Multi-input segmentation of damaged brain in acute ischemic stroke patients using slow fusion with skip connection
DOI:
https://doi.org/10.7557/18.6223Keywords:
Acute ischemic stroke, Transfer learning, image segmentationAbstract
Time is a fundamental factor during stroke treat-ments. A fast, automatic approach that segmentsthe ischemic regions helps treatment decisions. In clinical use today, a set of color-coded parametric maps generated from computed tomography per-fusion (CTP) images are investigated manually to decide a treatment plan. We propose an automatic method based on a neural network using a set of parametric maps to segment the two ischemic regions (core and penumbra) in patients affected by acute ischemic stroke. Our model is based on a convolution-deconvolution bottleneck structure with multi-input and slow fusion. A loss function based on the focal Tversky index addresses the data imbalance issue. The proposed architecture demon-strates effective performance and results comparable to the ground truth annotated by neuroradiologists. A Dice coefficient of 0.81 for penumbra and 0.52 for core over the large vessel occlusion test set is achieved. The full implementation is available at: https://git.io/JtFGb.
References
N. Abraham and N. M. Khan. A novel focal tversky loss function with improved attention u-net for lesion segmentation. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pages 683–687. IEEE, 2019. doi: 10.1109/ISBI.2019.8759329.
S. M. Abulnaga and J. Rubin. Ischemic stroke lesion segmentation in ct perfusion scans using pyramid pooling and focal loss. In International MICCAI Brainlesion Workshop, pages 352–363. Springer, 2018. doi: 10.1007/ 978-3-030-11723-8 36.
L. Alzubaidi, M. Al-Amidie, A. Al-Asadi, A. J. Humaidi, O. Al-Shamma, M. A. Fadhel, J. Zhang, J. Santamarıa, and Y. Duan. Novel transfer learning approach for medical imaging with limited labeled data. Cancers, 13(7): 1590, 2021. doi: 10.3390/cancers13071590. video classification with convolutional neural networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 1725–1732, 2014. doi: 10.1109/ CVPR.2014.223.
A. S. Kasasbeh, S. Christensen, M. W. Parsons, B. Campbell, G. W. Albers, and M. G. Lansberg. Artificial neural network computer tomography perfusion prediction of ischemic core. Stroke, 50(6):1578–1581, 2019. doi: 10.1161/STROKEAHA.118.022649.
D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. doi: 10.48550/arXiv. 1412.6980.
K. Kurz, G. Ringstad, A. Odland, R. Advani, E. Farbu, and M. Kurz. Radiological imaging in acute ischaemic stroke. European journal of neurology, 23:8–17, 2016. doi: 10.1111/ene. 12849.
J. Carreira and A. Zisserman. Quo vadis, action recognition? a new model and the kinetics dataset. In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. doi: 10.1109/CVPR.2017.502.
A. Clerigues, S. Valverde, J. Bernal, J. Freixenet, A. Oliver, and X. Llado. Acute ischemic stroke lesion core segmentation in ct perfusion images using fully convolutional neural networks. Computers in Biology and Medicine, 115:103487, 2019. doi: 10.1016/j.compbiomed. 2019.103487.
E. S. O. E. E. Committee, E. W. Committee, et al. Guidelines for management of ischaemic stroke and transient ischaemic attack 2008. Cerebrovascular diseases, 25(5):457–507, 2008. doi: 10.1159/000131083.
K. Gadzicki, R. Khamsehashari, and C. Zetzsche. Early vs late fusion in multimodal convolutional neural networks. In 2020 IEEE 23rd International Conference on Information Fusion (FUSION), pages 1–6. IEEE, 2020. doi: 10.23919/FUSION45008.2020.9190246.
A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, and L. Fei-Fei. Large-scale
R. LaLonde, I. Tanner, K. Nikiforaki, G. Z. Papadakis, P. Kandel, C. W. Bolan, M. B. Wallace, and U. Bagci. Inn: inflated neural networks for ipmn diagnosis. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 101–109. Springer, 2019. doi: 10.1007/ 978-3-030-32254-0 12.
C. Lucas, A. Kemmling, A. M. Mamlouk, and M. P. Heinrich. Multi-scale neural network for automatic segmentation of ischemic strokes on acute perfusion images. In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pages 1118–1121. IEEE, 2018. doi: 10.1109/ISBI.2018.8363767.
Ø. Meinich-Bache, S. L. Austnes, K. Engan, I. Austvoll, T. Eftestøl, H. Myklebust, S. Kusulla, H. Kidanto, and H. Ersdal. Activity recognition from newborn resuscitation videos. IEEE journal of biomedical and health informatics, 24(11):3258–3267, 2020. doi: 10. 1109/JBHI.2020.2978252.
B. Murphy, A. Fox, D. Lee, D. Sahlas, S. Black, M. Hogan, S. Coutts, A. Demchuk, M. Goyal, R. Aviv, et al. Identification of penumbra and infarct in acute ischemic stroke using computed tomography perfusion– derived blood flow and blood volume measurements. Stroke, 37(7):1771–1777, 2006. doi: 10.1161/01.STR.0000227243.96808.53.
S. Ojaghihaghighi, S. S. Vahdati, A. Mikaeilpour, and A. Ramouz. Comparison of neurological clinical manifestation in patients with hemorrhagic and ischemic stroke. World journal of emergency medicine, 8(1):34, 2017. doi: 10.5847/wjem.j.1920-8642.2017.01.006.
O. Ronneberger, P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer, 2015. doi: 10.1007/ 978-3-319-24574-4 28.
all-cause mortality, and cause-specific mortality for 249 causes of death, 1980–2015: a systematic analysis for the global burden of disease study 2015. The lancet. doi: 10.1016/ S0140-6736(16)31012-1.
R. Wetteland, K. Engan, T. Eftestøl, V. Kvikstad, and E. A. Janssen. A multiscale approach for whole-slide image segmentation of five tissue classes in urothelial carcinoma slides. Technology in Cancer Research & Treatment, 19, 2020. doi: 10.1177/ 1533033820946787. Springer, 2017. doi: 10.1007/978-3-319-67389-9 44.
L. Tomasetti, K. Engan, M. Khanmohammadi, and K. D. Kurz. Cnn based segmentation of infarcted regions in acute cerebral stroke patients from computed tomography perfusion imaging. In Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, pages 1–8, 2020. doi: 10.1145/ 3388440.3412470.
L. Tomasetti, L. J. Høllesli, K. Engan, K. D. Kurz, M. W. Kurz, and M. Khanmohammadi. Machine learning algorithms vs. thresholding to segment ischemic regions in patients with acute ischemic stroke. IEEE Journal of Biomedical and Health Informatics, pages 1–1, 2021. doi: 10.1109/JBHI.2021.3097591.
H. Wang, M. Naghavi, C. Allen, R. M. Barber, Z. A. Bhutta, A. Carter, D. C. Casey, F. J. Charlson, A. Z. Chen, M. M. Coates, et al. Global, regional, and national life expectancy,
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Luca Tomasetti, Mahdieh Khanmohammadi, Kjersti Engan, Liv Jorunn Høllesli, Kathinka Dæhli Kurz
This work is licensed under a Creative Commons Attribution 4.0 International License.
