Skip to main content

Advertisement

SpringerLink
Log in

A new scheme of global feature management improved the performance and stability of radiomics model: a study based on CT images of acute brainstem infarction

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

Abstract

Objective

The performance and stability of radiomics model caused by dimension reduction remain being confronted with major challenges. In this study, we aimed to propose a new scheme of global feature management independent of dimension reduction to improve it.

Methods

The non-contrast computed tomography (NCCT) images of acute brainstem infarction (ABI) from two medical centers were used as test and validation sets. A new scheme was constructed based on global feature management, and the traditional scheme dependent on dimension reduction was used as control. The radiomic features of NCCT images were extracted in Matlab R2013a. The performance of prediction model was evaluated by the generalized linear model (GLM) and multivariate logistic regression. And, the stability of radiomics model was evaluated with the difference of area under curve (AUC) between the test and validation sets.

Results

Compared with the traditional scheme, the new scheme presented a similar detection performance (AUC: 0.875 vs. 0.883), yet a better performance in predicting prognosis (AUC: 0.864, OR = 0.917, p = 0.021 vs. AUC:0.806, OR = 0.972, p = 0.007). All these results were well verified in an independent validation set. Moreover, the new scheme showed stronger stability in both the detection model (ΔAUC: 0.013 vs. 0.039) and prediction model (ΔAUC = 0.004 vs. 0.044).

Conclusion

Although there might be several limitations, this study proved that the scheme of global feature management independent of dimension reduction could be a powerful supplement to the radiomics methodology.

Key Points

• The new scheme (S wavelet ) presented similar detection performances for ABI with the traditional scheme.

• A better predictive performance for END was found in the new scheme (S wavelet ) compared with the traditional scheme.

• Stronger model stability was found in both the detection and prediction models based on the new scheme.

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

ABI:

Acute brainstem infarction

CTP:

Computer tomography perfusion

END:

Early neurological deterioration

GLM:

Generalized linear model

HCs:

Healthy controls

MRI:

Magnetic resonance imaging

NCCT:

Non-contrast computed tomography

NIHSS:

National Institute of Health Stroke Scale

PCA:

Principal component analysis

RMC:

Regional Medical Consortium

ROI:

Regions of interest

References

  1. Lambin P, Leijenaar R, Deist T et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762

    Article  Google Scholar 

  2. Mayerhoefer M, Materka A, Langs G et al (2020) Introduction to radiomics. J Nucl Med: official publication, Society of Nuclear Medicine 61:488–495

    Article  CAS  Google Scholar 

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

    Article  Google Scholar 

  4. Kang D, Park J, Kim Y et al (2018) Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation. Neuro Oncol 20:1251–1261

    Article  Google Scholar 

  5. Huang Y, Liang C, He L et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34:2157–2164

  6. Xu L, Yang P, Liang W et al (2019) A radiomics approach based on support vector machine using MR images for preoperative lymph node status evaluation in intrahepatic cholangiocarcinoma. Theranostics 9:5374–5385

    Article  Google Scholar 

  7. Kontos D, Ikejimba L, Bakic P, Troxel A, Conant E, Maidment A (2011) Analysis of parenchymal texture with digital breast tomosynthesis: comparison with digital mammography and implications for cancer risk assessment. Radiology 261:80–91

    Article  Google Scholar 

  8. Rondina J, Hahn T, de Oliveira L et al (2014) SCoRS--a method based on stability for feature selection and mapping inneuroimaging [corrected]. IEEE Trans Med Imaging 33:85–98

    Article  Google Scholar 

  9. Parmar C, Grossmann P, Bussink J, Lambin P, Aerts H (2015) Machine learning methods for quantitative radiomic biomarkers. Sci Rep 5:13087

    Article  CAS  Google Scholar 

  10. Ayesha S, Hanif MK, Talib R (2020) Overview and comparative study of dimensionality reduction techniques for high dimensional data. Inf Fusion 59:44–58

    Article  Google Scholar 

  11. Berberich A, Schneider C, Reiff T, Gumbinger C, Ringleb P (2019) Dual antiplatelet therapy improves functional outcome in patients with progressive lacunar strokes. Stroke 50:1007–1009

