Automatic Cranial Defect Reconstruction with Self-Supervised Deep Deformable Masked Autoencoders
This work addresses the costly and time-consuming manual design of cranial implants for patients with cranial injuries, though it is incremental as it builds on existing self-supervised learning techniques.
The authors tackled the problem of automating cranial defect reconstruction for personalized implants by proposing a self-supervised masked autoencoder approach, which improved performance on SkullBreak and SkullFix datasets compared to state-of-the-art methods and enabled real-time reconstruction.
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.