Abstract
Perfusion imaging is the current gold standard for acute ischemic stroke analysis. It allows quantification of the salvageable and non-salvageable tissue regions (penumbra and core areas respectively). In clinical settings, the singular value decomposition (SVD) deconvolution is one of the most accepted and used approaches for generating interpretable and physically meaningful maps. Though this method has been widely validated in experimental and clinical settings, it might produce suboptimal results because the chosen inputs to the model cannot guarantee optimal performance. For the most critical input, the arterial input function (AIF), it is still controversial how and where it should be chosen even though the method is very sensitive to this input. In this work we propose an AIF selection approach that is optimized for maximal core lesion segmentation performance. The AIF is regressed by a neural network optimized through a differentiable SVD deconvolution, aiming to maximize core lesion segmentation agreement with ground truth data. To our knowledge, this is the first work exploiting a differentiable deconvolution model with neural networks. We show that our approach is able to generate AIFs without any manual annotation, and hence avoiding manual rater’s influences. The method achieves manual expert performance in the ISLES18 dataset. We conclude that the methodology opens new possibilities for improving perfusion imaging quantification with deep neural networks.
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
Albers, G.W., et al.: Ischemic core and hypoperfusion volumes predict infarct size in SWIFT PRIME. Ann. Neurol. 79(1), 76–89 (2016)
Bertels, J., Robben, D., Vandermeulen, D., Suetens, P.: Optimization with soft dice can lead to a volumetric bias. arXiv preprint arXiv:1911.02278 (2019)
Bland, J.M., Altman, D.: Statistical methods for assessing agreement between two methods of clinical measurement. Lancet 327(8476), 307–310 (1986)
Calamante, F.: Arterial input function in perfusion MRI: a comprehensive review. Progr. Nucl. Magn. Reson. Spectrosc. 74, 1–32 (2013)
Cereda, C.W., et al.: A benchmarking tool to evaluate computer tomography perfusion infarct core predictions against a DWI standard. J. Cereb. Blood Flow Metab. 36(10), 1780–1789 (2016)
Fan, S., et al.: An automatic estimation of arterial input function based on multi-stream 3d CNN. Front. Neuroinform. 13, 49 (2019)
Fieselmann, A., Kowarschik, M., Ganguly, A., Hornegger, J., Fahrig, R.: Deconvolution-based CT and MR brain perfusion measurement: theoretical model revisited and practical implementation details. J. Biomed. Imaging 2011, 14 (2011)
Ionescu, C., Vantzos, O., Sminchisescu, C.: Training deep networks with structured layers by matrix backpropagation. arXiv preprint arXiv:1509.07838 (2015)
Kistler, M., Bonaretti, S., Pfahrer, M., Niklaus, R., Büchler, P.: The virtual skeleton database: an open access repository for biomedical research and collaboration. J. Med. Internet Res. 15(11), e245 (2013)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Lin, L., Bivard, A., Krishnamurthy, V., Levi, C.R., Parsons, M.W.: Whole-brain CT perfusion to quantify acute ischemic penumbra and core. Radiology 279(3), 876–887 (2016)
Maier, O., et al.: ISLES 2015-a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Med. Image Anal. 35, 250–269 (2017)
Mlynash, M., Eyngorn, I., Bammer, R., Moseley, M., Tong, D.C.: Automated method for generating the arterial input function on perfusion-weighted MR imaging: validation in patients with stroke. Am. J. Neuroradiol. 26(6), 1479–1486 (2005)
Mouridsen, K., Christensen, S., Gyldensted, L., Østergaard, L.: Automatic selection of arterial input function using cluster analysis. Magn. Reson. Med.: Off. J. Int. Soc. Magn. Reson. Med. 55(3), 524–531 (2006)
Murase, K., Kikuchi, K., Miki, H., Shimizu, T., Ikezoe, J.: Determination of arterial input function using fuzzy clustering for quantification of cerebral blood flow with dynamic susceptibility contrast-enhanced mr imaging. J. Magn. Reson. Imaging: Off. J. Int. Soc. Magn. Reson. Med. 13(5), 797–806 (2001)
Murphy, B., Chen, X., Lee, T.Y.: Serial changes in CT cerebral blood volume and flow after 4 hours of middle cerebral occlusion in an animal model of embolic cerebral ischemia. Am. J. Neuroradiol. 28(4), 743–749 (2007)
Papadopoulo, T., Lourakis, M.I.A.: Estimating the Jacobian of the singular value decomposition: theory and applications. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 554–570. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45054-8_36
Peruzzo, D., Bertoldo, A., Zanderigo, F., Cobelli, C.: Automatic selection of arterial input function on dynamic contrast-enhanced MR images. Comput. Methods Programs Biomed. 104(3), e148–e157 (2011)
Rausch, M., Scheffler, K., Rudin, M., Radü, E.: Analysis of input functions from different arterial branches with gamma variate functions and cluster analysis for quantitative blood volume measurements. Magn. Reson. Imaging 18(10), 1235–1243 (2000)
Robben, D., Suetens, P.: Perfusion parameter estimation using neural networks and data augmentation. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11383, pp. 439–446. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11723-8_44
Shi, L., et al.: Automatic detection of arterial input function in dynamic contrast enhanced MRI based on affinity propagation clustering. J. Magn. Reson. Imaging 39(5), 1327–1337 (2014)
Sourbron, S., Luypaert, R., Morhard, D., Seelos, K., Reiser, M., Peller, M.: Deconvolution of bolus-tracking data: a comparison of discretization methods. Phys. Med. Biol. 52(22), 6761 (2007)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Townsend, J.: Differentiating the singular value decomposition. Technical Report 2016 (2016). https://j-towns.github.io/papers/svd-derivative
Vagal, A., et al.: Automated CT perfusion imaging for acute ischemic stroke: pearls and pitfalls for real-world use. Neurology 93(20), 888–898 (2019)
Acknowledgements
This project received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement TRABIT No 765148. EDLR, DR and DMS are employees of icometrix. DR is supported by an innovation mandate of Flanders Innovation & Entrepreneurship (VLAIO).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
de la Rosa, E., Robben, D., Sima, D.M., Kirschke, J.S., Menze, B. (2020). Differentiable Deconvolution for Improved Stroke Perfusion Analysis. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12267. Springer, Cham. https://doi.org/10.1007/978-3-030-59728-3_58
Download citation
DOI: https://doi.org/10.1007/978-3-030-59728-3_58
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59727-6
Online ISBN: 978-3-030-59728-3
eBook Packages: Computer ScienceComputer Science (R0)
