Abstract
In the presence of cardiovascular disease and neurodegenerative disorders, the white matter of the brains of clinical study participants often present bright spots in T2-weighted Magnetic Resonance Imaging scans. The pathways contributing to the emergence of these white matter hyperintensities are still debated. By offering the possibility to directly compare MRI patterns with cellular and tissue alterations, research studies coupling postmortem imaging with histological studies are the most likely to provide a satisfactory answer to these open questions. Unfortunately, manually segmenting white matter hyperintensities in postmortem MRI scans before histology is time-consuming and labor-intensive. In this work, we propose to tackle this issue with new, fully automatic segmentation tools relying on the most recent Deep Learning architectures. More specifically, we compare the ability to predict white matter hyperintensities from a registered pair of T1 and T2-weighted postmortem MRI scans of five Unet architectures: the original Unet, DoubleUNet, Attention UNet, Multiresolution UNet, and a new architecture specifically designed for the task. A detailed comparison between these five Unets and an ablation study, carried out on the sagittal slices of 13 pairs of high-resolution T1 and T2 weighted MRI scans manually annotated by neuroradiologists, demonstrate the superiority of our new approach and provide an estimation of the performance gains offered by the modules introduced in the new architecture.
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
References
Anbeek, P., Vincken, K.L., Van Osch, M.J.P., Bisschops, R.H.C., Van Det Grond, J.: Probabilistic segmentation of white matter lesions in MR imaging. NeuroImage 21(3), 1037–1044 (2004)
Anonymous: in revision
Avants, B., Tustison, N., Wu, J., Cook, P., Gee, J.: An open source multivariate framework for n-tissue segmentation with evaluation on public data. Neuroinformatics 9(4), 381–400 (2011)
Benson, R.R., et al.: Older people with impaired mobility have specific loci of periventricular abnormality on MRI. Neurology 58(1), 48–55 (2002)
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49
Fiford, C.M., et al.: Automated white matter hyperintensity segmentation using bayesian model selection: assessment and correlations with cognitive change. Neuroinformatics 18, 429–449 (2020)
Gibson, E., Gao, F., Black, S.E., Lobaugh, N.J.: Automatic segmentation of white matter hyperintensities in the elderly using flair images at 3t. J. Magn. Reson. Imaging 31(6), 1311–1322 (2010)
Giese, A.K., et al.: White matter hyperintensity burden in acute stroke patients differs by ischemic stroke subtype. Neurology 95(1), e79–e88 (2020)
Grinberg, L., et al.: Improved detection of incipient vascular changes by a biotechnological platform combining post mortem MRI in situ with neuropathology. J. Neurol. Sci. 283(1–2), 2–8 (2009)
Habes, M., et al.: White matter hyperintensities and imaging patterns of brain ageing in the general population. Brain 139(4), 1164–1179 (2016)
Habes, M., et al.: White matter lesions: spatial heterogeneity, links to risk factors, cognition, genetics, and atrophy. Neurology 91(10), e964–e975 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Ibtehaz, N., Rahman, M.S.: Multiresunet: rethinking the u-net architecture for multimodal biomedical image segmentation. Neural Netw. 121, 74–87 (2020)
Jenkinson, M., Beckmann, C., Behrens, T., Woolrich, M., Smith, S.: FSL. NeuroImage 62(2), 782–790 (2012)
Jha, D., Riegler, M.A., Johansen, D., Halvorsen, P., Johansen, H.D.: Doubleu-net: a deep convolutional neural network for medical image segmentation. In: 2020 IEEE 33rd International Symposium on Computer-Based Medical Systems (CBMS), pp. 558–564. IEEE (2020)
Jonkman, L.E., Kenkhuis, B., Geurts, J.J., van de Berg, W.D.: Post-mortem MRI and histopathology in neurologic disease: a translational approach. Neurosci. Bull. 35, 229–243 (2019)
Lee, S., et al.: White matter hyperintensities are a core feature of Alzheimer’s disease: evidence from the dominantly inherited Alzheimer network. Ann. Neurol. 79(6), 929–939 (2016)
Maldjian, J.A., et al.: Automated white matter total lesion volume segmentation in diabetes. Am. J. Neuroradiol. 34(12), 2265–2270 (2013)
Manjón, J., Coupé, P., Martí-Bonmatí, L., Collins, D., Robles, M.: Adaptive non-local means denoising of MR images with spatially varying noise levels. J. Magn. Resonan. Imaging: JMRI 31(1), 192–203 (2010)
Murray, M.E., et al.: A quantitative postmortem MRI design sensitive to white matter hyperintensity differences and their relationship with underlying pathology. J. Neuropathol. Exp. Neurol. 71(12), 1113–1122 (2012)
Oktay, O., et al.: Attention U-net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)
Rahil, M., Anoop, B., Girish, G., Kothari, A.R., Koolagudi, S.G., Rajan, J.: A deep ensemble learning-based CNN architecture for multiclass retinal fluid segmentation in oct images. IEEE Access (2023)
Rashid, T., et al.: DeepMIR: a deep neural network for differential detection of cerebral microbleeds and iron deposits in MRI. Sci. Rep. 11(1), 14124 (2021)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Roseborough, A.D., et al.: Post-mortem 7 tesla MRI detection of white matter hyperintensities: a multidisciplinary voxel-wise comparison of imaging and histological correlates. NeuroImage: Clin. 27, 102340 (2020)
Samaille, T., et al.: Contrast-based fully automatic segmentation of white matter hyperintensities: method and validation. PLoS ONE 7(11), e48953 (2012)
Simões, R., et al.: Automatic segmentation of cerebral white matter hyperintensities using only 3d flair images. Magn. Reson. Imaging 31(7), 1182–1189 (2013)
Smith, C.D., Snowdon, D.A., Wang, H., Markesbery, W.R.: White matter volumes and periventricular white matter hyperintensities in aging and dementia. Neurology 54(4), 838–842 (2000)
Tustison, N.J., et al.: N4ITK: improved n3 bias correction. IEEE Trans. Med. Imaging 29(6), 1310–1320 (2010)
Verhaaren, B.F., et al.: Multiethnic genome-wide association study of cerebral white matter hyperintensities on MRI. Circulat. Cardiovasc. Genet. 8(2), 398–409 (2015)
Viteri, J.A., Loayza, F.R., Pelaez, E., Layedra, F.: Automatic brain white matter hypertinsities segmentation using deep learning techniques. In: HEALTHINF, pp. 244–252 (2021)
Zhuang, F.J., Chen, Y., He, W.B., Cai, Z.Y.: Prevalence of white matter hyperintensities increases with age. Neural Regen. Res. 13(12), 2141 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Benet Nirmala, A. et al. (2023). Deep Attention Assisted Multi-resolution Networks for the Segmentation of White Matter Hyperintensities in Postmortem MRI Scans. In: Abdulkadir, A., et al. Machine Learning in Clinical Neuroimaging. MLCN 2023. Lecture Notes in Computer Science, vol 14312. Springer, Cham. https://doi.org/10.1007/978-3-031-44858-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-44858-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44857-7
Online ISBN: 978-3-031-44858-4
eBook Packages: Computer ScienceComputer Science (R0)
