MSU-Net: Multiscale Statistical U-Net for Real-Time 3D Cardiac MRI Video Segmentation
Lists
Only you see this
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},
}