Keywords: anatomical landmarks, localization, heatmap regression, spatial configuration
TL;DR: We show that the amount of required training data for landmark localization can be reduced with our proposed two-component CNN architecture, which follows the idea of handcrafted graphical models.
Abstract: In many medical image analysis applications, often only a limited amount of training data is available, which makes training of convolutional neural networks (CNNs) challenging. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the spatial configuration of landmarks. In our experimental evaluation, we show that the proposed SCN outperforms related methods in terms of landmark localization error on size-limited datasets.
Code Of Conduct: I have read and accept the code of conduct.
Remove If Rejected: Remove submission from public view if paper is rejected.