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

arXiv: https://arxiv.org/abs/1909.06726 · HTML: https://mlsanity.com/paper/1909.06726/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2019.

## Built on by (most cited first, 7 of 7)

- [Positional Contrastive Learning for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2106.09157/) (2021)
- [Modality specific U-Net variants for biomedical image segmentation: A survey](https://mlsanity.com/paper/2107.04537/) (2021)
- [ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease](https://mlsanity.com/paper/2101.10799/) (2021)
- [EchoCP: An Echocardiography Dataset in Contrast Transthoracic Echocardiography for Patent Foramen Ovale Diagnosis](https://mlsanity.com/paper/2105.08267/) (2021)
- [RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation](https://mlsanity.com/paper/2206.04682/) (2022)
- [Hardware-aware Real-time Myocardial Segmentation Quality Control in Contrast Echocardiography](https://mlsanity.com/paper/2109.06909/) (2021)
- [Development of A Real-time POCUS Image Quality Assessment and Acquisition Guidance System](https://mlsanity.com/paper/2212.08624/) (2022)

## Abstract (arXiv)

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.