# Dynamic Position Transformation and Boundary Refinement Network for Left Atrial Segmentation

arXiv: https://arxiv.org/abs/2407.05505 · HTML: https://mlsanity.com/paper/2407.05505/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 7 Jul 2024.

## Builds on (most cited first, 11 of 11)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images](https://mlsanity.com/paper/2007.10732/) (2020)
- [Semi-supervised Left Atrium Segmentation with Mutual Consistency Training](https://mlsanity.com/paper/2103.02911/) (2021)
- [Multi-Task Learning for Left Atrial Segmentation on GE-MRI](https://mlsanity.com/paper/1810.13205/) (2018)
- [Combating Uncertainty with Novel Losses for Automatic Left Atrium Segmentation](https://mlsanity.com/paper/1812.05807/) (2018)
- [Dilated Convolutions in Neural Networks for Left Atrial Segmentation in 3D Gadolinium Enhanced-MRI](https://mlsanity.com/paper/1808.01673/) (2018)
- [Revisiting Initializing Then Refining: An Incomplete and Missing Graph Imputation Network](https://mlsanity.com/paper/2302.07524/) (2023)
- [Left atrial ejection fraction estimation using SEGANet for fully automated segmentation of CINE MRI](https://mlsanity.com/paper/2008.13718/) (2020)

## Built on by (most cited first, 2 of 2)

- [How good nnU-Net for Segmenting Cardiac MRI: A Comprehensive Evaluation](https://mlsanity.com/paper/2408.06358/) (2024)
- [Segmenting Bi-Atrial Structures Using ResNext Based Framework](https://mlsanity.com/paper/2503.02892/) (2025)

## Abstract (arXiv)

Left atrial (LA) segmentation is a crucial technique for irregular heartbeat (i.e., atrial fibrillation) diagnosis. Most current methods for LA segmentation strictly assume that the input data is acquired using object-oriented center cropping, while this assumption may not always hold in practice due to the high cost of manual object annotation. Random cropping is a straightforward data pre-processing approach. However, it 1) introduces significant irregularities and incompleteness in the input data and 2) disrupts the coherence and continuity of object boundary regions. To tackle these issues, we propose a novel Dynamic Position transformation and Boundary refinement Network (DPBNet). The core idea is to dynamically adjust the relative position of irregular targets to construct their contextual relationships and prioritize difficult boundary pixels to enhance foreground-background distinction. Specifically, we design a shuffle-then-reorder attention module to adjust the position of disrupted objects in the latent space using dynamic generation ratios, such that the vital dependencies among these random cropping targets could be well captured and preserved. Moreover, to improve the accuracy of boundary localization, we introduce a dual fine-grained boundary loss with scenario-adaptive weights to handle the ambiguity of the dual boundary at a fine-grained level, promoting the clarity and continuity of the obtained results. Extensive experimental results on benchmark dataset have demonstrated that DPBNet consistently outperforms existing state-of-the-art methods.