2019) Integration of dynamic contrast-enhanced magnetic resonance imaging and T2-weighted imaging radiomic features by a canonical correlation analysis-based feature fusion method to predict histological grade in ductal breast carcinoma. Phys Med Biol. https://doi.org/10.1088/1361-6560/ab3fd3

  25. Liu Y, Shi H, Huang S et al (2019) Early prediction of acute xerostomia during radiation therapy for nasopharyngeal cancer based on delta radiomics from CT images. Quant Imaging Med Surg 9:1288–1302

    Article  Google Scholar 

  26. Shen TX, Liu L, Li WH et al (2019) CT imaging-based histogram features for prediction of EGFR mutation status of bone metastases in patients with primary lung adenocarcinoma. Cancer Imaging 19:34

    Article  Google Scholar 

  27. Sun Y, Hu P, Wang J et al (2018) Radiomic features of pretreatment MRI could identify T stage in patients with rectal cancer: preliminary findings. J Magn Reson Imaging. https://doi.org/10.1002/jmri.25969

  28. Wang H, Hu D, Yao H et al (2019) Radiomics analysis of multiparametric MRI for the preoperative evaluation of pathological grade in bladder cancer tumors. Eur Radiol. https://doi.org/10.1007/s00330-019-06222-8

  29. Garapati SS, Hadjiiski L, Cha KH et al (2017) Urinary bladder cancer staging in CT urography using machine learning. Med Phys 44:5814–5823

    Article  Google Scholar 

  30. Chen L, Pan X, Zhang YH et al (2019) Primary tumor site specificity is preserved in patient-derived tumor xenograft models. Front Genet 10:738

    Article  CAS  Google Scholar 

  31. Chen X, Zargari A, Hollingsworth AB, Liu H, Zheng B, Qiu Y (2019) Applying a new quantitative image analysis scheme based on global mammographic features to assist diagnosis of breast cancer. Comput Methods Programs Biomed 179:104995

    Article  Google Scholar 

  32. Geetha R, Sivasubramanian S, Kaliappan M, Vimal S, Annamalai S (2019) Cervical cancer identification with synthetic minority oversampling technique and PCA analysis using random forest classifier. J Med Syst 43:286

    Article  CAS  Google Scholar 

  33. Chen CH, Chang CK, Tu CY et al (2018) Radiomic features analysis in computed tomography images of lung nodule classification. PLoS One 13:e0192002

    Article  Google Scholar 

  34. Choi W, Oh JH, Riyahi S et al (2018) Radiomics analysis of pulmonary nodules in low-dose CT for early detection of lung cancer. Med Phys 45:1537–1549

    Article  Google Scholar 

  35. Wu W, Parmar C, Grossmann P et al (2016) Exploratory study to identify radiomics classifiers for lung cancer histology. Front Oncol 6:71

    PubMed  PubMed Central  Google Scholar 

  36. Mei D, Luo Y, Wang Y, Gong J (2018) CT texture analysis of lung adenocarcinoma: can radiomic features be surrogate biomarkers for EGFR mutation statuses. Cancer Imaging 18:52

    Article  Google Scholar 

  37. Coroller TP, Agrawal V, Narayan V et al (2016) Radiomic phenotype features predict pathological response in non-small cell lung cancer. Radiother Oncol 119:480–486

    Article  Google Scholar 

  38. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577

    Article  Google Scholar 

Download references

Funding

This study has received funding by National Natural Science Foundation of China (61571036, 61872030, and 81601457).

Author information

Author notes

  1. Xinhui Wang and Qi Wan contributed equally to this work.

Authors and Affiliations

  1. School of Electronic and Information Engineering, Beijing Jiaotong University, Shangyuan Village No 3 in Haidian, Beijing, China

    Xinhui Wang, Houjin Chen & Yanfeng Li

  2. Department of Radiology, The First Affiliated Hospital of Guangzhou Medical University, Yanjiangxilu No 151 in Yuexiu, Guangzhou, China

    Qi Wan & Xinchun Li

Authors
  1. Xinhui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qi Wan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Houjin Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yanfeng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xinchun Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Houjin Chen or Xinchun Li.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Houjin Chen.

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

• 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.

Electronic supplementary material

ESM 1

(DOC 106 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, X., Wan, Q., Chen, H. et al. Classification of pulmonary lesion based on multiparametric MRI: utility of radiomics and comparison of machine learning methods. Eur Radiol 30, 4595–4605 (2020). https://doi.org/10.1007/s00330-020-06768-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-020-06768-y

Keywords

Search

Navigation