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

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.

[1]  Ming Li,et al.  Real‐time interactive MRI‐guided cardiac surgery: Aortic valve replacement using a direct apical approach , 2006, Magnetic resonance in medicine.

[2]  Jens Frahm,et al.  High-speed real-time magnetic resonance imaging of fast tongue movements in elite horn players. , 2015, Quantitative imaging in medicine and surgery.

[3]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4]  Mihaela Pop,et al.  Real‐time MRI guidance of cardiac interventions , 2017, Journal of magnetic resonance imaging : JMRI.

[5]  Jens Frahm,et al.  Accelerated Computing in Magnetic Resonance Imaging: Real-Time Imaging Using Nonlinear Inverse Reconstruction , 2017, Comput. Math. Methods Medicine.

[6]  Klaus H. Maier-Hein,et al.  Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features , 2017, STACOM@MICCAI.

[7]  Nicholas Ayache,et al.  3-D Consistent and Robust Segmentation of Cardiac Images by Deep Learning With Spatial Propagation , 2018, IEEE Transactions on Medical Imaging.

[8]  Xin Yang,et al.  Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved? , 2018, IEEE Transactions on Medical Imaging.

[9]  Xiangyu Zhang,et al.  ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design , 2018, ECCV.

[10]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Jinjun Xiong,et al.  SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection , 2019, AAAI.

[12]  Zhiming Luo,et al.  Convolutional Neural Network With Shape Prior Applied to Cardiac MRI Segmentation , 2019, IEEE Journal of Biomedical and Health Informatics.