Improving Sensitivity on Identification and Delineation of Intracranial Hemorrhage Lesion Using Cascaded Deep Learning Models


Highly accurate detection of the intracranial hemorrhage without delay is a critical clinical issue for the diagnostic decision and treatment in an emergency room. In the context of a study on diagnostic accuracy, there is a tradeoff between sensitivity and specificity. In order to improve sensitivity while preserving specificity, we propose a cascade deep learning model constructed using two convolutional neural networks (CNNs) and dual fully convolutional networks (FCNs). The cascade CNN model is built for identifying bleeding; hereafter the dual FCN is to detect five different subtypes of intracranial hemorrhage and to delineate their lesions. Using a total of 135,974 CT images including 33,391 images labeled as bleeding, each of CNN/FCN models was trained separately on image data preprocessed by two different settings of window level/width. One is a default window (50/100[level/width]) and the other is a stroke window setting (40/40). By combining them, we obtained a better outcome on both binary classification and segmentation of hemorrhagic lesions compared to a single CNN and FCN model. In determining whether it is bleeding or not, there was around 1% improvement in sensitivity (97.91% [± 0.47]) while retaining specificity (98.76% [± 0.10]). For delineation of bleeding lesions, we obtained overall segmentation performance at 80.19% in precision and 82.15% in recall which is 3.44% improvement compared to using a single FCN model.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13


  1. 1.

    Organization WH: World health statistics 2015: World Health Organization, 2015

  2. 2.

    Bluhmki E, Chamorro Á, Dávalos A, Machnig T, Sauce C, Wahlgren N, Wardlaw J, Hacke W: Stroke treatment with alteplase given 3· 0–4· 5 h after onset of acute ischaemic stroke (ECASS III): additional outcomes and subgroup analysis of a randomised controlled trial. Lancet Neurol 8:1095–1102, 2009

    Article  CAS  PubMed  Google Scholar 

  3. 3.

    Disorders NIoN, Group Sr-PSS: Tissue plasminogen activator for acute ischemic stroke. N Engl J Med 333:1581–1588, 1995

    Article  Google Scholar 

  4. 4.

    Hu T-T, Yan L, Yan P-F, Wang X, Yue G-F: Assessment of the ABC/2 method of epidural hematoma volume measurement as compared to computer-assisted planimetric analysis. Biol Res Nurs 18:5–11, 2016

    Article  CAS  PubMed  Google Scholar 

  5. 5.

    Bhadauria H, Dewal M: Intracranial hemorrhage detection using spatial fuzzy c-mean and region-based active contour on brain CT imaging. SIViP 8:357–364, 2014

    Article  Google Scholar 

  6. 6.

    Muschelli J, Sweeney EM, Ullman NL, Vespa P, Hanley DF, Crainiceanu CM: PItcHPERFeCT: Primary intracranial hemorrhage probability estimation using random forests on CT. NeuroImage Clin 14:379–390, 2017

    Article  PubMed  PubMed Central  Google Scholar 

  7. 7.

    Al-Ayyoub M, Alawad D, Al-Darabsah K, Aljarrah I: Automatic detection and classification of brain hemorrhages. WSEAS Trans Comput 12:395–405, 2013

    Google Scholar 

  8. 8.

    Jones N: The learning machines. Nature 505:146–148, 2014

    Article  CAS  PubMed  Google Scholar 

  9. 9.

    Patel A, Manniesing R: A convolutional neural network for intracranial hemorrhage detection in non-contrast CT. Proc. Medical Imaging 2018: Computer-Aided Diagnosis: City

  10. 10.

    Phong TD, et al.: Brain Hemorrhage Diagnosis by Using Deep Learning. Proc. Proceedings of the 2017 International Conference on Machine Learning and Soft Computing: City

  11. 11.

    Arbabshirani MR, Fornwalt BK, Mongelluzzo GJ, Suever JD, Geise BD, Patel AA, Moore GJ: Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration. npj Digit Med 1:9, 2018

    Article  PubMed  PubMed Central  Google Scholar 

  12. 12.

