Division of Cardiothoracic Imaging, Joint Department of Medical Imaging, University of Toronto, Toronto, Canada.
Department of Medicine, University of Toronto, Toronto, Ontario, Canada.
Br J Radiol. 2022 Oct 1;95(1139):20210722. doi: 10.1259/bjr.20210722. Epub 2022 Sep 20.
Right-to-left ventricle diameter ratio (dRV/dLV) on CT pulmonary angiography (CTPA) is a predictor of outcomes in non-operated chronic thromboembolic pulmonary hypertension (CTEPH) patients. The purpose of this study is to evaluate the performance of a novel machine learning (ML) algorithm for dRV/dLV measurement in operated CTEPH patients and its association with post-operative outcomes.
This retrospective study reviewed consecutive CTEPH patients who underwent pulmonary endarterectomy between 2013 and 2017. ML calculated dRV/dLV on pre-operative CTPA and compared with manual measures. Associations of dRV/dLV with patient characteristics and post-operative outcomes were evaluated including intensive care (ICU) and hospital length of stay (LOS) using multivariable linear regression analysis. Prolonged LOS was defined as greater than median.
ML segmented the ventricles in 99/125 (79%) patients. The most common cause of failure was misidentification of the moderator band as the interventricular septum (7.9%). Mean dRV/dLV by ML was 1.4 ± 0.4 and strongly correlated with manual measures ( = 0.9-0.96 < 0.0001). dRV/dLV was moderately correlated with measures of pulmonary hypertension on right heart catheterization and RV dilatation on echocardiogram ( = 0.5-0.6, < 0.0001). dRV/dLV ≥ 1.2 was associated with proximal Jamieson type disease ( = 0.032), longer cardiopulmonary bypass ( = 0.037), aortic cross-clamp ( = 0.022) and circulatory arrest ( < 0.001) at surgery and dRV/dLV ≥ 1.6 with post-operative ECMO ( = 0.006). dRV/dLV was independently associated with prolonged ICU LOS (OR = 3.79, 95% CI 1.1-13.06, = 0.035).
dRV/dLV was associated with CTEPH severity and independently associated with prolonged ICU LOS. This CT parameter may therefore assist in perioperative planning. Further refinement of the ML algorithm or CTPA technique is required to avoid errors in ventricular segmentation.
Automated right-to-left ventricle ratio measurement by machine learning is feasible and is independently associated with outcome after pulmonary endarterectomy.
CT 肺动脉造影（CTPA）上右心室/左心室直径比（dRV/dLV）是未经手术的慢性血栓栓塞性肺动脉高压（CTEPH）患者结局的预测因子。本研究的目的是评估一种新的机器学习（ML）算法在手术治疗 CTEPH 患者中的 dRV/dLV 测量性能及其与术后结局的相关性。
这项回顾性研究纳入了 2013 年至 2017 年间接受肺动脉内膜切除术的连续 CTEPH 患者。ML 在术前 CTPA 上计算 dRV/dLV，并与手动测量进行比较。使用多变量线性回归分析评估 dRV/dLV 与患者特征和术后结局的相关性，包括 ICU 和住院时间（LOS），并将 LOS 延长定义为大于中位数。
ML 对 99/125（79%）例患者的心室进行了分割。最常见的失败原因是将中隔 moderator 带误识别为室间隔（7.9%）。ML 计算的 dRV/dLV 平均值为 1.4±0.4，与手动测量高度相关（r=0.9-0.96，<0.0001）。dRV/dLV 与右心导管检查的肺动脉高压和超声心动图上的 RV 扩张程度中度相关（r=0.5-0.6，<0.0001）。dRV/dLV≥1.2 与近端 Jamieson 型疾病（r=0.032）、体外循环时间更长（r=0.037）、主动脉阻断时间（r=0.022）和停循环时间（r<0.001）有关，而 dRV/dLV≥1.6 与术后 ECMO 有关（r=0.006）。dRV/dLV 与 ICU LOS 延长独立相关（OR=3.79，95%CI 1.1-13.06，r=0.035）。
dRV/dLV 与 CTEPH 严重程度相关，与 ICU LOS 延长独立相关。因此，该 CT 参数可能有助于围手术期计划。需要进一步改进 ML 算法或 CTPA 技术，以避免心室分割错误。
通过机器学习进行自动右心室/左心室比值测量是可行的，并且与肺内膜切除术术后结局独立相关。
