Abstract
Brain midline shift is often caused by various clinical conditions such as high intracranial pressure, which can be deadly. To facilitate clinical evaluation, automated methods have been proposed to classify whether midline shift is severe or not, e.g., larger than 5 mm away from the ideal midline. There are only limited methods using landmark or symmetry, attempting to provide more intuitive results such as midline delineation. However, landmark- or symmetry-based methods could be easily affected by anatomical variability and large brain deformations. In this study, we formulated the midline delineation as a skeleton extraction task and proposed a novel regression-based line detection network (RLDN) for the robust midline delineation especially in largely deformed brains. Basically, the proposed method includes three parts: (1) multi-scale line detection, (2) weighted line integration, and (3) regression-based refinement. The first two parts were used to capture high-level semantic and low-level detailed information to extract deformed midline, while the last part was utilized to regress more accurate midline positions. We validated the RLDN on 100 training and 28 testing subjects with a mean midline shift of 7 mm and the maximum shift of 16 mm (induced by hemorrhage). Experimental results show that our proposed method achieves state-of-the-art accuracy with a mean line difference of \(1.17\pm 0.72\) mm and F1-score of 0.78 from manual delineations. Our proposed robust midline delineation method is also beneficial for other cases such as midline deformation from tumor, traumatic brain injury, and abscess.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, M., et al.: Automatic estimation of midline shift in patients with cerebral glioma based on enhanced voigt model and local symmetry. Australas. Phys. Eng. Sci. Med. 38(4), 627–641 (2015)
Chilamkurthy, S., et al.: Development and validation of deep learning algorithms for detection of critical findings in head CT scans. arXiv preprint arXiv:1803.05854 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Ke, W., Chen, J., Jiao, J., Zhao, G., Ye, Q.: SRN: side-output residual network for object symmetry detection in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1068–1076 (2017)
Liao, C.C., Xiao, F., Wong, J.M., Chiang, I.J.: Automatic recognition of midline shift on brain CT images. Comput. Biol. Med. 40(3), 331–339 (2010)
Liu, R., et al.: Automatic detection and quantification of brain midline shift using anatomical marker model. Comput. Med. Imaging Graph. 38(1), 1–14 (2014)
Liu, Y., Cheng, M.M., Hu, X., Wang, K., Bai, X.: Richer convolutional features for edge detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3000–3009 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Xie, S., Tu, Z.: Holistically-nested edge detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1395–1403 (2015)
Yang, F., Li, X., Cheng, H., Guo, Y., Chen, L., Li, J.: Multi-scale bidirectional FCN for object skeleton extraction. In: Thirty-Second AAAI Conference on Artificial Intelligence, pp. 7461–7468 (2018)
Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: LIFT: learned invariant feature transform. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 467–483. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_28
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881–2890 (2017)
Zhao, K., Shen, W., Gao, S., Li, D., Cheng, M.M.: HI-FI: Hierarchical feature integration for skeleton detection. arXiv preprint arXiv:1801.01849 (2018)
Acknowledgements
This work was partially supported by the National Key Research and Development Program of China (2018YFC0116400).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wei, H. et al. (2019). Regression-Based Line Detection Network for Delineation of Largely Deformed Brain Midline. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11766. Springer, Cham. https://doi.org/10.1007/978-3-030-32248-9_93
Download citation
DOI: https://doi.org/10.1007/978-3-030-32248-9_93
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32247-2
Online ISBN: 978-3-030-32248-9
eBook Packages: Computer ScienceComputer Science (R0)