An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation

TL;DR

This paper compares 2D and 3D deep learning models for automated segmentation of cardiac MRI images, demonstrating high accuracy and efficiency on a standard dataset.

Contribution

It systematically evaluates various CNN architectures for cardiac MRI segmentation, highlighting the effectiveness of 2D slice-based approaches over 3D methods.

Findings

2D networks perform well due to slice thickness

Network architecture has minor impact on results

Achieved high Dice coefficients and fast processing times

Abstract

Accurate segmentation of the heart is an important step towards evaluating cardiac function. In this paper, we present a fully automated framework for segmentation of the left (LV) and right (RV) ventricular cavities and the myocardium (Myo) on short-axis cardiac MR images. We investigate various 2D and 3D convolutional neural network architectures for this task. We investigate the suitability of various state-of-the art 2D and 3D convolutional neural network architectures, as well as slight modifications thereof, for this task. Experiments were performed on the ACDC 2017 challenge training dataset comprising cardiac MR images of 100 patients, where manual reference segmentations were made available for end-diastolic (ED) and end-systolic (ES) frames. We find that processing the images in a slice-by-slice fashion using 2D networks is beneficial due to a relatively large slice thickness. However, the exact network architecture only plays a minor role. We report mean Dice coefficients of $0.950$ (LV), $0.893$ (RV), and $0.899$ (Myo), respectively with an average evaluation time of 1.1 seconds per volume on a modern GPU.