Noncontrast computer tomography–based radiomics model for predicting intracerebral hemorrhage expansion: preliminary findings and comparison with conventional radiological model



To develop a radiomics model for predicting hematoma expansion in patients with intracerebral hemorrhage (ICH) and to compare its predictive performance with a conventional radiological feature-based model.


We retrospectively analyzed 251 consecutive patients with acute ICH. Two radiologists independently assessed baseline noncontrast computed tomography (NCCT) images. For each radiologist, a radiological model was constructed from radiological variables; a radiomics score model was constructed from high-dimensional quantitative features extracted from NCCT images; and a combined model was constructed using both radiological variables and radiomics score. Development of models was constructed in a primary cohort (n = 177). We then validated the results in an independent validation cohort (n = 74). The primary outcome was hematoma expansion. We compared the three models for predicting hematoma expansion. Predictive performance was assessed with the receiver operating characteristic (ROC) curve analysis.


In the primary cohort, combined model and radiomics model showed greater AUCs than radiological model for both readers (all p < .05). In the validation cohort, combined model and radiomics model showed greater AUCs, sensitivities, and accuracies than radiological model for reader 2 (all p < .05). Combined model showed greater AUC than radiomics model for reader 1 only in the primary cohort (p = .03). Performance of three models was comparable between reader 1 and reader 2 in both cohorts (all p > .05).


NCCT-based radiomics model showed high predictive performance and outperformed radiological model in the prediction of early hematoma expansion in ICH patients.

Key Points

Radiomics model showed better performance for prediction of hematoma expansion in patients with intracerebral hemorrhage than radiological feature-based model.

Hematomas which expanded in follow-up NCCT tended to be larger in baseline volume, more irregular in shape, more heterogeneous in composition, and coarser in texture.

A radiomics model provides a convenient and objective tool for prediction of hematoma expansion that helps to define subsets of patients who would benefit from anti-expansion therapy.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4



Computed tomography angiography


Interclass correlation coefficient


Intracerebral hemorrhage


Least absolute shrinkage and selection operator


Noncontrast computed tomography


Picture archiving and communication system


Radiomics score


Variance inflation factor


Volume of interest


  1. 1.

    Falcone GJ, Biffi A, Brouwers HB et al (2013) Predictors of hematoma volume in deep and lobar supratentorial intracerebral hemorrhage. JAMA Neurol 70:988–994

    Article  Google Scholar 

  2. 2.

    Qureshi AI, Tuhrim S, Broderick JP, Batjer HH, Hondo H, Hanley DF (2001) Spontaneous intracerebral hemorrhage. N Engl J Med 344:1450–1460

    CAS  Article  Google Scholar 

  3. 3.

    van Asch CJ, Luitse MJ, Rinkel GJ, van der Tweel I, Algra A, Klijn CJ (2010) Incidence, case fatality, and functional outcome of intracerebral haemorrhage over time, according to age, sex, and ethnic origin: a systematic review and meta-analysis. Lancet Neurol 9:167–176

    Article  Google Scholar 

  4. 4.

    Brouwers HB, Chang Y, Falcone GJ et al (2014) Predicting hematoma expansion after primary intracerebral hemorrhage. JAMA Neurol 71:158–164

    Article  Google Scholar 

  5. 5.

    Dowlatshahi D, Demchuk AM, Flaherty ML, Ali M, Lyden PL, Smith EE (2011) Defining hematoma expansion in intracerebral hemorrhage: relationship with patient outcomes. Neurology 76:1238–1244

  6. 6.

    Peng WJ, Reis C, Reis H, Zhang J, Yang J (2017) Predictive value of CTA spot sign on hematoma expansion in intracerebral hemorrhage patients. Biomed Res Int 2017:4137210

    PubMed  PubMed Central  Google Scholar 

  7. 7.

    Xu X, Zhang J, Yang K, Wang Q, Xu B, Chen X (2018) Accuracy of spot sign in predicting hematoma expansion and clinical outcome: a meta-analysis. Medicine (Baltimore) 97:e11945

    Article  Google Scholar 

  8. 8.

    Goldstein JN, Brouwers HB, Romero JM et al (2012) SCORE-IT: the spot sign score in restricting ICH growth─an Atach-II Ancillary Study. J Vasc Interv Neurol 5:20

    PubMed  PubMed Central  Google Scholar 

  9. 9.

    Hussein O, Sawalha K, Fritz J et al (2019) The significance of contrast density of the computed tomography-angiographic spot sign and its correlation with hematoma expansion. J Stroke Cerebrovasc Dis.

  10. 10.

    Barras CD, Tress BM, Christensen S et al (2009) Density and shape as CT predictors of intracerebral hemorrhage growth. Stroke 40:1325

    Article  Google Scholar 

  11. 11.

    Selariu E, Zia E, Brizzi M, Abul-Kasim K (2012) Swirl sign in intracerebral haemorrhage: definition, prevalence, reliability and prognostic value. BMC Neurol 12:109

    Article  Google Scholar 

  12. 12.

    Li Q, Zhang G, Huang YJ et al (2015) Blend sign on computed tomography: novel and reliable predictor for early hematoma growth in patients with intracerebral hemorrhage. Stroke 46:2119

    Article  Google Scholar 

  13. 13.

    Li Q, Liu QJ, Yang WS et al (2018) Island sign: an imaging predictor for early hematoma expansion and poor outcome in patients with intracerebral hemorrhage. Stroke 48:3019

    Article  Google Scholar 

  14. 14.

