Abstract
Perfusion CT is widely used in acute ischemic stroke to determine eligibility for acute treatment, by defining an ischemic core and penumbra. In this work, we propose a novel way of building on prior information for the automatic prediction and segmentation of stroke lesions. To this end, we reformulate the task to identify differences from a prior segmentation by extending a three-dimensional Attention Gated Unet with a skip connection allowing only an unchanged prior to bypass most of the network. We show that this technique improves results obtained by a baseline Attention Gated Unet on both the Geneva Stroke Dataset and the ISLES 2018 dataset.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
ISLES: Ischemic Stroke Lesion Segmentation Challenge (2018). http://www.isles-challenge.org/
Albers, G.W., et al.: Thrombectomy for Stroke at 6 to 16 Hours with Selection by Perfusion Imaging. New England J. Med. 378(8), 708–718 (2018). https://doi.org/10.1056/NEJMoa1713973. Massachusetts Medical Society, publisher eprint
Shalini, A., et al.: Cerebral blood flow predicts the infarct core. Stroke 50(10), 2783–2789 (2019). https://doi.org/10.1161/STROKEAHA.119.026640. https://www.ahajournals.org/doi/10.1161/STROKEAHA.119.026640. Publisher: American Heart Association
Belkin, M., Hsu, D., Ma, S., Mandal, S.: Reconciling modern machine learning practice and the bias-variance trade-off. arXiv:1812.11118 [cs, stat] (2019)
Benjamin Emelia, J., et al.: Heart disease and stroke statistics–2019 update: a report from the American Heart Association. Circulation, 139(10), e56–e528 (2019). https://doi.org/10.1161/CIR.0000000000000659. https://www.ahajournals.org/doi/10.1161/CIR.0000000000000659. Publisher: American Heart Association
Campbell, B.C.V., Khatri, P.: Stroke. Lancet 396(10244), 129–142 (2020). https://doi.org/10.1016/S0140-6736(20)31179-X. https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(20)31179-X/abstract. Publisher: Elsevier
Campbell, B.C.V., et al.: Cerebral blood flow is the optimal CT perfusion parameter for assessing infarct core. Stroke, 42(12), 3435–3440 (2011). https://doi.org/10.1161/STROKEAHA.111.618355. https://www.ahajournals.org/doi/10.1161/strokeaha.111.618355. Publisher: American Heart Association
Carrera, E., Wintermark, M.: Imaging-based selection of patients for acute stroke treatment: is it ready for prime time? Neurology 88(24), 2242–2243 (2017). https://doi.org/10.1212/WNL.0000000000004051
Chen, Y., Li, Y., Zheng, Y.: Ensembles of modalities fused model for ischemic stroke lesion segmentation, p. 1
Clèrigues, A., Valverde, S., Bernal, J., Freixenet, J., Oliver, A., Lladó, X.: Acute ischemic stroke lesion core segmentation in CT perfusion images using fully convolutional neural networks. Comput. Biol. Med. 115, 103487 (2019). https://doi.org/10.1016/j.compbiomed.2019.103487. http://www.sciencedirect.com/science/article/pii/S0010482519303555
Jenkinson, M., Pechaud, M., Smith, S.: BET2 - MR-Based Estimation of Brain, Skull and Scalp Surfaces, p. 1
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) (2013). https://doi.org/10.2196/jmir.2930. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3841349/
Klug, J., et al.: Integrating regional perfusion CT information to improve prediction of infarction after stroke. J. Cerebr. Blood Flow Metab. (2020). https://doi.org/10.1177/0271678X20924549. https://journals.sagepub.com/doi/10.1177/0271678X20924549. Publisher: SAGE PublicationsSage UK: London, England
Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. arXiv:1409.5185 [cs, stat] (2014)
Liu, P.: Stroke lesion segmentation with 2D novel CNN pipeline and novel loss function. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11383, pp. 253–262. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11723-8_25