    Jnawali K, Arbabshirani MR, Rao N, Patel AA: Deep 3D convolution neural network for CT brain hemorrhage classification. Proc. Medical Imaging 2018: Computer-Aided Diagnosis: City

  13. 13.

    Grewal M, Srivastava MM, Kumar P, Varadarajan S: RADnet: Radiologist level accuracy using deep learning for hemorrhage detection in CT scans. Proc. Biomedical Imaging (ISBI 2018), 2018 IEEE 15th International Symposium on: City

  14. 14.

    Titano JJ et al.: Automated deep-neural-network surveillance of cranial images for acute neurologic events. Nat Med 24:1337–1341, 2018

    Article  CAS  Google Scholar 

  15. 15.

    Chilamkurthy S, et al.: Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans, 2018

  16. 16.

    Chang P, et al.: Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT39:1609–1616, 2018

  17. 17.

    Lev MH, Farkas J, Gemmete JJ, Hossain ST, Hunter GJ, Koroshetz WJ, Gonzalez RG: Acute stroke: improved nonenhanced CT detection—benefits of soft-copy interpretation by using variable window width and center level settings. Radiology 213:150–155, 1999

    Article  CAS  PubMed  Google Scholar 

  18. 18.

    Turner P, Holdsworth G: CT stroke window settings: an unfortunate misleading misnomer? Br J Radiol 84:1061–1066, 2011

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. 19.

    Lee H et al.: Pixel-level deep segmentation: artificial intelligence quantifies muscle on computed tomography for body morphometric analysis. J Digit Imaging 30:487–498, 2017

    Article  PubMed  PubMed Central  Google Scholar 

  20. 20.

    Badrinarayanan V, Kendall A, Cipolla R: Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39:2481–2495, 2017

    Article  PubMed  Google Scholar 

  21. 21.

    Ronneberger O, Fischer P, Brox T: U-net: Convolutional networks for biomedical image segmentation. Proc. International Conference on Medical image computing and computer-assisted intervention: City

  22. 22.

    Long J, Shelhamer E, Darrell T: Fully convolutional networks for semantic segmentation. Proc. Proceedings of the IEEE conference on computer vision and pattern recognition: City

  23. 23.

    Kalinovsky A, Kovalev V: Lung image segmentation using deep learning methods and convolutional neural networks, 2016

    Google Scholar 

  24. 24.

    Milletari F, Navab N, Ahmadi S-A: V-net: Fully convolutional neural networks for volumetric medical image segmentation. Proc. 3D Vision (3DV), 2016 Fourth International Conference on: City

  25. 25.

    Curiale AH, Colavecchia FD, Kaluza P, Isoardi RA, Mato G: Automatic Myocardial Segmentation by Using A Deep Learning Network in Cardiac MRI. arXiv preprint arXiv:170807452, 2017

  26. 26.

    Szegedy C, et al.: Going deeper with convolutions: City

  27. 27.

    Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40:834–848, 2018

    Article  PubMed  Google Scholar 

  28. 28.

    Chen L-C, Papandreou G, Schroff F, Adam H: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:170605587, 2017

  29. 29.

    Zhao H, Shi J, Qi X, Wang X, Jia J: Pyramid scene parsing network. Proc. IEEE Conf on Computer Vision and Pattern Recognition (CVPR): City

Download references

Author information



Corresponding author

Correspondence to Junghwan Cho.

Ethics declarations

This data collection was reviewed and approved by the ethics committee at Kyungpook National University Hospital and Kyungpook National University Hospital Chilgok (KNUH 2017-06-005 and KNUCH 2016-11-050).

Additional information

Publisher’s note

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

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cho, J., Park, KS., Karki, M. et al. Improving Sensitivity on Identification and Delineation of Intracranial Hemorrhage Lesion Using Cascaded Deep Learning Models. J Digit Imaging 32, 450–461 (2019).

Download citation


  • Cascaded deep learning model
  • Lesion segmentation
  • Sensitivity
  • CT window setting
  • Fully convolutional networks
  • Intracranial hemorrhage