血液透析患者心胸比率自动计算方法的验证

Validation of an Automated Cardiothoracic Ratio Calculation for Hemodialysis Patients.

作者信息

Chou Hsin-Hsu, Lin Jin-Yi, Shen Guan-Ting, Huang Chih-Yuan

机构信息

Department of Pediatrics, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi 600566, Taiwan.

Department of Bioinformatics and Medical Engineering, Asia University, Taichung 413305, Taiwan.

出版信息

Diagnostics (Basel). 2023 Apr 9;13(8):1376. doi: 10.3390/diagnostics13081376.

DOI:10.3390/diagnostics13081376

PMID:37189477

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10137564/

Abstract

UNLABELLED

Cardiomegaly is associated with poor clinical outcomes and is assessed by routine monitoring of the cardiothoracic ratio (CTR) from chest X-rays (CXRs). Judgment of the margins of the heart and lungs is subjective and may vary between different operators.

METHODS

Patients aged > 19 years in our hemodialysis unit from March 2021 to October 2021 were enrolled. The borders of the lungs and heart on CXRs were labeled by two nephrologists as the ground truth (nephrologist-defined mask). We implemented AlbuNet-34, a U-Net variant, to predict the heart and lung margins from CXR images and to automatically calculate the CTRs.

RESULTS

The coefficient of determination (R) obtained using the neural network model was 0.96, compared with an R of 0.90 obtained by nurse practitioners. The mean difference between the CTRs calculated by the nurse practitioners and senior nephrologists was 1.52 ± 1.46%, and that between the neural network model and the nephrologists was 0.83 ± 0.87% ( < 0.001). The mean CTR calculation duration was 85 s using the manual method and less than 2 s using the automated method ( < 0.001).

CONCLUSIONS

Our study confirmed the validity of automated CTR calculations. By achieving high accuracy and saving time, our model can be implemented in clinical practice.

摘要

未标注

心脏肥大与不良临床结局相关，可通过胸部X线片（CXR）常规监测心胸比率（CTR）进行评估。心脏和肺部边缘的判断具有主观性，不同操作者之间可能存在差异。

方法

纳入2021年3月至2021年10月在我们血液透析单元年龄大于19岁的患者。两名肾病学家将CXR上的肺和心脏边界标记为标准真值（肾病学家定义的掩码）。我们实施了AlbuNet - 34（一种U - Net变体），以从CXR图像预测心脏和肺部边缘并自动计算CTR。

结果

使用神经网络模型获得的决定系数（R）为0.96，而执业护士获得的R为0.90。执业护士和资深肾病学家计算的CTR之间的平均差异为1.52±1.46%，神经网络模型和肾病学家之间的平均差异为0.83±0.87%（<0.001）。手动方法计算CTR的平均持续时间为85秒，自动方法为不到2秒（<0.001）。