Advertisement

Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types

  • Yupeng Zhang
  • Baorui Zhang
  • Fei Liang
  • Shikai Liang
  • Yuxiang Zhang
  • Peng Yan
  • Chao Ma
  • Aihua Liu
  • Feng Guo
  • Chuhan Jiang
Emergency Radiology
  • 77 Downloads

Abstract

Objective

To investigate the classification ability of quantitative radiomics features extracted on non-contrast-enhanced CT (NECT) image for discrimination of AVM-related hematomas from those caused by other etiologies.

Methods

Two hundred sixty-one cases with intraparenchymal hematomas underwent baseline CT scan between 2012 and 2017 in our center. Cases were split into a training dataset (n = 180) and a test dataset (n = 81). Hematoma types were dichotomized into two classes, namely, AVM-related hematomas (AVM-H) and hematomas caused by other etiologies. A total of 576 radiomics features of 6 feature groups were extracted from NECT. We applied 11 feature selection methods to select informative features from each feature group. Selected radiomics features and the clinical feature age were then used to fit machine learning classifiers. In combination of the 11 feature selection methods and 8 classifiers, we constructed 88 predictive models. Predictive models were evaluated and the optimal one was selected and evaluated.

Results

The selected radiomics model was RELF_Ada, which was trained with Adaboost classifier and features selected by Relief method. Cross-validated area under the curve (AUC) on training dataset was 0.988 and the relative standard deviation (RSD%) was 0.062. AUC on the test dataset was 0.957. Accuracy (ACC), sensitivity, specificity, positive prediction value (PPV), and negative predictive value (NPV) were 0.926, 0.889, 0.937, 0.800, and 0.967, respectively.

Conclusions

Machine learning models with radiomics features extracted from NECT scan accurately discriminated AVM-related intraparenchymal hematomas from those caused by other etiologies. This technique provided a fast, non-invasive approach without use of contrast to diagnose this disease.

Key Points

• Radiomics features from non-contrast-enhanced CT accurately discriminated AVM-related hematomas from those caused by other etiologies.

• AVM-related hematomas tended to be larger in diameter, coarser in texture, and more heterogeneous in composition.

• Adaboost classifier is an efficient approach for analyzing radiomics features.

Keywords

Cerebrum Hematoma Radiomics Machine learning Cerebral arteriovenous malformations 

Abbreviations

AVM-H

AVM-related hematomas

CAA-H

Cerebral amyloid angiopathy-related hematomas

CTA

CT angiography

DSA

Digital subtraction angiography

HP-H

Hypertension-related hematomas

MRA

Magnetic resonance angiography

NECT

Non-contrast-enhanced CT

rIAs

Rupture of intracranial aneurysms

Notes

Acknowledgements

We thank Erkang Guo, Xin Feng, Wenhua Fan, Luyao Wang, and Fei Peng for data collection. We also thank Dr. Peng Jiang, Yuhua Jiang, and Huijian Ge for the diagnosis of the hematoma types.

Funding

This study has received funding by the National Natural Science Foundation of China (Grant No. 81371314) and the High-level Personnel Training Program of Beijing Health system (Grant No. 2013-2-016).

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Chuhan Jiang.

Conflict of interest

The authors declare that they have no conflict of interest.

Statistics and biometry

One of the authors has significant statistical expertise.

