A Comprehensive Approach for Learning-based Fully-Automated Inter-slice Motion Correction for Short-Axis Cine Cardiac MR Image Stacks

TL;DR

This paper introduces an automated method for correcting inter-slice respiratory motion in short-axis cine cardiac MRI stacks using probabilistic segmentation maps and decision forests, improving image consistency for better analysis.

Contribution

The novel approach combines probabilistic segmentation maps with registration techniques and leverages available long-axis images or a 3D model to enhance motion correction accuracy.

Findings

High accuracy in motion compensation demonstrated on healthy subjects

Robustness of the method across different datasets

Outperforms existing techniques using LA images and segmentations

Abstract

In the clinical routine, short axis (SA) cine cardiac MR (CMR) image stacks are acquired during multiple subsequent breath-holds. If the patient cannot consistently hold the breath at the same position, the acquired image stack will be affected by inter-slice respiratory motion and will not correctly represent the cardiac volume, introducing potential errors in the following analyses and visualisations. We propose an approach to automatically correct inter-slice respiratory motion in SA CMR image stacks. Our approach makes use of probabilistic segmentation maps (PSMs) of the left ventricular (LV) cavity generated with decision forests. PSMs are generated for each slice of the SA stack and rigidly registered in-plane to a target PSM. If long axis (LA) images are available, PSMs are generated for them and combined to create the target PSM; if not, the target PSM is produced from the same stack using a 3D model trained from motion-free stacks. The proposed approach was tested on a dataset of SA stacks acquired from 24 healthy subjects (for which anatomical 3D cardiac images were also available as reference) and compared to two techniques which use LA intensity images and LA segmentations as targets, respectively. The results show the accuracy and robustness of the proposed approach in motion compensation.