DeU-Net: Deformable U-Net for 3D Cardiac MRI Video Segmentation

TL;DR

DeU-Net introduces deformable attention mechanisms to improve 3D cardiac MRI video segmentation accuracy by effectively leveraging spatio-temporal information, addressing challenges like anisotropic resolution and ambiguous borders.

Contribution

The paper presents a novel DeU-Net architecture with TDAM and DGPA modules, enhancing feature aggregation for improved segmentation performance.

Findings

Achieves state-of-the-art results on standard metrics

Improves accuracy in marginal cardiac information segmentation

Effectively exploits spatio-temporal features in 3D MRI videos

Abstract

Automatic segmentation of cardiac magnetic resonance imaging (MRI) facilitates efficient and accurate volume measurement in clinical applications. However, due to anisotropic resolution and ambiguous border (e.g., right ventricular endocardium), existing methods suffer from the degradation of accuracy and robustness in 3D cardiac MRI video segmentation. In this paper, we propose a novel Deformable U-Net (DeU-Net) to fully exploit spatio-temporal information from 3D cardiac MRI video, including a Temporal Deformable Aggregation Module (TDAM) and a Deformable Global Position Attention (DGPA) network. First, the TDAM takes a cardiac MRI video clip as input with temporal information extracted by an offset prediction network. Then we fuse extracted temporal information via a temporal aggregation deformable convolution to produce fused feature maps. Furthermore, to aggregate meaningful features, we devise the DGPA network by employing deformable attention U-Net, which can encode a wider range of multi-dimensional contextual information into global and local features. Experimental results show that our DeU-Net achieves the state-of-the-art performance on commonly used evaluation metrics, especially for cardiac marginal information (ASSD and HD).