Temporal extrapolation of heart wall segmentation in cardiac magnetic resonance images via pixel tracking

TL;DR

This paper presents a pixel tracking method for extrapolating heart wall segmentation in cardiac MRI, achieving high accuracy without needing training data, making it suitable for data-limited scenarios.

Contribution

The study introduces a training-free pixel tracking approach for cardiac segmentation, offering an alternative to deep learning methods in limited data contexts.

Findings

Dice scores between 0.81 and 0.84 for tracked masks

Method does not require training data

Effective in scenarios with limited annotated datasets

Abstract

In this study, we have tailored a pixel tracking method for temporal extrapolation of the ventricular segmentation masks in cardiac magnetic resonance images. The pixel tracking process starts from the end-diastolic frame of the heart cycle using the available manually segmented images to predict the end-systolic segmentation mask. The superpixels approach is used to divide the raw images into smaller cells and in each time frame, new labels are assigned to the image cells which leads to tracking the movement of the heart wall elements through different frames. The tracked masks at the end of systole are compared with the already available manually segmented masks and dice scores are found to be between 0.81 to 0.84. Considering the fact that the proposed method does not necessarily require a training dataset, it could be an attractive alternative approach to deep learning segmentation methods in scenarios where training data are limited.