Automatic Cranial Defect Reconstruction with Self-Supervised Deep Deformable Masked Autoencoders (2404.13106v2)
Abstract: Thousands of people suffer from cranial injuries every year. They require personalized implants that need to be designed and manufactured before the reconstruction surgery. The manual design is expensive and time-consuming leading to searching for algorithms whose goal is to automatize the process. The problem can be formulated as volumetric shape completion and solved by deep neural networks dedicated to supervised image segmentation. However, such an approach requires annotating the ground-truth defects which is costly and time-consuming. Usually, the process is replaced with synthetic defect generation. However, even the synthetic ground-truth generation is time-consuming and limits the data heterogeneity, thus the deep models' generalizability. In our work, we propose an alternative and simple approach to use a self-supervised masked autoencoder to solve the problem. This approach by design increases the heterogeneity of the training set and can be seen as a form of data augmentation. We compare the proposed method with several state-of-the-art deep neural networks and show both the quantitative and qualitative improvement on the SkullBreak and SkullFix datasets. The proposed method can be used to efficiently reconstruct the cranial defects in real time.
- Michael C. Dewan et al., “Global neurosurgery: the current capacity and deficit in the provision of essential neurosurgical care. Executive Summary of the Global Neurosurgery Initiative at the Program in Global Surgery and Social Change,” Journal of Neurosurgery, vol. 130, no. 4, pp. 1055–1064, 2019.
- Jianning Li et al., “AutoImplant 2020-First MICCAI Challenge on Automatic Cranial Implant Design,” IEEE Transactions on Medical Imaging, vol. 40, no. 9, pp. 2329–2342, 2021.
- Jianning Li et al., “Towards clinical applicability and computational efficiency in automatic cranial implant design: An overview of the autoimplant 2021 cranial implant design challenge,” Medical Image Analysis, vol. 88, pp. 102865, 2023.
- “Cranial Implant Prediction by Learning an Ensemble of Slice-Based Skull Completion Networks,” MICCAI 2021, Cranial Implant Design Challenge, vol. 13123 LNCS, pp. 95–104, 2021.
- H. Mahdi et al., “A U-Net Based System for Cranial Implant Design with Pre-processing and Learned Implant Filtering,” MICCAI 2021, Cranial Implant Design Challenge, vol. 13123 LNCS, pp. 63–79, 2021.
- “Improving the Automatic Cranial Implant Design in Cranioplasty by Linking Different Datasets,” MICCAI 2021, Cranial Implant Design Challenge, vol. 13123 LNCS, pp. 29–44, 2021.
- “Deep Learning Using Augmentation via Registration: 1st Place Solution to the AutoImplant 2020 Challenge,” MICCAI 2020, Cranial Implant Design Challenge, pp. 47–55, 2020.
- K. Kwarciak and M. Wodzinski, “Deep Generative Networks for Heterogeneous Augmentation of Cranial Defects,” Proceedings of the IEEE/CVR International Conference on Computer Vision - LIMIT Workshop, pp. 1066–1074, 2023.
- M. Wodzinski et al., “Deep learning-based framework for automatic cranial defect reconstruction and implant modeling,” Computer Methods and Programs in Biomedicine, vol. 226, pp. 1–13, 2022.
- M. Wodzinski et al., “High-Resolution Cranial Defect Reconstruction by Iterative, Low-Resolution, Point Cloud Completion Transformers,” International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 333–343, 2023.
- P. Friedrich et al., “Point Cloud Diffusion Models for Automatic Implant Generation,” International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 112–122, 2023.
- O. Kodym et al., “SkullBreak / SkullFix – Dataset for automatic cranial implant design and a benchmark for volumetric shape learning tasks,” Data in Brief, vol. 35, 2021.
- J. Li et al., “MUG500+: Database of 500 high-resolution healthy human skulls and 29 craniotomy skulls and implants,” Data in Brief, vol. 39, 2021.
- “Masked autoencoders are scalable vision learners,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 16000–16009.
- “Masked autoencoders as spatiotemporal learners,” Advances in neural information processing systems, vol. 35, pp. 35946–35958, 2022.
- “A survey on masked autoencoder for self-supervised learning in vision and beyond,” arXiv preprint arXiv:2208.00173, 2022.
- “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 2015, pp. 234–241.
- “Left-ventricle quantification using residual u-net,” in Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges: 9th International Workshop, STACOM 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers 9. Springer, 2019, pp. 371–380.
- “Unetr: Transformers for 3d medical image segmentation,” in Proceedings of the IEEE/CVF winter conference on applications of computer vision, 2022, pp. 574–584.
- “Swin UNETR: Swin transformers for semantic segmentation of brain tumors in mri images,” in International MICCAI Brainlesion Workshop. Springer, 2021, pp. 272–284.
- “Attention U-net: Learning where to look for the pancreas,” arXiv preprint arXiv:1804.03999, 2018.
- Andriy Myronenko, “3D MRI brain tumor segmentation using autoencoder regularization,” in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part II 4. Springer, 2019, pp. 311–320.
- M. Jorge Cardoso et al., “MONAI: An open-source framework for deep learning in healthcare,” Nov. 2022.
- “TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning,” Computer Methods and Programs in Biomedicine, vol. 208, pp. 106236, 2021.