Multi-view Semi-supervised 3D Whole Brain Segmentation with a Self-ensemble Network

Yuan-Xing Zhao, Yan-Ming Zhang, Ming Song, Cheng-Lin LiuMICCAI 2019 · OpenReview

Abstract

Despite remarkable progress, 3D whole brain segmentation of structural magnetic resonance imaging (MRI) into a large number of regions (>100) is still difficult due to the lack of annotated data and the limitation of GPU memory. To address these challenges, we propose a semi-supervised segmentation method based on deep neural networks to exploit the plenty of unlabeled data by extending the self-training method, and improve the U-Net model by designing a novel self-ensemble architecture and a random patch-size training strategy. Further, to reduce the model storage and computational cost, we get a compact model by knowledge distillation. Extensive experiments conducted on the MICCAI 2012 dataset demonstrate that our method dramatically outperforms previous methods and has achieved the state-of-the-art performance. Our compact model segments an MRI image within 3 s on a TITAN X GPU, which is much faster than multi-atlas based methods and previous deep learning methods.
BibTeX
@inproceedings{zhao2019multi,
  author = {Yuan-Xing Zhao and Yan-Ming Zhang and Ming Song and Cheng-Lin Liu},
  title = {{Multi-view Semi-supervised 3D Whole Brain Segmentation with a Self-ensemble Network}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2019},
  url = {https://openreview.net/forum?id=MHKgRYVTU2N},
}

Loading related content...

Figure