用普通MRI图生成关节软骨T1ρ图，省时又省力。
Utilizing 3D Fast Spin Echo Anatomical Imaging to Reduce the Number of Contrast Preparations in $T_{1ρ}$ Quantification of Knee Cartilage Using Learning-Based Methods
- 用PD加权图像和深度学习模型预测T1ρ图，减少增强扫描次数。
- 误差低于5%，在低信噪比下仍表现优于传统方法。
- 适合临床快速评估骨关节炎，兼容现有设备限制。
目的：提出并评估一种加速T1ρ定量的新方法，结合T1ρ加权快速自旋回波（FSE）图像与质子密度（PD）加权解剖FSE图像，利用深度学习模型实现T1ρ映射，旨在缩短扫描时间并推动其在骨关节炎（OA）评估中的常规临床应用。方法：本回顾性研究使用40名受试者（30名OA患者，10名健康志愿者）的MRI数据，以一整块PD加权解剖FSE图像和一整块非零自旋锁定时间下的T1ρ加权图像作为输入，训练2D U-Net与多层感知机（MLP）等深度学习模型。生成的T1ρ图与基于四幅T1ρ加权图像的传统非线性最小二乘（NLLS）拟合方法得到的真实值进行对比，评估指标包括平均绝对误差（MAE）、平均绝对百分比误差（MAPE）、区域误差（RE）和区域百分比误差（RPE）。结果：深度学习模型在所有评估场景中均达到低于5%的区域百分比误差（RPE），优于NLLS方法，尤其在低信噪比条件下表现更优。其中2D U-Net效果最佳，有效利用空间信息实现精确拟合。所提方法兼容较短自旋锁定时间（TSL），缓解了射频硬件与特定吸收率（SAR）限制。结论：该方法可仅用PD加权解剖图像实现高效可靠的T1ρ映射，显著缩短扫描时间，同时满足临床标准，有望推动定量MRI技术在常规临床实践中的落地，助力骨关节炎的诊断与监测。
原文摘要 · Abstract (English)
Purpose: To propose and evaluate an accelerated $T_{1ρ}$ quantification method that combines $T_{1ρ}$-weighted fast spin echo (FSE) images and proton density (PD)-weighted anatomical FSE images, leveraging deep learning models for $T_{1ρ}$ mapping. The goal is to reduce scan time and facilitate integration into routine clinical workflows for osteoarthritis (OA) assessment. Methods: This retrospective study utilized MRI data from 40 participants (30 OA patients and 10 healthy volunteers). A volume of PD-weighted anatomical FSE images and a volume of $T_{1ρ}$-weighted images acquired at a non-zero spin-lock time were used as input to train deep learning models, including a 2D U-Net and a multi-layer perceptron (MLP). $T_{1ρ}$ maps generated by these models were compared with ground truth maps derived from a traditional non-linear least squares (NLLS) fitting method using four $T_{1ρ}$-weighted images. Evaluation metrics included mean absolute error (MAE), mean absolute percentage error (MAPE), regional error (RE), and regional percentage error (RPE). Results: Deep learning models achieved RPEs below 5% across all evaluated scenarios, outperforming NLLS methods, especially in low signal-to-noise conditions. The best results were obtained using the 2D U-Net, which effectively leveraged spatial information for accurate $T_{1ρ}$ fitting. The proposed method demonstrated compatibility with shorter TSLs, alleviating RF hardware and specific absorption rate (SAR) limitations. Conclusion: The proposed approach enables efficient $T_{1ρ}$ mapping using PD-weighted anatomical images, reducing scan time while maintaining clinical standards. This method has the potential to facilitate the integration of quantitative MRI techniques into routine clinical practice, benefiting OA diagnosis and monitoring.
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。