MSU-Net: Multiscale Statistical U-Net for Real-Time 3D Cardiac MRI Video Segmentation

Tianchen Wang, Jinjun Xiong, Xiaowei Xu, Meng Jiang, Haiyun Yuan, Meiping Huang, Jian Zhuang, Yiyu Shi

Abstract

Cardiac magnetic resonance imaging (MRI) is an essential tool for MRI-guided surgery and real-time intervention. The MRI videos are expected to be segmented on-the-fly in real practice. However, existing segmentation methods would suffer from drastic accuracy loss when modified for speedup. In this work, we propose Multiscale Statistical U-Net (MSU-Net) for real-time 3D MRI video segmentation in cardiac surgical guidance. Our idea is to model the input samples as multiscale canonical form distributions for speedup, while the spatio-temporal correlation is still fully utilized. A parallel statistical U-Net is then designed to efficiently process these distributions. The fast data sampling and efficient parallel structure of MSU-Net endorse the fast and accurate inference. Compared with vanilla U-Net and a modified state-of-the-art method GridNet, our method achieves up to 268% and 237% speedup with 1.6% and 3.6% increased Dice scores.
BibTeX
@inproceedings{wang2019msu,
  author = {Tianchen Wang and Jinjun Xiong and Xiaowei Xu and Meng Jiang and Haiyun Yuan and Meiping Huang and Jian Zhuang and Yiyu Shi},
  title = {{MSU-Net: Multiscale Statistical U-Net for Real-Time 3D Cardiac MRI Video Segmentation}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2019},
  url = {https://openreview.net/forum?id=SCOcQGT4Dp},
}
Figure