用合成分形数据训练的深度学习模型，可达到真实心脏MRI数据的效果。
Training deep learning based dynamic MR image reconstruction using synthetic fractals
- 用四元数朱利亚分形生成动态MRI训练数据，模拟多线圈采集
- 分形训练模型在图像质量和心室容积测量上与真实数据训练无显著差异
- 为动态MRI重建提供开源可扩展的替代方案，适合临床研究者使用
目的：探究是否可用合成分形数据训练深度学习（DL）模型进行动态MRI重建，以规避心脏MRI数据集存在的隐私、授权和获取限制。方法：利用四元数朱利亚分形生成2D+time图像，模拟多线圈MRI采集，生成配对的全采样与径向欠采样k空间数据。使用这些分形数据训练3D UNet去伪影模型（F-DL），并与在真实心脏MRI数据上训练的同结构模型（CMR-DL）对比。两者均在10名患者前瞻性采集的实时径向心脏MRI上评估，结果与压缩感知（CS）及低秩深度图像先验（LR-DIP）比较。所有重建图像进行质量评分，心室容积和射血分数与参考屏气电影MRI对比。结果：F-DL与CMR-DL在主观评分上无显著差异（p=0.9），且均优于CS与LR-DIP（p<0.001）。F-DL得到的心室容积与功能与CMR-DL一致，无显著偏倚，一致性界限可接受；而LR-DIP存在显著偏倚（p=0.016）且界限更宽。结论：基于合成分形数据训练的DL模型可实现与真实心脏MRI数据训练相当的实时心脏MRI重建效果，分形数据提供了一种开放、可扩展的替代方案，有助于构建更具泛化能力的动态MRI重建模型。
原文摘要 · Abstract (English)
Purpose: To investigate whether synthetically generated fractal data can be used to train deep learning (DL) models for dynamic MRI reconstruction, thereby avoiding the privacy, licensing, and availability limitations associated with cardiac MR training datasets. Methods: A training dataset was generated using quaternion Julia fractals to produce 2D+time images. Multi-coil MRI acquisition was simulated to generate paired fully sampled and radially undersampled k-space data. A 3D UNet deep artefact suppression model was trained using these fractal data (F-DL) and compared with an identical model trained on cardiac MRI data (CMR-DL). Both models were evaluated on prospectively acquired radial real-time cardiac MRI from 10 patients. Reconstructions were compared against compressed sensing(CS) and low-rank deep image prior (LR-DIP). All reconstrctuions were ranked for image quality, while ventricular volumes and ejection fraction were compared with reference breath-hold cine MRI. Results: There was no significant difference in qualitative ranking between F-DL and CMR-DL (p=0.9), while both outperformed CS and LR-DIP (p<0.001). Ventricular volumes and function derived from F-DL were similar to CMR-DL, showing no significant bias and accptable limits of agreement compared to reference cine imaging. However, LR-DIP had a signifcant bias (p=0.016) and wider lmits of agreement. Conclusion: DL models trained using synthetic fractal data can reconstruct real-time cardiac MRI with image quality and clinical measurements comparable to models trained on true cardiac MRI data. Fractal training data provide an open, scalable alternative to clinical datasets and may enable development of more generalisable DL reconstruction models for dynamic MRI.
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。