Detection and classification of intracranial haemorrhage on CT images using a novel deep-learning algorithm

Ji Young Lee, Jong Soo Kim, Tae Yoon Kim, Young Soo Kim, Ji Young Lee, Jong Soo Kim, Tae Yoon Kim, Young Soo Kim

Abstract

A novel deep-learning algorithm for artificial neural networks (ANNs), completely different from the back-propagation method, was developed in a previous study. The purpose of this study was to assess the feasibility of using the algorithm for the detection of intracranial haemorrhage (ICH) and the classification of its subtypes, without employing the convolutional neural network (CNN). For the detection of ICH with the summation of all the computed tomography (CT) images for each case, the area under the ROC curve (AUC) was 0.859, and the sensitivity and the specificity were 78.0% and 80.0%, respectively. Regarding ICH localisation, CT images were divided into 10 subdivisions based on the intracranial height. With the subdivision of 41-50%, the best diagnostic performance for detecting ICH was obtained with AUC of 0.903, the sensitivity of 82.5%, and the specificity of 84.1%. For the classification of the ICH to subtypes, the accuracy rate for subarachnoid haemorrhage (SAH) was considerably excellent at 91.7%. This study revealed that our approach can greatly reduce the ICH diagnosis time in an actual emergency situation with a fairly good diagnostic performance.

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Example of CT image processing for preparing image data. (a) Summed image of a subdivision for a case. (b) Square image expanded to fit in a square.
Figure 2
Figure 2
Example of CT image processing for preparing image data. (a) Square image expanded to fit in a square. (b) Subtracted image to eliminate the skull image and other images not related to ICH.
Figure 3
Figure 3
Schematic representation of the pipeline to detect and classify ICH on brain CT.
Figure 4
Figure 4
Computer screen for the training progress of an artificial neural network.

References

    1. Qureshi AI, Mendelow AD, Hanley DF. Intracerebral haemorrhage. Lancet. 2009;373:1632–1644. doi: 10.1016/s0140-6736(09)60371-8.
    1. Chang PD, Kuoy E. Hybrid 3D/2D convolutional neural network for hemorrhage evaluation on head CT. Am. J. Neuroradiol. 2018;39:1609–1616. doi: 10.3174/ajnr.A5742.
    1. Ginat DT. Analysis of head CT scans flagged by deep learning software for acute intracranial hemorrhage. Neuroradiology. 2020;62:335–340. doi: 10.1007/s00234-019-02330-w.
    1. van Asch CJ, et al. 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. 2010;9:167–176. doi: 10.1016/S1474-4422(09)70340-0.
    1. Prevedello LM, et al. Automated critical test findings identification and online notification system using artificial intelligence in imaging. Radiology. 2017;285:923–931. doi: 10.1148/radiol.2017162664.
    1. Arbabshirani MR, et al. Advanced machine learning in action: Identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration. NPJ Digit. Med. 2018;1:9. doi: 10.1038/s41746-017-0015-z.
    1. Ye H, et al. Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network. Eur. Radiol. 2019;29:6191–6201. doi: 10.1007/s00330-019-06163-2.
    1. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–444. doi: 10.1038/nature14539.
    1. Zaharchuk G, Gong E. Deep learning in neuroradiology. AJNR Am. J. Neuroradiol. 2018;39:1776–1784. doi: 10.3174/ajnr.A5543.
    1. Werbos, P. Beyond regression: New tools for prediction and analysis in the behavioral sciences. Ph. D. dissertation, Harvard University (1974).
    1. Sathyanarayana S. A gentle introduction to backpropagation. Numer. Insight. 2014;7:1–15.
    1. Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1986;323:533–536. doi: 10.1038/323533a0.
    1. Kim EK, et al. Applying data-driven imaging biomarker in mammography for breast cancer screening: Preliminary study. Sci. Rep. 2018;8:2762. doi: 10.1038/s41598-018-21215-1.
    1. Lee H, Yune S. An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets. Nat. Biomed. Eng. 2019;3:173–182. doi: 10.1038/s41551-018-0324-9.
    1. Kim JS, Cho Y, Lim TH. Prediction of the location of the glottis in laryngeal images by using a novel deep-learning algorithm. IEEE Access. 2019;7:79545–79554. doi: 10.1109/ACCESS.2019.2923002.
    1. Soffer S, et al. Convolutional neural networks for radiologic images: A radiologist's guide. Radiology. 2019;290:590–606. doi: 10.1148/radiol.2018180547.
    1. Chilamkurthy S, et al. Deep learning algorithms for detection of critical findings in head CT scans: A retrospective study. Lancet. 2018;392:2388–2396. doi: 10.1016/s0140-6736(18)31645-3.

Source: PubMed

Sponsorer og samarbejdspartnere

Medicinske tilstande

Narkotikainterventioner

3
Abonner