Dynamic Position Transformation and Boundary Refinement Network for Left Atrial Segmentation

TL;DR

This paper introduces DPBNet, a novel neural network that dynamically adjusts target positions and refines boundaries to improve left atrial segmentation in irregular and randomly cropped medical images.

Contribution

The paper proposes a dynamic position transformation and boundary refinement network with a shuffle-then-reorder attention module and dual boundary loss, addressing irregular cropping challenges in LA segmentation.

Findings

DPBNet outperforms state-of-the-art methods on benchmark datasets.

The dynamic position adjustment improves contextual relationship modeling.

Boundary refinement enhances segmentation accuracy and boundary clarity.

Abstract

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.