S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences
This addresses the need for scalable SSMs in clinical applications by reducing reliance on expert annotations, though it is incremental in improving unsupervised techniques.
The paper tackles the problem of constructing statistical shape models (SSMs) without manual annotations by proposing an unsupervised method using deep geometric features and functional correspondences, achieving significant improvements in correspondence estimation for anatomical structures like the thyroid and heart.
Statistical shape models (SSMs) are an established way to represent the anatomy of a population with various clinically relevant applications. However, they typically require domain expertise, and labor-intensive landmark annotations to construct. We address these shortcomings by proposing an unsupervised method that leverages deep geometric features and functional correspondences to simultaneously learn local and global shape structures across population anatomies. Our pipeline significantly improves unsupervised correspondence estimation for SSMs compared to baseline methods, even on highly irregular surface topologies. We demonstrate this for two different anatomical structures: the thyroid and a multi-chamber heart dataset. Furthermore, our method is robust enough to learn from noisy neural network predictions, potentially enabling scaling SSMs to larger patient populations without manual segmentation annotation.