Abstract
Purpose
To build a stroke territory classifier model in DWI by designing the problem as a multiclass segmentation task by defining each stroke territory as distinct segmentation targets and leveraging the guidance of voxel wise dense predictions.
Materials and Methods
Retrospective analysis of DWI images of 218 consecutive acute anterior or posterior ischemic stroke patients examined between January 2017 to April 2020 in a single center was carried out. Each stroke area was defined as distinct segmentation target with different class labels. U-Net based network was trained followed by majority voting of the voxel wise predictions of the model to transform them into patient level stroke territory classes. Effects of bias field correction and registration to a common space were explored.
Results
Of the 218 patients included in this study, 141 (65%) were anterior stroke, and 77 were posterior stroke (35%) whereas 117 (53%) were male and 101 (47%) were female. The model built with original images reached 0.77 accuracy, while the model built with N4 bias corrected images reached 0.80 and the model built with images which were N4 bias corrected and then registered into a common space reached 0.83 accuracy values.
Conclusion
Voxel wise dense prediction coupled with bias field correction to eliminate artificial signal increase and registration to a common space help models for better performance than using original images. Knowing the properties of target domain while designing deep learning models is important for the overall success of these models.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availibility
The data that support the findings of this study are not openly available due to reasons of sensitivity and are available from the corresponding author upon reasonable request.
Code availability
Code will be made available after publication of the manuscript at this URL: https://www.github.com/ozgurkoska78. Data is not allowed to be shared for ethical reasons.
Abbreviations
- DWI:
-
Diffusion weighted imaging
- MNI template:
-
Montreal neurology institute brain anatomy MRI template
- ISLES:
-
Ischemic stroke lesion segmentation challenge
References
Lee KY, Liu CC, Chen DYT, et al. Automatic detection and vascular territory classification of hyperacute staged ischemic stroke on diffusion weighted image using convolutional neural networks. Sci Rep. 2023;13:404. https://doi.org/10.1038/s41598-023-27621-4.
Virani SS, Alonso A, Aparicio HJ, et al. Heart disease and stroke statistics-2021 update: a report from the American heart association. Circulation. 2021;143:e254–743. https://doi.org/10.1161/CIR.0000000000000950.
Roth GA, Abate D, Abate KH, et al. Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980–2017: a systematic analysis for the global burden of disease study. Lancet. 2017;392(10159):1736–88. https://doi.org/10.1016/S0140-6736(18)32203-7.
Liyuan C, Zhiyuan F, Yingjian Y, et al. Deep learning in ischemic stroke imaging analysis: a comprehensive review. BioMed Res Int. 2022. https://doi.org/10.1155/2022/2456550.
Bamford J, Sandercock P, Dennis M, et al. A prospective study of acute cerebrovascular disease in the community: the oxfordshire community stroke project 1981–86 1 methodology, demography and incident cases of first-ever stroke. J Neurol Neurosurg Psychiatry. 1988;51(11):1373–80. https://doi.org/10.1136/jnnp.51.11.1373.
Tao WD, Liu M, Fisher M, et al. Posterior versus anterior circulation infarction: How different are the neurological deficits? Stroke. 2012;43(8):2060–5. https://doi.org/10.1161/STROKEAHA.112.652420.
Baron CA, Kate M, Gioia L, et al. Reduction of diffusion-weighted imaging contrast of acute ischemic stroke at short diffusion times. Stroke. 2015;46(8):2136–41. https://doi.org/10.1161/STROKEAHA.115.008815.
Lee EJ, Kim YH, Kim N, Kang DW. Deep into the brain: artificial intelligence in stroke imaging. J Stroke. 2017;19(3):277–85. https://doi.org/10.5853/jos.2017.02.54.
Valliani AAA, Ranti D, Oermann EK. Deep learning and neurology: a systematic review. Neurol Ther. 2018;8(2):351–65. https://doi.org/10.1007/s40120-019-00153-8.
Kamal H, Lopez V, Sheth S. Machine learning in acute ischemic stroke neuroimaging. Front Neurol. 2018;9:945. https://doi.org/10.3389/fenur.2018.00945.
Murray NM, Unberath M, Hager GD, Hui FK. Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: a systematic review. J Neurointervent Surg. 2020;12(2):156–64. https://doi.org/10.1136/neurintsurg-2019-015135.
Cetinoglu YK, Koska IO, Uluc ME, et al. Detection and vascular territorial classification of stroke on diffusion-weighted MRI by deep learning. Eur J Radiol. 2021;145: 110050. https://doi.org/10.1016/j.ejrad.2021.110050.