    Article  Google Scholar 

  12. Aerts H, Velazquez E, Leijenaar R et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006

    Article  CAS  Google Scholar 

  13. Galili T (2015) dendextend: an R package for visualizing, adjusting and comparing trees of hierarchical clustering. Bioinformatics 31:3718–3720

    Article  CAS  Google Scholar 

  14. Meyer M, Ronald J, Vernuccio F et al (2019) Reproducibility of CT radiomic features within the same patient: influence of radiation dose and CT reconstruction settings. Radiology 293:583–591

    Article  Google Scholar 

  15. Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446

  16. Wei J, Jiang H, Gu D et al (2020) Radiomics in liver diseases: current progress and future opportunities. Liver Int 40:2050–2063

  17. Weiner M, Veitch D, Aisen P et al (2015) 2014 update of the Alzheimer's Disease Neuroimaging Initiative: a review of papers published since its inception. Alzheimers Dement 11:e1–e120

  18. Baessler B, Mannil M, Oebel S, Maintz D, Alkadhi H, Manka R (2018) Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images. Radiology 286:103–112

    Article  Google Scholar 

  19. Fain S (2019) Machine learning reveals the texture of regional lung ventilation at CT. Radiology 293:685–686

    Article  Google Scholar 

  20. Truhn D, Schrading S, Haarburger C, Schneider H, Merhof D, Kuhl C (2019) Radiomic versus convolutional neural networks analysis for classification of contrast-enhancing lesions at multiparametric breast MRI. Radiology 290:290–297

    Article  Google Scholar 

  21. Lin Y, Zhang L, Bao J et al (2014) Risk factors and etiological subtype analysis of brainstem infarctions. J Neurol Sci 338:118–121

    Article  Google Scholar 

  22. Schellinger P, Fiebach J, Hacke W (2003) Imaging-based decision making in thrombolytic therapy for ischemic stroke: present status. Stroke 34:575–583

    Article  Google Scholar 

  23. Kazmierczak P, Dührsen M, Forbrig R et al (2020) Ultrafast brain magnetic resonance imaging in acute neurological emergencies: diagnostic accuracy and impact on patient management. Invest Radiol 55:181–189

    Article  Google Scholar 

  24. Runge V, Richter J, Heverhagen J (2017) Speed in clinical magnetic resonance. Invest Radiol 52:1–17

    Article  Google Scholar 

  25. Gomolka R, Chrzan R, Urbanik A, Nowinski W (2016) A quantitative method using head noncontrast CT scans to detect hyperacute nonvisible ischemic changes in patients with stroke. J Neuroimaging 26:581–587

  26. Srivatsan A, Christensen S, Lansberg M (2019) A relative noncontrast CT map to detect early ischemic changes in acute stroke. J Neuroimaging 29:182–186

Download references

Acknowledgements

The authors disclosed receipt of the following financial support for the research, authorship, and publication of this article.

Funding

This work was supported by National Natural Science Foundation of China (81871343); Jiangsu Provincial Key Research and Development Plan (BE2021693).

Author information

Author notes

  1. Yuefeng Li and Yuhang Xie contributed equally to this work.

Authors and Affiliations

  1. Department of Radiology, Affiliated Hospital of Jiangsu University, Zhenjiang, China

    Yuefeng Li

  2. Department of Psychiatry, Zhenjiang Mental Health Center, Zhenjiang, China

    Yuefeng Li & Guohai Li

  3. Neuroimaging Laboratory, Medical College of Jiangsu University, Zhenjiang, China

    Yuhang Xie, Yuhao Xu & Ningning Zhang

  4. Department of Radiology, Zhongda Affiliated Hospital of Southeast University, Nanjing, China

    Shenghong Ju

Authors
  1. Yuefeng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuhang Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuhao Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ningning Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Guohai Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shenghong Ju
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Guohai Li or Shenghong Ju.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Shenghong Ju.

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 subjects (patients) in this study.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• prospective

• predictive study

• performed at multi-institutions (multi-center data)

Additional information

Publisher’s note

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

Supplementary Information

ESM 1

(DOCX 1556 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, Y., Xie, Y., Xu, Y. et al. A new scheme of global feature management improved the performance and stability of radiomics model: a study based on CT images of acute brainstem infarction. Eur Radiol 32, 5508–5516 (2022). https://doi.org/10.1007/s00330-022-08659-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-08659-w

Keywords

Search

Navigation