# Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences

Source: [Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences](<https://www.sota2.com/research/paper/68fa64801e209131cea04e98>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:05:03.439Z

Authors: Chen Qin, Wenjia Bai, Jo Schlemper, Steffen E. Petersen, Stefan K. Piechnik, Stefan Neubauer, Daniel Rueckert

Published: 2018-06-11T15:45:47.000Z

## Abstract

Cardiac motion estimation and segmentation play important roles in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In this paper, we propose a novel deep learning method for joint estimation of motion and segmentation from cardiac MR image sequences. The proposed network consists of two branches: a cardiac motion estimation branch which is built on a novel unsupervised Siamese style recurrent spatial transformer network, and a cardiac segmentation branch that is based on a fully convolutional network. In particular, a joint multi-scale feature encoder is learned by optimizing the segmentation branch and the motion estimation branch simultaneously. This enables the weakly-supervised segmentation by taking advantage of features that are unsupervisedly learned in the motion estimation branch from a large amount of unannotated data. Experimental results using cardiac MRI images from 220 subjects show that the joint learning of both tasks is complementary and the proposed models outperform the competing methods significantly in terms of accuracy and speed.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Cardiac Shape Registration on UK Biobank](<https://www.sota2.com/research/sota/cardiac-shape-registration-on-uk-biobank.md>): Cardiac shape registration; UK BioBank; DSC (%): 85.53.

- [Cardiac Shape Registration on M&M (ED and ES)](<https://www.sota2.com/research/sota/cardiac-shape-registration-on-m-and-m-ed-and-es.md>): Cardiac shape registration; M&M (ED and ES); DSC: 77.45.

- [Cardiac Indices Estimation on UK Biobank (test)](<https://www.sota2.com/research/sota/cardiac-indices-estimation-on-uk-biobank-test.md>): Cardiac clinical indices estimation; UK Biobank (test); LVEDV: 116.57.

- [Cardiac clinical indices calculation on M&M](<https://www.sota2.com/research/sota/cardiac-clinical-indices-calculation-on-m-and-m.md>): Cardiac clinical indices calculation; m&m; LVEDV: 163.52.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1806.04066>)

[PDF](<https://arxiv.org/pdf/1806.04066.pdf>)