arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15167cs.CVstat.APstat.ML
收藏

分布式深度学习在4D流体MRI超分辨率中的应用:域移位下的超分辨率提升

Distributional Deep Learning for Super-Resolution of 4D Flow MRI under Domain Shift

Department of Epidemiology and Biostatistics, University of California, San Francisco(流行病学与生物统计学系,加州大学旧金山分校)

Xiaoyi Wen, Fei Jiang

AI总结:

本文提出分布式深度学习框架,用于提升4D流体MRI在域移位下的超分辨率性能,通过训练和微调提高模型鲁棒性与泛化能力。

摘要:

超分辨率在医学影像中被广泛用于增强低质量数据,减少扫描时间并提高异常检测能力。传统超分辨率方法通常依赖于低分辨率和高分辨率图像配对数据集,训练模型从其人工降质的对应物中重建高分辨率图像。然而,在实际临床环境中,低分辨率数据往往源于与简单降采样显著不同的获取机制。因此,这些输入可能超出训练数据的领域,导致由于域移位而模型泛化能力差。为了解决这一限制,我们提出了一种分布式深度学习框架,以提高模型的鲁棒性和领域泛化能力。我们为此方法开发了用于增强4D流体MRI(4DF)分辨率的方案。4DF是一种新型成像模态,能够捕捉血流速度和临床相关指标,如血管壁应力。这些指标对于评估动脉瘤破裂风险至关重要。我们的模型最初在高分辨率计算流体力学(CFD)模拟及其降采样对应物上进行训练。然后在一小部分配对的4D流体MRI和CFD样本上进行微调。我们推导了我们分布估计器的理论性质,并证明了我们的框架通过真实数据应用显著优于传统深度学习方法。这突显了分布学习在解决域移位和在临床真实场景中提高超分辨率性能方面的有效性。

英文摘要:

Super-resolution is widely used in medical imaging to enhance low-quality data, reducing scan time and improving abnormality detection. Conventional super-resolution approaches typically rely on paired datasets of downsampled and original high resolution images, training models to reconstruct high resolution images from their artificially degraded counterparts. However, in real-world clinical settings, low resolution data often arise from acquisition mechanisms that differ significantly from simple downsampling. As a result, these inputs may lie outside the domain of the training data, leading to poor model generalization due to domain shift. To address this limitation, we propose a distributional deep learning framework that improves model robustness and domain generalization. We develop this approch for enhancing the resolution of 4D Flow MRI (4DF). This is a novel imaging modality that captures hemodynamic flow velocity and clinically relevant metrics such as vessel wall stress. These metrics are critical for assessing aneurysm rupture risk. Our model is initially trained on high resolution computational fluid dynamics (CFD) simulations and their downsampled counterparts. It is then fine-tuned on a small, harmonized dataset of paired 4D Flow MRI and CFD samples. We derive the theoretical properties of our distributional estimators and demonstrate that our framework significantly outperforms traditional deep learning approaches through real data applications. This highlights the effectiveness of distributional learning in addressing domain shift and improving super-resolution performance in clinically realistic scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