MRI2Mesh: Intervertebral Disc Mesh Generation from Low Resolution MRI Using Graph Neural Networks with Cross Level Feature Fusion

Sai Natarajan, Aleksei Tiulpin, Ludovic Humbert, Miguel Ángel González Ballester

Abstract

This paper tackles the challenge of reconstructing high resolution meshes of intervertebral discs from low resolution thick-sliced sagittal MR images of the lumbar spine. By generating the meshes directly from the volume, we eliminate the error propagation incurred when segmentation is used as an intermediary step. Our method is based on a combination of Convolutional and Graph Neural Networks. We propose a novel cross-level disc feature fusion scheme, addressing both local and global shape context. This differs fundamentally from other surface reconstruction approaches, since our method exploits the underlying anatomical characteristics via an axial attention transformer. Experimental results show that the proposed method improves the Hausdorff distance by 5.87% and point-to-surface distance by 14.5% when compared to other baseline models.
BibTeX
@inproceedings{natarajan2023mri,
  author = {Sai Natarajan and Aleksei Tiulpin and Ludovic Humbert and Miguel Ángel González Ballester},
  title = {{MRI2Mesh: Intervertebral Disc Mesh Generation from Low Resolution MRI Using Graph Neural Networks with Cross Level Feature Fusion}},
  booktitle = {ISBI},
  year = {2023},
  doi = {10.1109/isbi53787.2023.10230651},
}

Loading related content...

Figure