Fast Medical Shape Reconstruction via Meta-learned Implicit Neural Representations
This work addresses the need for fast and generalizable anatomical shape reconstruction in clinical settings like surgical planning, though it is incremental as it builds on existing implicit neural methods with meta-learning for optimization.
The paper tackled the problem of slow and poorly generalizing medical shape reconstruction from medical images by using meta-learned implicit neural representations, achieving an order of magnitude reduction in inference time while maintaining high accuracy across multiple datasets and input configurations.
Efficient and fast reconstruction of anatomical structures plays a crucial role in clinical practice. Minimizing retrieval and processing times not only potentially enhances swift response and decision-making in critical scenarios but also supports interactive surgical planning and navigation. Recent methods attempt to solve the medical shape reconstruction problem by utilizing implicit neural functions. However, their performance suffers in terms of generalization and computation time, a critical metric for real-time applications. To address these challenges, we propose to leverage meta-learning to improve the network parameters initialization, reducing inference time by an order of magnitude while maintaining high accuracy. We evaluate our approach on three public datasets covering different anatomical shapes and modalities, namely CT and MRI. Our experimental results show that our model can handle various input configurations, such as sparse slices with different orientations and spacings. Additionally, we demonstrate that our method exhibits strong transferable capabilities in generalizing to shape domains unobserved at training time.