Skip to main content
SpringerLink
Log in

Quantitative Serial CT Imaging-Derived Features Improve Prediction of Malignant Cerebral Edema after Ischemic Stroke

  • Original Work
  • Published:
Neurocritical Care Aims and scope Submit manuscript

A Response to this article was published on 22 September 2020

A Letters to the editor to this article was published on 21 September 2020

Abstract

Introduction

Malignant cerebral edema develops in a small subset of patients with hemispheric strokes, precipitating deterioration and death if decompressive hemicraniectomy (DHC) is not performed in a timely manner. Predicting which stroke patients will develop malignant edema is imprecise based on clinical data alone. Head computed tomography (CT) imaging is often performed at baseline and 24-h. We determined the incremental value of incorporating imaging-derived features from serial CTs to enhance prediction of malignant edema.

Methods

We identified hemispheric stroke patients at three sites with NIHSS ≥ 7 who had baseline as well as 24-h clinical and CT imaging data. We extracted quantitative imaging features from baseline and follow-up CTs, including CSF volume, intracranial reserve (CSF/cranial volume), as well as midline shift (MLS) and infarct-related hypodensity volume. Potentially lethal malignant edema was defined as requiring DHC or dying with MLS over 5-mm. We built machine-learning models using logistic regression first with baseline data and then adding 24-h data including reduction in CSF volume (ΔCSF). Model performance was evaluated with cross-validation using metrics of recall (sensitivity), precision (predictive value), as well as area under receiver-operating-characteristic and precision-recall curves (AUROC, AUPRC).

Results

Twenty of 361 patients (6%) died or underwent DHC. Baseline clinical variables alone had recall of 60% with low precision (7%), AUROC 0.59, AUPRC 0.15. Adding baseline intracranial reserve improved recall to 80% and AUROC to 0.82 but precision remained only 16% (AUPRC 0.28). Incorporating ΔCSF improved AUPRC to 0.53 (AUROC 0.91) while all imaging features further improved prediction (recall 90%, precision 38%, AUROC 0.96, AUPRC 0.66).

Conclusion

Incorporating quantitative CT-based imaging features from baseline and 24-h CT enhances identification of patients with malignant edema needing DHC. Further refinements and external validation of such imaging-based machine-learning models are required.

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

Similar content being viewed by others

References

  1. Battey TW, Karki M, Singhal AB, Wu O, Sadaghiani S, Campbell BC, Davis SM, Donnan GA, Sheth KN, Kimberly WT. Brain edema predicts outcome after nonlacunar ischemic stroke. Stroke. 2014;45(12):3643–8. https://doi.org/10.1161/STROKEAHA.114.006884.

    Article  PubMed  PubMed Central  Google Scholar 

  2. Broocks G, Flottmann F, Scheibel A, Aigner A, Faizy TD, Hanning U, Leischner H, Broocks SI, Fiehler J, Gellissen S, Kemmling A. Quantitative lesion water uptake in acute stroke computed tomography is a predictor of malignant infarction. Stroke. 2018;49(8):1906–12. https://doi.org/10.1161/STROKEAHA.118.020507.

    Article  PubMed  Google Scholar 

  3. Krieger DW, Demchuk AM, Kasner SE, Jauss M, Hantson L. Early clinical and radiological predictors of fatal brain swelling in ischemic stroke. Stroke. 1999;30:287–92.

    Article  CAS  Google Scholar 

  4. Hacke W, Schwab S, Horn M, Spranger M, De Georgia M, von Kummer R. ‘Malignant’ middle cerebral artery territory infarction: clinical course and prognostic signs. Arch Neurol. 1996;53:309–15.

    Article  CAS  Google Scholar 

  5. Berrouschot J, Sterker M, Bettin S, Köster J, Schneider D. Mortality of space-occupying (‘malignant’) middle cerebral artery infarction under conservative intensive care. Intensive Care Med. 1998;24:620–3.