Lucas, C., Aulmann, L., Kemmling, A., Madany Mamlouk, A., Heinrich, M.: Estimation of the principal ischaemic stroke growth directions for predicting tissue outcomes, pp. 69–79 (2020). https://doi.org/10.1007/978-3-030-46640-4_7
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). https://doi.org/10.1016/j.media.2016.07.009
Kim, M., Patrick, T., Greg, Z.: Artificial intelligence applications in stroke. Stroke 51(8), 2573–2579 (2020). https://doi.org/10.1161/STROKEAHA.119.027479. https://www.ahajournals.org/doi/10.1161/STROKEAHA.119.027479. Publisher: American Heart Association
Muschelli, J., Ullman, N.L., Mould, W.A., Vespa, P., Hanley, D.F., Crainiceanu, C.M.: Validated automatic brain extraction of head CT images. Neuroimage 114, 379–385 (2015). https://doi.org/10.1016/j.neuroimage.2015.03.074
Nielsen, A., Hansen, M.B., Tietze, A., Mouridsen, K.: Prediction of tissue outcome and assessment of treatment effect in acute ischemic stroke using deep learning. Stroke 49(6), 1394–1401 (2018). https://doi.org/10.1161/STROKEAHA.117.019740. https://www.ahajournals.org/doi/full/10.1161/strokeaha.117.019740. Publisher: American Heart Association
Nogueira, R.G., et al.: DAWN trial investigators: thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct. N. Engl. J. Med. 378(1), 11–21 (2018). https://doi.org/10.1056/NEJMoa1706442
Nosrati, M.S., Hamarneh, G.: Incorporating prior knowledge in medical image segmentation: a survey. arXiv:1607.01092 [cs] (2016)
Oktay, O., et al.: Anatomically constrained neural networks (ACNNs): application to cardiac image enhancement and segmentation. IEEE Trans. Med. Imaging 37(2), 384–395 (2018). https://doi.org/10.1109/TMI.2017.2743464. Conference Name: IEEE Transactions on Medical Imaging
Oktay, O., et al.: Attention U-Net: learning where to look for the pancreas, p. 10
Péez-García, F., Sparks, R., Ourselin, S.: TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. arXiv:2003.04696 [cs, eess, stat] (2020)
Robben, D., et al.: Prediction of final infarct volume from native CT perfusion and treatment parameters using deep learning. Med. Image Anal. 59, 101589 (2020). https://doi.org/10.1016/j.media.2019.101589. http://www.sciencedirect.com/science/article/pii/S136184151930129X
Schlemper, J., et al.: Attention gated networks: learning to leverage salient regions in medical images. Med. Image Anal. 53, 197–207 (2019). https://doi.org/10.1016/j.media.2019.01.012. http://www.sciencedirect.com/science/article/pii/S1361841518306133
Song, T., Huang, N.: Integrated extractor, generator and segmentor for ischemic stroke lesion segmentation. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11383, pp. 310–318. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11723-8_31
Straka, M., Albers, G.W., Bammer, R.: Real-time diffusion-perfusion mismatch analysis in acute stroke. J. Magn. Reson. Imaging: JMRI, 32(5), 1024–1037 (2010). https://doi.org/10.1002/jmri.22338. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2975404/
Yu, Y., et al.: Use of deep learning to predict final ischemic stroke lesions from initial magnetic resonance imaging. JAMA Netw. Open 3(3), e200772–e200772 (2020). https://doi.org/10.1001/jamanetworkopen.2020.0772. https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2762679. Publisher: American Medical Association
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_49
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Klug, J., Leclerc, G., Dirren, E., Preti, M.G., Van De Ville, D., Carrera, E. (2021). Bayesian Skip Net: Building on Prior Information for the Prediction and Segmentation of Stroke Lesions. In: Crimi, A., Bakas, S. (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2020. Lecture Notes in Computer Science(), vol 12658. Springer, Cham. https://doi.org/10.1007/978-3-030-72084-1_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-72084-1_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72083-4
Online ISBN: 978-3-030-72084-1
eBook Packages: Computer ScienceComputer Science (R0)