Chao Bonnie T, Sage Andrew T, McInnis Micheal C, Ma Jun, Grubert Van Iderstine Micah, Zhou Xuanzi, Valero Jerome, Cypel Marcelo, Liu Mingyao, Wang Bo, Keshavjee Shaf
Latner Thoracic Research Laboratories, Toronto General Hospital Research Institute, University Health Network, Toronto, ON, Canada.
Institute of Biomedical Engineering, University of Toronto, Toronto, ON, Canada.
NPJ Digit Med. 2024 Oct 3;7(1):272. doi: 10.1038/s41746-024-01260-z.
Ex vivo lung perfusion (EVLP) enables advanced assessment of human lungs for transplant suitability. We developed a convolutional neural network (CNN)-based approach to analyze the largest cohort of isolated lung radiographs to date. CNNs were trained to process 1300 longitudinal radiographs from n = 650 clinical EVLP cases. Latent features were transformed into principal components (PC) and correlated with known radiographic findings. PCs were combined with physiological data to classify clinical outcomes: (1) recipient time to extubation of <72 h, (2) ≥ 72 h, and (3) lungs unsuitable for transplantation. The top PC was significantly correlated with infiltration (Spearman R: 0·72, p < 0·0001), and adding radiographic PCs significantly improved the discrimination for clinical outcomes (Accuracy: 73 vs 78%, p = 0·014). CNN-derived radiographic lung features therefore add substantial value to the current assessments. This approach can be adopted by EVLP centers worldwide to harness radiographic information without requiring real-time radiological expertise.
体外肺灌注（EVLP）能够对用于移植的人类肺部进行高级评估。我们开发了一种基于卷积神经网络（CNN）的方法，以分析迄今为止最大规模的离体肺部X光片队列。对卷积神经网络进行训练，以处理来自n = 650例临床EVLP病例的1300张纵向X光片。将潜在特征转换为主成分（PC），并与已知的X光检查结果相关联。将主成分与生理数据相结合，以对临床结果进行分类：（1）接受者拔管时间<72小时，（2）≥72小时，以及（3）肺部不适合移植。顶级主成分与浸润显著相关（斯皮尔曼相关系数R：0·72，p < 0·0001），并且添加X光主成分显著提高了对临床结果的判别能力（准确率：73%对78%，p = 0·014）。因此，卷积神经网络衍生的肺部X光特征为当前评估增添了重要价值。全球的EVLP中心均可采用这种方法来利用X光信息，而无需实时放射学专业知识。
