用隐式神经表示实现心肌运动与应变的高效精准建模
Implicit Neural Representations of Intramyocardial Motion and Strain
- 基于隐式神经网络，通过学习潜在编码预测心室连续位移
- 在452例数据上误差仅2.14mm，应变误差低于现有方法
- 速度提升380倍，适合大规模心脏磁共振数据分析
从标记MRI自动量化心肌运动与应变仍是重要但具挑战的任务。本文提出一种基于隐式神经表示（INRs）的方法，通过学习的潜在编码预测左心室（LV）连续位移，无需推理时优化。在452例英国生物银行测试数据上，该方法实现了最佳跟踪精度（2.14 mm RMSE），并优于三种深度学习基线，在全局周向（2.86%）和径向（6.42%）应变联合误差上表现最优。此外，该方法比最准确的基线快约380倍。结果表明，基于INR的模型适用于大规模心脏磁共振数据中心肌应变的高精度、可扩展分析。代码见https://github.com/andrewjackbell/Displacement-INR。
原文摘要 · Abstract (English)
Automatic quantification of intramyocardial motion and strain from tagging MRI remains an important but challenging task. We propose a method using implicit neural representations (INRs), conditioned on learned latent codes, to predict continuous left ventricular (LV) displacement -- without requiring inference-time optimisation. Evaluated on 452 UK Biobank test cases, our method achieved the best tracking accuracy (2.14 mm RMSE) and the lowest combined error in global circumferential (2.86%) and radial (6.42%) strain compared to three deep learning baselines. In addition, our method is $\sim$380$\times$ faster than the most accurate baseline. These results highlight the suitability of INR-based models for accurate and scalable analysis of myocardial strain in large CMR datasets. The code can be found at https://github.com/andrewjackbell/Displacement-INR
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。