Abstract

Signed distance map (SDM) is a common representation of surfaces in medical image analysis and machine learning. The computational complexity of SDM for 3D parametric shapes is often a bottleneck in many applications, thus limiting their interest. In this paper, we propose a learning based SDM generation neural network which is demonstrated on a tridimensional cochlea shape model parameterized by 4 shape parameters. The proposed SDM Neural Network generates a cochlea signed distance map depending on four input parameters and we show that the deep learning approach leads to a 60 fold improvement in the time of computation compared to more classical SDM generation methods. Therefore, the proposed approach achieves a good trade-off between accuracy and efficiency.

Key Words: Deep Learning, Signed Distance Map, Cochlea Shape Model, Neural Network, Accuracy, Efficiency

Main points

• Proposes a learning based SDM generation neural network demonstrated on a tridimensional cochlea shape model parameterized by 4 shape parameters.

• The deep learning approach leads to a 60 fold improvement in the time of computation compared to more classical SDM generation methods.

• The proposed approach achieves a good trade-off between accuracy and efficiency.

Citation

@misc{wang2020deep,
      title={A Deep Learning based Fast Signed Distance Map Generation}, 
      author={Zihao Wang and Clair Vandersteen and Thomas Demarcy and Dan Gnansia and Charles Raffaelli and Nicolas Guevara and Hervé Delingette},
      year={2020},
      eprint={2005.12662},
      archivePrefix={arXiv},
      primaryClass={cs.GR}
}