PSPU-Net for Automatic Short Axis Cine MRI Segmentation of Left and Right Ventricles

Abstract

Characterization of the heart anatomy and function is mostly done with magnetic resonance image cine series. To achieve a correct characterization, the volume of the right and left ventricle need to be segmented, which is a timeconsuming task. We propose a new convolutional neural network architecture that combines U-net with PSP modules (PSPU-net) for the segmentation of left and right ventricle cavities and left ventricle myocardium in the diastolic frame of short-axis cine MRI images and compare its results against a classic 3D U-net architecture. We used a dataset containing 399 cases in total. The results showed higher quality results in both segmentation and final volume estimation for a test set of 99 cases in the case of the PSPU-net, with global dice metrics of 0.910 and median absolute relative errors in volume estimations of 0.026 and 0.039 for the left ventricle cavity and myocardium and 0.051 for the right ventricles cavity.

On the usability of synthetic data for improving the robustness of deep learning-based segmentation of cardiac magnetic resonance images

“…There have been a number of works aimed at developing sophisticated deep learning approaches tackling CMR image segmentation on specific data-sets (Baumgartner et al, 2017;Bernard et al, 2018;Ammar et al, 2021;Pérez-Pelegrí et al, 2020;Yang et al, 2020). While these models demonstrate high performance on samples extracted from the same data-set, they have not been tested in cross-data settings.…”

Plantorgan hunter: a deep learning-based framework for quantitative profiling plant subcellular morphology

“…To comprehensively evaluate the performance of OrgSegNet, we compared it with some classical DL image segmentation algorithms: PSPNet 11 , DeepLabv3+ 12 , DANet 13 , DNLNet 14 , PSPU-Net 15 , Swin Transformer (Swin) 16 , and for both accuracy and speed (Fig. 3a).…”

Applications of Deep Leaning on Cardiac MRI: Design Approaches for a Computer Aided Diagnosis

“…This chapter is based on a conference paper published in the context of this thesis [124]. The paper is available at: https://doi.org/10.1109/BIBE50027.2020.00177.…”