    Article  CAS  Google Scholar 

  6. Vahedi K, Hofmeijer J, Juettler E, Vicaut E, George B, Algra A, Amelink GJ, Schmiedeck P, Schwab S, Rothwell PM, Bousser M-G, van der Worp HB, Hacke W. Early decompressive surgery in malignant infarction of the middle cerebral artery: a pooled analysis of three randomised controlled trials. Lancet Neurol. 2007;6:215–22. https://doi.org/10.1016/S1474-4422(07)70036-4.

    Article  PubMed  Google Scholar 

  7. Silver FL, Norris JW, Lewis AJ, Hachinski VC. Early mortality following stroke: a prospective review. Stroke. 1984;15:492–6. https://doi.org/10.1161/01.STR.15.3.492.

    Article  CAS  PubMed  Google Scholar 

  8. Heinsius T, Bogousslavsky J, Van Melle G. Large infarcts in the middle cerebral artery territory. Etiology and outcome patterns. Neurology. 1998;50:341–50.

    Article  CAS  Google Scholar 

  9. Hofmeijer J, Algra A, Kappelle LJ, van der Worp HB. Predictors of life-threatening brain edema in middle cerebral artery infarction. Cerebrovasc Dis (Basel, Switzerland). 2008;25:176–84. https://doi.org/10.1159/000113736.

    Article  Google Scholar 

  10. Thomalla G, Hartmann F, Juettler E, Singer OC, Lehnhardt F-G, Köhrmann M, Kersten JF, Krützelmann A, Humpich MC, Sobesky J, Gerloff C, Villringer A, Fiehler J, Neumann-Haefelin T, Schellinger PD, Röther J. Prediction of malignant middle cerebral artery infarction by magnetic resonance imaging within 6 hours of symptom onset: a prospective multicenter observational study. Ann Neurol. 2010;68:435–45. https://doi.org/10.1002/ana.22125.

    Article  PubMed  Google Scholar 

  11. Dhar R, Yuan K, Kulik T, Chen Y, Heitsch L, An H, Ford A, Lee JM. CSF volumetric analysis for quantification of cerebral edema after hemispheric infarction. Neurocrit Care. 2015. https://doi.org/10.1007/s12028-015-0204-z.

    Article  PubMed  Google Scholar 

  12. Broocks G, Flottmann F, Ernst M, Faizy TD, Minnerup J, Siemonsen S, Fiehler J, Kemmling A. Computed tomography-based imaging of voxel-wise lesion water uptake in ischemic brain: relationship between density and direct volumetry. Invest Radiol. 2018;53(4):207–13. https://doi.org/10.1097/RLI.0000000000000430.

    Article  PubMed  Google Scholar 

  13. Minnerup J, Wersching H, Ringelstein EB, Heindel W, Niederstadt T, Schilling M, Schäbitz W-R, Kemmling A. Prediction of malignant middle cerebral artery infarction using computed tomography-based intracranial volume reserve measurements. Stroke. 2011;42:3403–9. https://doi.org/10.1161/STROKEAHA.111.619734.

    Article  PubMed  Google Scholar 

  14. Kauw F, Bennink E, de Jong H, Kappelle LJ, Horsch AD, Velthuis BK, Dankbaar JW, Investigators D, follows Diaa. Intracranial cerebrospinal fluid volume as a predictor of malignant middle cerebral artery infarction. Stroke. 2019;50:1437–43. https://doi.org/10.1161/strokeaha.119.024882.

    Article  PubMed Central  Google Scholar 

  15. Dhar R, Chen Y, Hamzehloo A, Kumar A, Heitsch L, He J, Chen L, Slowik A, Strbian D, Lee JM. Reduction in Cerebrospinal Fluid Volume as an Early Quantitative Biomarker of Cerebral Edema After Ischemic Stroke. Stroke. 2020;51(2):462–7. https://doi.org/10.1161/STROKEAHA.119.027895.

    Article  PubMed  Google Scholar 

  16. Ong CJ, Gluckstein J, Laurido-Soto O, Yan Y, Dhar R, Lee JM. Enhanced detection of edema in malignant anterior circulation stroke (EDEMA) score: a risk prediction tool. Stroke. 2017;48(7):1969–72. https://doi.org/10.1161/STROKEAHA.117.016733.