Informed consent

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

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

References

  1. 1.
    Heit JJ, Iv M, Wintermark M (2017) Imaging of intracranial hemorrhage. J Stroke 19:11–27CrossRefGoogle Scholar
  2. 2.
    Balami JS, Buchan AM (2012) Complications of intracerebral haemorrhage. Lancet Neurol 11:101–118CrossRefGoogle Scholar
  3. 3.
    Nemoto M, Masuda H, Sakaeyama Y et al (2018) Clinical characteristics of subarachnoid hemorrhage with an intracerebral hematoma and prognostic factors. J Stroke Cerebrovasc Dis 27:1160–1166CrossRefGoogle Scholar
  4. 4.
    Fukuda K, Majumdar M, Masoud H et al (2017) Multicenter assessment of morbidity associated with cerebral arteriovenous malformation hemorrhages. J Neurointerv Surg 9:664–668CrossRefGoogle Scholar
  5. 5.
    Li Q, Gao X, Yao Z et al (2017) Permeability surface of deep middle cerebral artery territory on computed tomographic perfusion predicts hemorrhagic transformation after stroke. Stroke 48:2412–2418CrossRefGoogle Scholar
  6. 6.
    Roh D, Sun CH, Schmidt JM et al (2018) Primary intracerebral hemorrhage: a closer look at hypertension and cerebral amyloid angiopathy. Neurocrit Care.  https://doi.org/10.1007/s12028-018-0514-z CrossRefGoogle Scholar
  7. 7.
    Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006CrossRefGoogle Scholar
  8. 8.
    Sun H, Chen Y, Huang Q et al (2018) Psychoradiologic utility of MR imaging for diagnosis of attention deficit hyperactivity disorder: a radiomics analysis. Radiology 287:620–630CrossRefGoogle Scholar
  9. 9.
    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577CrossRefGoogle Scholar
  10. 10.
    Chen CH, Chang CK, Tu CY et al (2018) Radiomic features analysis in computed tomography images of lung nodule classification. PLoS One 13:e0192002CrossRefGoogle Scholar
  11. 11.
    Yang L, Dong D, Fang M et al (2018) Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer? Eur Radiol 28:2058–2067CrossRefGoogle Scholar
  12. 12.
    Suh HB, Choi YS, Bae S et al (2018) Primary central nervous system lymphoma and atypical glioblastoma: differentiation using radiomics approach. Eur Radiol  https://doi.org/10.1007/s00330-018-5368-4 CrossRefGoogle Scholar
  13. 13.
    van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107CrossRefGoogle Scholar
  14. 14.
    Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27:1226–1238CrossRefGoogle Scholar
  15. 15.
    Saeys Y, Inza I, Larranaga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23:2507–2517CrossRefGoogle Scholar
  16. 16.
    Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJ (2015) Machine learning methods for quantitative radiomic biomarkers. Sci Rep 5:13087CrossRefGoogle Scholar
  17. 17.
    Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830Google Scholar
  18. 18.
    Martinez JL, Macdonald RL (2015) Surgical strategies for acutely ruptured arteriovenous malformations. Front Neurol Neurosci 37:166–181CrossRefGoogle Scholar
  19. 19.
    Barone DG, Marcus HJ, Guilfoyle MR et al (2017) Clinical experience and results of microsurgical resection of arterioveonous malformation in the presence of space-occupying intracerebral hematoma. Neurosurgery 81:75–86CrossRefGoogle Scholar
  20. 20.
    Heit JJ, Pastena GT, Nogueira RG et al (2016) Cerebral angiography for evaluation of patients with CT angiogram-negative subarachnoid hemorrhage: an 11-year experience. AJNR Am J Neuroradiol 37:297–304CrossRefGoogle Scholar
  21. 21.
    Hong JF, Song YF, Liu HB, Liu Z, Wang SS (2015) The clinical characteristics and treatment of cerebral microarteriovenous malformation presenting with intracerebral hemorrhage: a series of 13 cases. Biomed Res Int 2015:257153PubMedPubMedCentralGoogle Scholar
  22. 22.
    Ogilvy CS, Heros RC, Ojemann RG, New PF (1988) Angiographically occult arteriovenous malformations. J Neurosurg 69:350–355CrossRefGoogle Scholar
  23. 23.
    Ueyama K, Koyama S (2017) Basal ganglia arteriovenous malformation in an elderly patient presented with putaminal hemorrhage, diagnosed after hematoma evacuation by imaging: a case report. Brain Nerve 69:79–83PubMedGoogle Scholar
  24. 24.
    Wagle WA, Smith TW, Weiner M (1984) Intracerebral hemorrhage caused by cerebral amyloid angiopathy: radiographic-pathologic correlation. AJNR Am J Neuroradiol 5:171–176PubMedGoogle Scholar
  25. 25.
    Murthy SB, Merkler AE, Omran SS et al (2017) Outcomes after intracerebral hemorrhage from arteriovenous malformations. Neurology 88:1882–1888CrossRefGoogle Scholar
  26. 26.
    Kang D, Park JE, Kim YH 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  https://doi.org/10.1093/neuonc/noy021 CrossRefGoogle Scholar
  27. 27.
    Li Y, Qian Z, Xu K et al (2018) MRI features predict p53 status in lower-grade gliomas via a machine-learning approach. Neuroimage Clin 17:306–311CrossRefGoogle Scholar
  28. 28.
    Li Y, Liu X, Qian Z et al (2018) Genotype prediction of ATRX mutation in lower-grade gliomas using an MRI radiomics signature. Eur Radiol  https://doi.org/10.1007/s00330-017-5267-0 CrossRefGoogle Scholar
  29. 29.
    Prasanna P, Patel J, Partovi S, Madabhushi A, Tiwari P (2017) Radiomic features from the peritumoral brain parenchyma on treatment-naive multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: preliminary findings. Eur Radiol 27:4188–4197CrossRefGoogle Scholar
  30. 30.
    Zhu X, Dong D, Chen Z et al (2018) Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur Radiol  https://doi.org/10.1007/s00330-017-5221-1 CrossRefGoogle Scholar
  31. 31.
    Shi Z, Zhu C, Degnan AJ et al (2018) Identification of high-risk plaque features in intracranial atherosclerosis: initial experience using a radiomic approach. Eur Radiol  https://doi.org/10.1007/s00330-018-5395-1 CrossRefGoogle Scholar
  32. 32.
    Shen Q, Shan Y, Hu Z et al (2018) Quantitative parameters of CT texture analysis as potential markers for early prediction of spontaneous intracranial hemorrhage enlargement. Eur Radiol  https://doi.org/10.1007/s00330-018-5364-8 CrossRefGoogle Scholar
  33. 33.
    Brouwers HB, Chang Y, Falcone GJ et al (2014) Predicting hematoma expansion after primary intracerebral hemorrhage. JAMA Neurol 71:158–164CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2018

Authors and Affiliations

  • Yupeng Zhang
    • 1
  • Baorui Zhang
    • 1
  • Fei Liang
    • 1
  • Shikai Liang
    • 2
  • Yuxiang Zhang
    • 1
  • Peng Yan
    • 1
  • Chao Ma
    • 1
  • Aihua Liu
    • 1
  • Feng Guo
    • 3
  • Chuhan Jiang
    • 1
  1. 1.Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan HospitalCapital Medical UniversityBeijingChina
  2. 2.Department of Neurosurgery, Beijing Tsinghua Changgung Hospital, School of Clinical MedicineTsinghua UniversityBeijingChina
  3. 3.Department of NeurosurgeryLinyi People’s HospitalLinyi CityChina

Personalised recommendations