Abstract
Dice loss is the most widely used loss function in deep learning methods for unbalanced medical image segmentation. The main limitation of Dice loss is that it weighs different parts of the to-be-segmented region of interest (ROI) equally, which is inappropriate given that the fuzzy boundary is typically more challenging to segment than central parts. A recently-proposed boundary loss weighs different parts of an ROI according to their distances to the ROI’s boundary, thus providing complementary information to Dice loss. However, boundary loss can not be directly applied to patch-based 3D convolutional neural networks (CNNs), significantly limiting its utility. In this paper, we proposed and validated a two-stage 3D+2D framework making use of 3D CNN for spatial information extraction and also boundary loss to complement the typically-used generalized Dice loss, for segmenting stroke lesions from magnetic resonance (MR) images. A 3D patch-based fully convolutional network was firstly used to learn local spatial features. And then the to-be-segmented MR image and the probability map predicted from the trained 3D model were sliced and fed into a 2D network with a joint loss combining boundary loss and generalized Dice loss. We evaluated the proposed method on a publicly-available dataset consisting of 229 T1-weighted MR images. The proposed approach yielded an average Dice score of 56.25% and an average Hausdorff distance of 27.14 mm, performing much better than existing state-of-the-art stroke lesion segmentation methods.
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
Similar content being viewed by others
References
Johnson, W., Onuma, O., Owolabi, M., et al.: Stroke: a global response is needed. Bull. World Health Organ. 94(9), 634 (2016)
Pinto, A., Mckinley, R., Alves, V., et al.: Stroke lesion outcome prediction based on MRI imaging combined with clinical information. Front. Neurol. 9, 1060 (2018)
Cramer, S.C., Wolf, S.L., Adams Jr., H.P., et al.: Stroke recovery and rehabilitation research: issues, opportunities, and the National Institutes of Health StrokeNet. Stroke 48(3), 813–819 (2017)
Burke Quinlan, E., Dodakian, L., See, J., et al.: Neural function, injury, and stroke subtype predict treatment gains after stroke. Ann. Neuro. 77(1), 132–145 (2015)
Crinion, J., Holland, A.L., Copland, D.A., Thompson, C.K., Hillis, A.E.: Neuroimaging in aphasia treatment research: quantifying brain lesions after stroke. Neuroimage 73, 208–214 (2013)
Tipirneni, S.A., Christensen, S., Straka, M., et al.: Prediction of final infarct volume on subacute MRI by quantifying cerebral edema in ischemic stroke. J. Cereb. Blood Flow Metab. 37(8), 3077–3084 (2017)
Ito, K.L., Kim, H., Liew, S.L.: A comparison of automated lesion segmentation approaches for chronic stroke T1-weighted MRI data. Hum. Brain Mapp. 40(16), 4669–4685 (2019)
Seghier, M.L., Ramlackhansingh, A., Crinion, J., Leff, A.P., Price, C.J.: Lesion identification using unified segmentation-normalisation models and fuzzy clustering. NeuroImage 41(4), 1253–1266 (2008)
Pustina, D., Coslett, H.B., Turkeltaub, P.E., Tustison, N., Schwartz, M.F., Avants, B.: Automated segmentation of chronic stroke lesions using LINDA: lesion identification with neighborhood data analysis. Hum. Brain Mapp. 37(4), 1405–1421 (2016)
De Haan, B., Clas, P., Juenger, H., Wilke, M., Karnath, H.O.: Fast semi-automated lesion demarcation in stroke. NeuroImage Clin. 9, 69–74 (2015)
Griffis, J.C., Allendorfer, J.B., Szaflarski, J.P.: Voxel-based Gaussian naïve Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans. J. Neurosci. Methods 257, 97–108 (2016)
Qi, K., et al.: X-Net: brain stroke lesion segmentation based on depthwise separable convolution and long-range dependencies. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11766, pp. 247–255. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32248-9_28
Zhou, Y., Huang, W., Dong, P., et al.: D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation. IEEE/ACM Trans. Comput. Biol. Bioinform (2019)
Xue, Y., Farhat, F.G., Boukrina, O., et al.: A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images. NeuroImage Clin. 25, 102118 (2020)
Yang, H., et al.: CLCI-Net: cross-level fusion and context inference networks for lesion segmentation of chronic stroke. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11766, pp. 266–274. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32248-9_30
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
Wu, J., Zhang, Y., Tang, X.: A multi-atlas guided 3D fully convolutional network for MRI-based subcortical segmentation. In: ISBI, pp. 705–708. IEEE (2019)
Maier, O., Menze, B.H., von der Gablentz, J., Häni, L., et al.: ISLES 2015-A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Med. Image Anal. 35, 250–269 (2017)
Chen, H., Dou, Q., Yu, L., Qin, J., Heng, P.A.: VoxResNet: deep voxelwise residual networks for brain segmentation from 3D MR images. NeuroImage 170, 446–455 (2018)
Zhang, Y., Wu, J., Liu, Y., Chen, Y., Wu, X., Tang, X.: MI-UNet: multi-inputs UNet incorporating brain parcellation for stroke lesion segmentation from T1-weighted magnetic resonance images. IEEE J. Biomed. Health Inform. (2020)
Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV, pp. 565–571. IEEE (2016)
Kervadec, H., Bouchtiba, J., Desrosiers, C., et al.: Boundary loss for highly unbalanced segmentation. In: MIDL, pp. 285–296 (2019)
Kamnitsas, K., Ledig, C., Newcombe, V.F., et al.: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61–78 (2017)
Dolz, J., Desrosiers, C., Ayed, I.B.: 3D fully convolutional networks for subcortical segmentation in MRI: a large-scale study. NeuroImage 170, 456–470 (2018)
Lian, C., Zhang, J., Liu, M., et al.: Multi-channel multi-scale fully convolutional network for 3D perivascular spaces segmentation in 7T MR images. Med. Image Anal. 46, 106–117 (2018)
Liew, S.L., Anglin, J.M., Banks, N.W., et al.: A large, open-source dataset of stroke anatomical brain images and manual lesion segmentations. Sci. Data 5, 180011 (2018)
Li, C., Sun, H., Liu, Z., Wang, M., Zheng, H., Wang, S.: Learning cross-modal deep representations for multi-modal MR image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 57–65. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_7
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NIPS, pp. 5998–6008 (2017)
Wu, J., Zhang, Y., Tang, X.: A joint 3D+2D fully convolutional framework for subcortical segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11766, pp. 301–309. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32248-9_34
Acknowledgement
This study was supported by the Shenzhen Basic Research Program (JCYJ20190809120205578), the National Key R&D Program of China (2017YFC0112404) and the National Natural Science Foundation of China (81501546).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, Y., Wu, J., Liu, Y., Chen, Y., Wu, E.X., Tang, X. (2020). A 3D+2D CNN Approach Incorporating Boundary Loss for Stroke Lesion Segmentation. In: Liu, M., Yan, P., Lian, C., Cao, X. (eds) Machine Learning in Medical Imaging. MLMI 2020. Lecture Notes in Computer Science(), vol 12436. Springer, Cham. https://doi.org/10.1007/978-3-030-59861-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-59861-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59860-0
Online ISBN: 978-3-030-59861-7
eBook Packages: Computer ScienceComputer Science (R0)
