Mank Quinten J, Thabit Abdullah, Maat Alexander P W M, Siregar Sabrina, van Walsum Theo, Kluin Jolanda, Sadeghi Amir H
Department of Cardiothoracic Surgery, Thoraxcenter, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands.
Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands.
Interdiscip Cardiovasc Thorac Surg. 2025 May 6;40(5). doi: 10.1093/icvts/ivaf101.
This study aimed to develop an automated method for pulmonary artery and vein segmentation in both left and right lungs from computed tomography (CT) images using artificial intelligence (AI). The segmentations were evaluated using PulmoSR software, which provides 3D visualizations of patient-specific anatomy, potentially enhancing a surgeon's understanding of the lung structure.
A dataset of 125 CT scans from lung segmentectomy patients at Erasmus MC was used. Manual annotations for pulmonary arteries and veins were created with 3D Slicer. nnU-Net models were trained for both lungs, assessed using Dice score, sensitivity and specificity. Intraoperative recordings demonstrated clinical applicability. A paired t-test evaluated statistical significance of the differences between automatic and manual segmentations.
The nnU-Net model, trained at full 3D resolution, achieved a mean Dice score between 0.91 and 0.92. The mean sensitivity and specificity were: left artery: 0.86 and 0.99, right artery: 0.84 and 0.99, left vein: 0.85 and 0.99, right vein: 0.85 and 0.99. The automatic method reduced segmentation time from ∼1.5 hours to under 5 minutes. Five cases were evaluated to demonstrate how the segmentations support lung segmentectomy procedures. P-values for Dice scores were all below 0.01, indicating statistical significance.
The nnU-Net models successfully performed automatic segmentation of pulmonary arteries and veins in both lungs. When integrated with visualization tools, these automatic segmentations can enhance preoperative and intraoperative planning by providing detailed 3D views of patients anatomy.
本研究旨在开发一种利用人工智能（AI）从计算机断层扫描（CT）图像中自动分割左右肺肺动脉和肺静脉的方法。使用PulmoSR软件对分割结果进行评估，该软件可提供患者特定解剖结构的三维可视化，可能增强外科医生对肺结构的理解。
使用了来自伊拉斯谟医学中心肺段切除术患者的125例CT扫描数据集。使用3D Slicer创建肺动脉和肺静脉的手动注释。对双肺训练nnU-Net模型，使用Dice分数、敏感性和特异性进行评估。术中记录证明了临床适用性。配对t检验评估自动分割和手动分割之间差异的统计学意义。
在全三维分辨率下训练的nnU-Net模型，平均Dice分数在0.91至0.92之间。平均敏感性和特异性分别为：左动脉：0.86和0.99，右动脉：0.84和0.99，左静脉：0.85和0.99，右静脉：0.85和0.99。自动方法将分割时间从约1.5小时减少到5分钟以内。评估了5个病例，以展示分割如何支持肺段切除术。Dice分数的P值均低于0.01，表明具有统计学意义。
nnU-Net模型成功地对双肺的肺动脉和肺静脉进行了自动分割。当与可视化工具集成时，这些自动分割可以通过提供患者解剖结构的详细三维视图来增强术前和术中规划。