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L. MobileNetV2: inverted residuals and linear bottlenecks, in. IEEE/CVF Conf Computer Vision Pattern Recogn. 2018;2018:4510–20. https://doi.org/10.1109/CVPR.2018.00474.
Tan M and Le Q. EfficientNet: rethinking model scaling for convolutional neural networks, in: Proceedings of the 36th International Conference on Machine Learning ICML 2019, 2019, pp. 6105–6114.
Fedorov A, Beichel R, Kalpathy-Cramer J, et al. 3D Slicer as an image computing platform for the quantitative imaging network. Magn Reson Imaging. 2012;30(9):1323–41. https://doi.org/10.1016/j.mri.2012.05.001.
Tustison NJ, Avants BB, Cook PA, et al. N4ITK: improved N3 bias correction. IEEE Trans Med Imaging. 2010;29(6):1310–20. https://doi.org/10.1109/TMI.2010.2046908.
Mazziotta JC, Toga AW, Evans A, Fox P, Lancaster J. A probabilistic atlas of the human brain: theory and rationale for its development the international consortium for brain mapping. Neuroimage. 1995;2(2):89–101. https://doi.org/10.1006/nimg.1995.1012.
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, editors. Medical image computing and computer-assisted intervention MICCAI 2015. MICCAI 2015 lecture notes in computer science. Cham: Springer; 2015.
Martín Abadi, Ashish Agarwal, Paul Barham, et al. TensorFlow: Large-scale machine learning on heterogeneous systems. 2015. Software available from tensorflow.org.
Chollet F. Keras, 2015. Software available from keras.io
Yogananda CGB, Shah BR, Nalawade SS, et al. MRI-based deep-learning method for determining glioma MGMT promoter methylation status. Am J Neuroradil. 2021;42(5):845–52. https://doi.org/10.3174/AJNR.A7029.
Vermeer SE, Hollander M, van Dijk EJ, et al. Silent brain infarcts and white matter lesions increase stroke risk in the general population: the Rotterdam scan study. Stroke. 2003;34(5):1126–9. https://doi.org/10.1161/01.STR.0000068408.82115.D2.
Kim BJ, Lee SH. Prognostic impact of cerebral small vessel disease on stroke outcome. Journal of stroke. 2015;17(2):101–10. https://doi.org/10.5853/jos.2015.17.2.101.
Goceri E. Medical image data augmentation: techniques, comparisons and interpretations. Artif Intell Rev. 2023;56:12561–605. https://doi.org/10.1007/s10462-023-10453-z.
Praveen GB, Agrawal A, Sundaram P, Sardesai S. Ischemic stroke lesion segmentation using stacked sparse auto-encoder. Comput Biol Med. 2018;99:38–52. https://doi.org/10.1016/j.compbiomed.2018.05.027.
Pinto A, Pereira S, Meier R, et al. Combining unsupervised and supervised learning for predicting the final stroke lesion. Med Image Anal. 2021;69: 101888. https://doi.org/10.1016/j.media.2020.101888.
Do LN, Baek BH, Kim SK, et al. Automatic assessment of aspects using diffusion—weighted imaging in acute ischemic stroke using recurrent residual convolutional neural network. Diagnostics. 2020;10(10):803. https://doi.org/10.3390/diagnostics10100803.
Fahed R, Lecler A, Sabben C, et al. DWI-ASPECTS (diffusion-weighted imaging-Alberta stroke program early computed tomography scores) and dwi-flair (diffusion-weighted imaging-fluid attenuated inversion recovery) mismatch in thrombectomy candidates. Stroke. 2018;49(1):223–7. https://doi.org/10.1161/STROKEAHA.117.019508.
Cheng X, Su X, Shi J, et al. Comparison of automated and manual DWI-ASPECTS in acute ischemic stroke: total and region-specific assessment. Eur Radiol. 2021;31(6):4130–7.
Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. PMLR. 2010;2010(9):249–56.
Diederik P. Kingma and Jimmy Lei Ba. Adam: A method for stochastic optimization. 2014. arXiv:1412.6980v9
Funding
No funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
The authors declare that they have no conflicts of interest.
Ethical approval and consent to participate
This study was approved by the institutional review board.
Consent for publication
The institutional review board did not require the informed consent for the retrospective studies. Thus, it was waived.
Human and animal rights
The experiments on humans were followed in accordance with the ethical standards of the institutional review board and with the Helsinki Declaration. No animals were used in this study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
About this article
Cite this article
Koska, I.O., Selver, M.A., Gelal, F. et al. Voxel level dense prediction of acute stroke territory in DWI using deep learning segmentation models and image enhancement strategies. Jpn J Radiol (2024). https://doi.org/10.1007/s11604-024-01582-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11604-024-01582-8