Cranial Implant Prediction using Low-Resolution 3D Shape Completion and High-Resolution 2D Refinement
This work addresses the challenge of cranial implant design for medical applications, offering a solution that balances 3D understanding with computational feasibility, though it appears incremental as it builds on existing deep learning methods.
The paper tackles the problem of designing cranial implants by proposing a two-stage network that combines low-resolution 3D shape completion with high-resolution 2D refinement to predict high-resolution 3D implants, achieving accurate results in terms of dice-score and Hausdorff distance.
Designing of a cranial implant needs a 3D understanding of the complete skull shape. Thus, taking a 2D approach is sub-optimal, since a 2D model lacks a holistic 3D view of both the defective and healthy skulls. Further, loading the whole 3D skull shapes at its original image resolution is not feasible in commonly available GPUs. To mitigate these issues, we propose a fully convolutional network composed of two subnetworks. The first subnetwork is designed to complete the shape of the downsampled defective skull. The second subnetwork upsamples the reconstructed shape slice-wise. We train the 3D and 2D networks together end-to-end, with a hierarchical loss function. Our proposed solution accurately predicts a high-resolution 3D implant in the challenge test case in terms of dice-score and the Hausdorff distance.