Spatiotemporal motion prediction in free-breathing liver scans via a recurrent multi-scale encoder decoder

TL;DR

This paper introduces a multi-scale recurrent encoder-decoder model to predict liver motion during free-breathing MRI scans, achieving high accuracy in vessel position prediction and outperforming existing methods.

Contribution

The paper presents a novel multi-scale recurrent encoder-decoder architecture for spatiotemporal motion prediction in liver MRI scans, demonstrating improved accuracy over state-of-the-art approaches.

Findings

Achieved mean vessel position prediction error of 2.07 mm.

Model outperformed existing methods in accuracy.

Increased prediction frames improved model performance.

Abstract

In this work we propose a multi-scale recurrent encoder-decoder architecture to predict the breathing induced organ deformation in future frames. The model was trained end-to-end from input images to predict a sequence of motion labels. Targets were created by quantizing the displacement fields obtained from deformable image registration. We report results using MRI free-breathing acquisitions from 12 volunteers. Experiments were aimed at investigating the proposed multi-scale design and the effect of increasing the number of predicted frames on the overall accuracy of the model. The proposed model was able to predict vessel positions in the next temporal image with a mean accuracy of 2.07 (2.95) mm showing increased performance in comparison with state-of-the-art approaches.