Malik Halima, Uelwer Tobias, Röwer Lena Maria, Hußmann Janina, Verde Pablo Emilio, Harmeling Stefan, Voit Dirk, Frahm Jens, Klee Dirk, Pillekamp Frank
Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich Heine University, Düsseldorf, North Rhine-Westphalia, Germany.
Department of Computer Science, Technical University of Dortmund, Dortmund, North Rhine-Westphalia, Germany.
Med Phys. 2025 Aug;52(8):e18019. doi: 10.1002/mp.18019.
Cardiac real-time MRI (RT-MRI) in combination with MR-compatible spirometry (MRcS) offers unique opportunities to study heart-lung interactions. In contrast to other techniques that monitor respiration during MRI, MRcS provides quantitative respiratory data. Though MRcS is well tolerated, shortening of the scanning time with MRcS would be desirable, especially in young and sick patients.
The aim of the study was to predict airflow and lung volume based on RT-MR images after a short learning phase of combined RT-MRI and MRcS to provide respiratory data for subsequent short axis stack-based volumetries.
Cardiac RT-MRI (1.5 T; short axis; 30 frames/s) was acquired during free breathing in combination with MRcS in adult healthy subjects (n = 10). MR images with MRcS were recorded during a learning phase to collect training data. The iterative Lucas-Kanade method was applied to estimate optical flow from the captured MR images. A ridge regression model was fitted to predict airflow and thus also the lung volume from the estimated optical flow. Hyperparameters were estimated using leave-one-out cross validation and the performance was assessed on a held-out test dataset. Different durations and compositions of the learning phase were investigated to develop the most efficient measurement protocol. Coefficient of determination (R), relative mean squared error (rMSE), Bland-Altman analysis on absolute tidal volume difference (aTVD), and absolute maximal airflow difference (aMFD) were used to validate the predictions on held-out test data.
MRI combined with MRcS can train a machine learning algorithm to provide excellent predictive quantitative respiratory volume and flow for the remaining study. The optimal trade-off between predictive power and time necessary for training was reached with a shortened cardiac volumetry protocol covering only about two breaths per slice and every second slice (airflow: mean R: 0.984, mean rMSE: 0.015, Bias aMFD: -0.01 L/s with +0.084/-0.1 95% CI and volume: mean R: 0.990, mean rMSE: 0.003, Bias aTVD: 4.27 mL with +33/-24 95% CI) at a total duration of 100 s. Shorter protocols or application of the algorithm to subsequent studies in the same subject or even in different subjects still provided useful qualitative data.
Machine-learning-based prediction of respiratory flow and lung volume from cardiac RT-MR images after a short training phase with MRcS is feasible and can help to shorten the time with MRcS while providing accurate respiratory data during RT-MRI.
心脏实时磁共振成像（RT-MRI）与磁共振兼容肺活量测定法（MRcS）相结合，为研究心肺相互作用提供了独特的机会。与其他在MRI期间监测呼吸的技术不同，MRcS可提供定量的呼吸数据。尽管MRcS耐受性良好，但缩短使用MRcS的扫描时间仍是可取的，尤其是对于年轻和患病患者。
本研究的目的是在联合RT-MRI和MRcS的短学习阶段后，基于RT-MR图像预测气流和肺容积，以便为后续基于短轴堆栈的容积测定提供呼吸数据。
在成年健康受试者（n = 10）自由呼吸期间，结合MRcS采集心脏RT-MRI（1.5 T；短轴；30帧/秒）。在学习阶段记录带有MRcS的MR图像以收集训练数据。应用迭代卢卡斯-卡纳德方法从捕获的MR图像中估计光流。拟合岭回归模型以根据估计的光流预测气流，进而预测肺容积。使用留一法交叉验证估计超参数，并在留出的测试数据集上评估性能。研究了学习阶段的不同持续时间和组成，以制定最有效的测量方案。使用决定系数（R）、相对均方误差（rMSE）、绝对潮气量差异（aTVD）的布兰德-奥特曼分析以及绝对最大气流差异（aMFD）来验证对留出的测试数据的预测。
MRI与MRcS相结合可以训练机器学习算法，为其余研究提供出色的预测性定量呼吸容积和流量。通过缩短的心脏容积测定方案达到了预测能力与训练所需时间之间的最佳平衡，该方案每切片仅覆盖约两次呼吸且每隔一片（气流：平均R：0.984，平均rMSE：0.015，偏差aMFD：-0.01 L/s，95% CI为+0.084/-0.1；容积：平均R：0.990，平均rMSE：0.003，偏差aTVD：4.27 mL，95% CI为+33/-24），总持续时间为100秒。更短的方案或将该算法应用于同一受试者甚至不同受试者的后续研究中，仍可提供有用的定性数据。
在使用MRcS进行短训练阶段后，基于心脏RT-MR图像通过机器学习预测呼吸流量和肺容积是可行的，并且有助于缩短使用MRcS的时间，同时在RT-MRI期间提供准确的呼吸数据。