    Article  PubMed  PubMed Central  Google Scholar 

  17. Thoren M, Azevedo E, Dawson J, Egido JA, Falcou A, Ford GA, Holmin S, Mikulik R, Ollikainen J, Wahlgren N, Ahmed N. Predictors for cerebral edema in acute ischemic stroke treated with intravenous thrombolysis. Stroke. 2017;48(9):2464–71. https://doi.org/10.1161/STROKEAHA.117.018223.

    Article  PubMed  Google Scholar 

  18. Dhar R, Chen Y, An H, Lee JM. Application of machine learning to automated analysis of cerebral edema in large cohorts of ischemic stroke patients. Front Neurol. 2018;9:687. https://doi.org/10.3389/fneur.2018.00687.

    Article  PubMed  PubMed Central  Google Scholar 

  19. Chen Y, Dhar R, Heitsch L, Ford A, Fernandez-Cadenas I, Carrera C, Montaner J, Lin W, Shen D, An H, Lee JM. Automated quantification of cerebral edema following hemispheric infarction: application of a machine-learning algorithm to evaluate CSF shifts on serial head CTs. Neuroimage Clin. 2016;12:673–80. https://doi.org/10.1016/j.nicl.2016.09.018.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One. 2015;10(3):e0118432. https://doi.org/10.1371/journal.pone.0118432.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  21. Park J, Goh D-H, Sung J-K, Hwang Y-H, Kang D-H, Kim Y. Timely assessment of infarct volume and brain atrophy in acute hemispheric infarction for early surgical decompression: strict cutoff criteria with high specificity. Acta Neurochir. 2012;154:79–85. https://doi.org/10.1007/s00701-011-1178-z.

    Article  PubMed  Google Scholar 

  22. Broocks G, Kemmling A, Aberle J, Kniep H, Bechstein M, Flottmann F, Leischner H, Faizy TD, Nawabi J, Schon G, Sporns P, Thomalla G, Fiehler J, Hanning U. Ischemic lesion water uptake in acute stroke: Is blood glucose related to cause and effect? J Stroke. 2019;21(3):347–9. https://doi.org/10.5853/jos.2019.01935.

    Article  PubMed  PubMed Central  Google Scholar 

  23. Diprose WK, Diprose JP, Wang MTM, Tarr GP, McFetridge A, Barber PA. Automated measurement of cerebral atrophy and outcome in endovascular thrombectomy. Stroke. 2019;50(12):3636–8. https://doi.org/10.1161/STROKEAHA.119.027120.

    Article  PubMed  Google Scholar 

  24. Liu Y, Chen PC, Krause J, Peng L. How to read articles that use machine learning: users’ guides to the medical literature. JAMA. 2019;322(18):1806–16. https://doi.org/10.1001/jama.2019.16489.

    Article  PubMed  Google Scholar 

  25. Counsell C, Dennis M. Systematic review of prognostic models in patients with acute stroke. Cerebrovasc Dis. 2001;12(3):159–70. https://doi.org/10.1159/000047699.

    Article  CAS  PubMed  Google Scholar 

  26. Kimberly WT, Bevers MB, von Kummer R, Demchuk AM, Romero JM, Elm JJ, Hinson HE, Molyneaux BJ, Simard JM, Sheth KN. Effect of IV glyburide on adjudicated edema endpoints in the GAMES-RP Trial. Neurology. 2018;91(23):e2163–9. https://doi.org/10.1212/WNL.0000000000006618.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Vorasayan P, Bevers MB, Beslow LA, Sze G, Molyneaux BJ, Hinson HE, Simard JM, von Kummer R, Sheth KN, Kimberly WT. Intravenous glibenclamide reduces lesional water uptake in large hemispheric infarction. Stroke. 2019;50:3021–327. https://doi.org/10.1161/strokeaha.119.026036.

    Article  PubMed  PubMed Central  Google Scholar 

  28. Horsch AD, Dankbaar JW, Stemerdink TA, Bennink E, van Seeters T, Kappelle LJ, Hofmeijer J, de Jong HW, van der Graaf Y, Velthuis BK, investigators D. Imaging findings associated with space-occupying edema in patients with large middle cerebral artery infarcts. AJNR Am J Neuroradiol. 2016. https://doi.org/10.3174/ajnr.A4637.