    Li Q, Zhang G, Xiong X et al (2016) Black hole sign: novel imaging marker that predicts hematoma growth in patients with intracerebral hemorrhage. Stroke 47:1777–1781

    Article  Google Scholar 

  15. 15.

    Boulouis G, Morotti A, Brouwers HB et al (2016) Association between hypodensities detected by computed tomography and hematoma expansion in patients with intracerebral hemorrhage. JAMA Neurol 73:961–968

    Article  Google Scholar 

  16. 16.

    Boulouis G, Morotti A, Charidimou A, Dowlatshahi D, Goldstein JN (2017) Noncontrast computed tomography markers of intracerebral hemorrhage expansion. Stroke 48:1120–1125

    Article  Google Scholar 

  17. 17.

    Yip SS, Aerts HJWL (2016) Applications and limitations of radiomics. Phys Med Biol 61:R150–R166

    CAS  Article  Google Scholar 

  18. 18.

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

    Article  Google Scholar 

  19. 19.

    Zhang Y, Zhang B, Liang F et al (2018) Radiomics features on non-contrast-enhanced CT scan can precisely classify AVM-related hematomas from other spontaneous intraparenchymal hematoma types. Eur Radiol.

  20. 20.

    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 28:4389–4396

  21. 21.

    Demchuk AM, Dowlatshahi D, Rodriguez-Luna D et al (2012) Prediction of haematoma growth and outcome in patients with intracerebral haemorrhage using the CT-angiography spot sign (PREDICT): a prospective observational study. Lancet Neurol 11:307–314

  22. 22.

    Chen Y, Chen TW, Wu CQ et al (2018) Radiomics model of contrast-enhanced computed tomography for predicting the recurrence of acute pancreatitis. Eur Radiol.

  23. 23.

    Ji GW, Zhang YD, Zhang H et al (2019) Biliary tract cancer at CT: a radiomics-based model to predict lymph node metastasis and survival outcomes. Radiology 290:90–98

    Article  Google Scholar 

  24. 24.

    Sauerbrei W, Royston P, Binder H (2007) Selection of important variables and determination of functional form for continuous predictors in multivariable model building. Stat Med 26:5512–5528

    Article  Google Scholar 

  25. 25.

    Huang YQ, Liang CH, 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

    Article  Google Scholar 

  26. 26.

    O’brien RM (2007) A caution regarding rules of thumb for variance inflation factors. Qual Quant 41:673–690

    Article  Google Scholar 

  27. 27.

    DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837–845

    CAS  Article  Google Scholar 

  28. 28.

    Wang X, Arima H, Al-Shahi Salman R et al (2015) Clinical prediction algorithm (BRAIN) to determine risk of hematoma growth in acute intracerebral hemorrhage. Stroke 46:376–381

    CAS  Article  Google Scholar 

  29. 29.

    Blacquiere D, Demchuk AM, Al-Hazzaa M et al (2015) Intracerebral hematoma morphologic appearance on noncontrast computed tomography predicts significant hematoma expansion. Stroke 46:3111–3116

    CAS  Article  Google Scholar 

  30. 30.

    Dowlatshahi D, Morotti A, Al-Ajlan FS et al (2019) Interrater and intrarater measurement reliability of noncontrast computed tomography predictors of intracerebral hemorrhage expansion. Stroke 50:1260–1262

    Article  Google Scholar 

  31. 31.

    Del Giudice A, D'Amico D, Sobesky J, Wellwood I (2014) Accuracy of the spot sign on computed tomography angiography as a predictor of haematoma enlargement after acute spontaneous intracerebral haemorrhage: a systematic review. Cerebrovasc Dis 37:268–276

    Article  Google Scholar 

  32. 32.

    Morotti A, Dowlatshahi D, Boulouis G et al (2018) Predicting intracerebral hemorrhage expansion with noncontrast computed tomography: the BAT Score. Stroke 49:1163–1169

    Article  Google Scholar 

  33. 33.

    Morotti A, Boulouis G, Romero JM et al (2017) Blood pressure reduction and noncontrast CT markers of intracerebral hemorrhage expansion. Neurology 89.

  34. 34.

    Barras CD, Tress BM, Christensen S et al (2013) Quantitative CT densitometry for predicting intracerebral hemorrhage growth. AJNR Am J Neuroradiol 34:1139–1144

    CAS  Article  Google Scholar 

  35. 35.

    Connor D, Huynh TJ, Demchuk AM et al (2015) Swirls and spots: relationship between qualitative and quantitative hematoma heterogeneity, hematoma expansion, and the spot sign. Neurovasc Imaging 1:1–8

    Article  Google Scholar 

  36. 36.

    Miyahara M, Noda R, Yamaguchi S et al (2018) New prediction score for hematoma expansion and neurological deterioration after spontaneous intracerebral hemorrhage: a hospital-based retrospective cohort study. J Stroke Cerebrovasc Dis 27:2543–2550

    Article  Google Scholar 

  37. 37.

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

    Article  Google Scholar 

Download references


This study has received funding from the Interdisciplinary clinical research project of Peking University First Hospital (2017CR21).

Author information



Corresponding author

Correspondence to Xiaodong Zhang.

Ethics declarations


The scientific guarantor of this publication is Xiaodong Zhang.

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

One of the authors has significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.


• 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


(DOCX 35 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Xie, H., Ma, S., Wang, X. et al. Noncontrast computer tomography–based radiomics model for predicting intracerebral hemorrhage expansion: preliminary findings and comparison with conventional radiological model. Eur Radiol 30, 87–98 (2020).

Download citation


  • Cerebral hemorrhage
  • Disease progression
  • Multidetector computed tomography
  • Algorithms
  • Computer-assisted diagnosis