Abstract
White matter hyperintensities (WMH) and ischaemic stroke lesions are frequently seen on brain magnetic resonance images (MRI) of people with cerebral small vessel disease (SVD). Segmentation and differentiation of these lesions is important in diagnosis, prognosis and management, but this is challenging to automate because they have similar appearance. In this study, we used MRI scans from four cohorts of people with sporadic SVD with both WMH and ischaemic stroke, acquired under diverse imaging protocols, totalling 297 individuals. We compared two state-of-the-art medical image segmentation frameworks and investigated the data characteristics affecting the performance. We found that nnU-Net and an ensemble of two Auto3DSeg-trained models outperform (p < 0.05 for WMH and stroke Dice Coefficients (DSC)) a model previously proposed for this task, achieving mean DSC of 0.613 and 0.615 respectively compared with 0.512. The segmentation performance was better when the stroke lesions were subcortical than when they were cortical, with a mean DSC of 0.635 compared with 0.580, for nnU-Net. We found that including only a small number (n = 12) of scans with lower contrast and lower resolution to the high quality training data (n = 150) resulted in improvements (p < 0.05) in the WMH DSC and 95th percentile of the Hausdorff Distance (95% HD) for stroke on the 61 lower quality scans in the test set. In conclusion, cortical stroke lesions are more likely to be confounded with WMH due to their size and shape, despite their different locations, and including only a few would-be out-of-distribution examples in the training data can result in statistically significant performance gains.
Supported by Medical Research Scotland and Canon Medical Research Europe.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
References
Antonelli, M., et al.: The medical segmentation decathlon. Nat. Commun. 13(1), 4128 (2022). https://doi.org/10.1038/s41467-022-30695-9
Avesta, A., et al.: Comparing 3D, 2.5D, and 2D approaches to brain image auto-segmentation. Bioengineering 10(2) (2023). https://doi.org/10.3390/bioengineering10020181
Clancy, U., et al.: Rationale and design of a longitudinal study of cerebral small vessel diseases, clinical and imaging outcomes in patients presenting with mild ischaemic stroke: mild stroke study 3. Eur. Stroke J. 6(1), 81–88 (2021). https://doi.org/10.1177/2396987320929617
Debette, S., et al.: Clinical significance of magnetic resonance imaging markers of vascular brain injury: a systematic review and meta-analysis. JAMA Neurol. 76(1), 81–94 (2019). https://doi.org/10.1001/jamaneurol.2018.3122
Dorent, R., et al.: Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets. Med. Image Anal. 67, 101862 (2021). https://doi.org/10.1016/j.media.2020.101862
Duan, Y., et al.: Primary categorizing and masking cerebral small vessel disease based on “deep learning system”. Front. Neuroinform. 14 (2020)
Guerrero, R., et al.: White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks. NeuroImage: Clin. 17, 918–934 (2018). https://doi.org/10.1016/j.nicl.2017.12.022
Hatamizadeh, A., et al.: Swin UNETR: swin transformers for semantic segmentation of brain tumors in MRI images. In: Crimi, A., Bakas, S. (eds.) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, pp. 272–284. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-08999-2_22
He, Y., et al.: Dints: differentiable neural network topology search for 3d medical image segmentation. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5837–5846 (2021). https://doi.org/10.1109/CVPR46437.2021.00578
Hernandez Petzsche, M.R., et al.: ISLES 2022: a multi-center magnetic resonance imaging stroke lesion segmentation dataset. Scientific Data 9(1), 762 (2022). https://doi.org/10.1038/s41597-022-01875-5
Isensee, F., et al.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021). https://doi.org/10.1038/s41592-020-01008-z
Kuijf, H.J., et al.: Standardized assessment of automatic segmentation of white matter hyperintensities and results of the WMH segmentation challenge. IEEE Trans. Med. Imaging 38(11), 2556–2568 (2019). https://doi.org/10.1109/TMI.2019.2905770
Liew, S.L., Lo, B.P., Donnelly, M.T.: A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms. Scientific Data 9(1), 320 (2022). https://doi.org/10.1038/s41597-022-01401-7
Liu, L., et al.: LLRHNet: multiple lesions segmentation using local-long range features. Front. Neuroinform. 16 (2022)
Makin, S.D., et al.: Clinically confirmed stroke with negative diffusion-weighted imaging magnetic resonance imaging. Stroke 46(11), 3142–3148 (2015). https://doi.org/10.1161/STROKEAHA.115.010665
MONAI: Medical open network for AI (2022). https://doi.org/10.5281/zenodo.7459814
Myronenko, A.: 3D MRI brain tumor segmentation using autoencoder regularization. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11384, pp. 311–320. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11726-9_28
Myronenko, A., Siddiquee, M.M.R., Yang, D., He, Y., Xu, D.: Automated head and neck tumor segmentation from 3D PET/CT HECKTOR 2022 challenge report. In: Andrearczyk, V., Oreiller, V., Hatt, M., Depeursinge, A. (eds.) Head and Neck Tumor Segmentation and Outcome Prediction, pp. 31–37. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-27420-6_2
Oreiller, V., et al.: Head and neck tumor segmentation in PET/CT: the HECKTOR challenge. Med. Image Anal. 77, 102336 (2022). https://doi.org/10.1016/j.media.2021.102336
Wang, Y., et al.: Multi-stage segmentation of white matter hyperintensity, cortical and lacunar infarcts. Neuroimage 60(4), 2379–2388 (2012). https://doi.org/10.1016/j.neuroimage.2012.02.034
Wardlaw, J.M., et al.: Brain aging, cognition in youth and old age and vascular disease in the lothian birth cohort 1936: rationale, design and methodology of the imaging protocol. Int. J. Stroke 6(6), 547–559 (2011). https://doi.org/10.1111/j.1747-4949.2011.00683.x
Wardlaw, J.M., et al.: Lacunar stroke is associated with diffuse blood-brain barrier dysfunction. Ann. Neurol. 65(2), 194–202 (2009). https://doi.org/10.1002/ana.21549
Wardlaw, J.M., et al.: Blood-brain barrier failure as a core mechanism in cerebral small vessel disease and dementia: evidence from a cohort study. Alzheimer’s & Dementia 13(6), 634–643 (2017). https://doi.org/10.1016/j.jalz.2016.09.006
Acknowledgements
We would like to acknowledge Medical Research Scotland and Canon Medical Research Europe for providing funding for this work. Data collection and preparation, ground truth generation and supervision received funding from the Row Fogo Charitable Trust (BRO-D. FID3668413), MRC UK (G0701120, G1001245, MR/M013111/1 and MR/R024065/1), Dementia Research Institute, and Wellcome Trust (WT088134/Z/09/A).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Phitidis, J. et al. (2024). Segmentation of White Matter Hyperintensities and Ischaemic Stroke Lesions in Structural MRI. In: Waiter, G., Lambrou, T., Leontidis, G., Oren, N., Morris, T., Gordon, S. (eds) Medical Image Understanding and Analysis. MIUA 2023. Lecture Notes in Computer Science, vol 14122. Springer, Cham. https://doi.org/10.1007/978-3-031-48593-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-48593-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48592-3
Online ISBN: 978-3-031-48593-0
eBook Packages: Computer ScienceComputer Science (R0)