search

neuronets / nobrainer

A framework for developing neural network models for 3D image processing.
Other
159 stars 45 forks source link

SpatialConfiguration-Net #111

Open kaczmarj opened 4 years ago

kaczmarj commented 4 years ago

Consider implementing https://arxiv.org/abs/1908.00748

Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization

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.

Aakanksha-Rana commented 4 years ago

Another Model to add ASD-NET (MICCAI'18): github page https://github.com/ginobilinie/asdnet