    Article  PubMed  Google Scholar 

  29. Jo K, Bajgur SS, Kim H, Choi HA, Huh PW, Lee K. A simple prediction score system for malignant brain edema progression in large hemispheric infarction. PLoS One. 2017;12(2):e0171425. https://doi.org/10.1371/journal.pone.0171425.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Hoelter P, Muehlen I, Goelitz P, Beuscher V, Schwab S, Doerfler A. Automated ASPECT scoring in acute ischemic stroke: comparison of three software tools. Neuroradiology. 2020. https://doi.org/10.1007/s00234-020-02439-3.

    Article  PubMed  PubMed Central  Google Scholar 

  31. Ramos LA, van der Steen WE, Sales Barros R, Majoie C, van den Berg R, Verbaan D, Vandertop WP, Zijlstra I, Zwinderman AH, Strijkers GJ, Olabarriaga SD, Marquering HA. Machine learning improves prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage. J Neurointerv Surg. 2019;11(5):497–502. https://doi.org/10.1136/neurintsurg-2018-014258.

    Article  PubMed  Google Scholar 

  32. Ho KC, Speier W, El-Saden S, Liebeskind DS, Saver JL, Bui AA, Arnold CW. Predicting discharge mortality after acute ischemic stroke using balanced data. AMIA Annu Symp Proc. 2014;2014:1787–96.

    PubMed  PubMed Central  Google Scholar 

  33. Ge Y, Wang Q, Wang L, Wu H, Peng C, Wang J, Xu Y, Xiong G, Zhang Y, Yi Y. Predicting post-stroke pneumonia using deep neural network approaches. Int J Med Inform. 2019;132:103986. https://doi.org/10.1016/j.ijmedinf.2019.103986.

    Article  PubMed  Google Scholar 

Download references

Funding

This work was supported by grants from the National Institutes of Health to JML (R01NS085419), RD (K23NS099440), DM (P30NS098577) and LH (K23NS099487).

Author information

Authors and Affiliations

  1. Department of Electrical and Systems Engineering, Washington University in St. Louis, Saint Louis, USA

    Hossein Mohammadian Foroushani

  2. Department of Neurology, Washington University in St. Louis School of Medicine, 660 S Euclid Avenue, Campus Box 8111, Saint Louis, MO, 63110, USA

    Ali Hamzehloo, Atul Kumar, Yasheng Chen, Jin-Moo Lee & Rajat Dhar

  3. Department of Emergency Medicine, Washington University School of Medicine, Washington, USA

    Laura Heitsch

  4. Department of Neurology, Jagiellonian University Medical College, Kraków, Poland

    Agnieszka Slowik

  5. Department of Neurology, Helsinki University Hospital, Helsinki, Finland

    Daniel Strbian

  6. Department of Radiology, Washington University School of Medicine, Saint Louis, USA

    Daniel S. Marcus

Authors
  1. Hossein Mohammadian Foroushani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ali Hamzehloo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Atul Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yasheng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Laura Heitsch
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Agnieszka Slowik
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Daniel Strbian
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jin-Moo Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Daniel S. Marcus
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Rajat Dhar
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors were involved in study concept and design and in critical revision of the manuscript for important intellectual content. AH, AK, YC and LH were involved in data acquisition and cleaning. HMF performed the data analysis. RD was involved in interpretation of results and in drafting the manuscript, along with HMF. All authors approved the final version of the manuscript.

Corresponding author

Correspondence to Rajat Dhar.

Ethics declarations

Conflict of interest

No authors have any conflicts of interest to disclose.

Informed consent

All research was conducted under approval of the institutional ethics review board and all subjects or legally authorized representatives provided informed consent for data collection.

Additional information

Publisher's Note

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

This work was performed at Washington University in St. Louis.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (DOCX 450 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Foroushani, H.M., Hamzehloo, A., Kumar, A. et al. Quantitative Serial CT Imaging-Derived Features Improve Prediction of Malignant Cerebral Edema after Ischemic Stroke. Neurocrit Care 33, 785–792 (2020). https://doi.org/10.1007/s12028-020-01056-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12028-020-01056-5

Keywords

Search

Navigation