Latent Shape Constraint for Anatomical Landmark Detection on Spine Radiographs
Florian Kordon, Andreas Maier, Holger Kunze
Friedrich-Alexander Universität Erlangen-Nürnberg, Lehrstuhl für Mustererkennung
Vertebral corner points are frequently used landmarks for a vast variety of orthopedic and trauma surgical applications. Algorithmic approaches that are designed to automatically detect them on 2D radiographs have to cope with varying image contrast, high noise levels, and superimposed soft tissue. To enforce an anatomically correct landmark configuration in presence of these limitations, this study investigates a regularization technique based on a data-driven shape encoding of the spine. A contractive PointNet autoencoder is used to map numerical landmark coordinate representations onto a low-dimensional shape manifold. A distance norm between prediction and ground truth encodings then serves as an additional regularization loss during optimization. The method is compared and evaluated on the SpineWeb16 dataset. Small improvements can be observed, recommending further analysis of the encoding design and composite cost function.
The author has not agreed to a public release of their video.