Abstract
Patient-specific implant (PSI) design is a challenging task and requires a specialist, who will spend a significant amount of time using computer aided design tools for implant creation, since patient-specific skull features have to be accounted for. Automating this process could potentially allow intraoperative PSI availability at a relatively low cost. This work proposes to use a 3D Sparse Convolutional Neural Network (SCNN) to reconstruct complete skulls given defective skulls (i.e., skull shape completion) and extract implants by taking the difference between them. With the help of recently published methods for sparse convolutions, it is now possible to avoid the downsampling of the whole skull volume, which is required for conventional dense 3D CNN applications proposed previously. Thus, the SCNN-based approach allows to preserve the original skull geometry. The proposed pipeline includes a supervised SCNN autoencoder network with data preprocessing steps, which further exploit the sparse nature of a skull scan. The best setup in our experiments achieves a Dice Score (DS) of 85.4%, a Border Dice Score of 94.6%, Hausdorff Distance (HD) of 4.91 and 95th percentile HD of 2.64 on the dataset for Task 3 of the AutoImplant 2021 challenge (https://autoimplant2021.grand-challenge.org/). The results are comparable with a dense CNN counterpart which has significantly more parameters and requires downsampling and cropping of the skull image on 6GB GPUs. The code is publicly available at https://github.com/akroviakov/SparseSkullCompletion.
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
Notes
- 1.
The work from J. Li. et al. [4] proposed a fast and memory-efficient nearest neighbor search solution for skull reconstruction, taking the advantage of the binariness and spatial sparsity of the skull images.
- 2.
Not to be confused with the sparse convolutional neural networks proposed in [5], which focused on model sparsity instead of data sparsity as in our work.
References
Li, J., et al.: Autoimplant 2020-first miccai challenge on automatic cranial implant design. IEEE Trans. Med. Imag. 40, 2329–2342 (2021)
Li, J., et al.: Automatic skull defect restoration and cranial implant generation for cranioplasty. Med. Image Anal. 73, 102171 (2021)
Li, J., Pepe, A., Gsaxner, C., Campe, G., Egger, J.: A baseline approach for AutoImplant: the MICCAI 2020 cranial implant design challenge. In: Syeda-Mahmood, T., et al. (eds.) CLIP/ML-CDS -2020. LNCS, vol. 12445, pp. 75–84. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60946-7_8
Li, J., Pepe, A., Gsaxner, C., Jin, Y., Egger, J.: Learning to rearrange voxels in binary segmentation masks for smooth manifold triangulation. arXiv preprint arXiv:2108.05269 (2021)
Liu, B., Wang, M., Foroosh, H., Tappen, M., Pensky, M.: Sparse convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 806–814 (2015)
Choy, C., Gwak, J., Savarese, S.: 4D Spatio-temporal convnets: Minkowski convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3075–3084 (2019)
Li, J., Egger, J.: Dataset descriptor for the AutoImplant cranial implant design challenge. In: Li, J., Egger, J. (eds.) AutoImplant 2020. LNCS, vol. 12439, pp. 10–15. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64327-0_2
Graham, B., van der Maaten, L.: Submanifold sparse convolutional networks. arXiv preprint arXiv:1706.01307 (2017)
Gwak, J., Choy, C.B., Savarese, S.: Generative sparse detection networks for 3D single-shot object detection. In: European Conference on Computer Vision (2020)
Li, C., Yang, Y., Feng, M., Chakradhar, S., Zhou, H.: Optimizing memory efficiency for deep convolutional neural networks on GPUs. In: SC’16: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 633–644. IEEE (2016)
Kodym, O., Španěl, M., Herout, A.: Cranial defect reconstruction using cascaded CNN with alignment (2020)
Matzkin, E., Newcombe, V., Glocker, B., Ferrante, E.: Cranial implant design via virtual craniectomy with shape prior (2020)
Acknowledgement
This work was supported by the following funding agencies:
\(\bullet \) CAMed (COMET K-Project 871132, see also https://www.medunigraz.at/camed/), which is funded by the Austrian Federal Ministry of Transport, Innovation and Technology (BMVIT) and the Austrian Federal Ministry for Digital and Economic Affairs (BMDW), and the Styrian Business Promotion Agency (SFG);
\(\bullet \) The Austrian Science Fund (FWF) KLI 678-B31 (enFaced).
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
Kroviakov, A., Li, J., Egger, J. (2021). Sparse Convolutional Neural Network for Skull Reconstruction. In: Li, J., Egger, J. (eds) Towards the Automatization of Cranial Implant Design in Cranioplasty II. AutoImplant 2021. Lecture Notes in Computer Science(), vol 13123. Springer, Cham. https://doi.org/10.1007/978-3-030-92652-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-92652-6_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92651-9
Online ISBN: 978-3-030-92652-6
eBook Packages: Computer ScienceComputer Science (R0)
