Jiang Yue, Punjabi Karan, Pierce Iain, Knight Daniel, Yao Tina, Steeden Jennifer, Hughes Alun D, Muthurangu Vivek, Davies Rhodri
Institute of Cardiovascular Science, University College London, London WC1N 1DZ, United Kingdom.
Barts Heart Centre, St. Bartholomew's Hospital, London EC1A 7BE, United Kingdom.
Magn Reson Imaging. 2025 Jan;115:110253. doi: 10.1016/j.mri.2024.110253. Epub 2024 Oct 12.
The identification and measurement of aortic aneurysms is an important clinical problem. While specialized high-resolution 3D CMR sequences allow detailed aortic assessment, they are time-consuming which limits their use in screening routine cardiac scans and in population studies.
A 3D U-Net, U-Net was used to create 3D isotropic segmentations of the aorta from standard anisotropic 2D trans-axial localizers with low through-plane resolution. Training data was generated from high-resolution 3D isotropic whole heart images by simulating anisotropic images that resemble the low-resolution 2D localizers (the inputs). These inputs were paired with 3D isotropic 'ground truth' segmentation masks (the targets) created by a clinician from the high-resolution isotropic images. Segmentation quality was evaluated using an external dataset from UK Biobank. Segmentation accuracy was measured against ground-truth segmentations from concurrently acquired cardiac-triggered, respiratory-gated, high-resolution 3D isotropic whole heart images. Finally, the proposed method was compared to U-Net, a 3D U-Net variant trained directly on high-resolution 3D isotropic images. A second observer was recruited to investigate the interobserver variability.
Qualitative validation on an external dataset (UK Biobank) of 180 subjects showed that 93 % of 3D segmentations with the proposed model (U-Net) were considered suitable for clinical use. In quantitative analysis, the proposed method (U-Net) showed good agreement with ground-truth segmentations from isotropic 3D images with a mean DICE score of 0.9, which is no difference from automated segmentations made directly on the high-resolution 3D isotropic aorta images (U-Net). When comparing measurements, there is no significant difference between U-Net U-Net and two clinical observers in the diameter measurements at the mid ascending aorta, mid aortic arch, and descending aorta.
A new method of producing isotropic 3D aortic segmentations from routine CMR 2D anisotropic localizers shows good agreement with segmentation made directly from 3D isotropic images. The method has the potential to be used as a simple screening method for aortic aneurysms without the need for additional sequences.
主动脉瘤的识别与测量是一个重要的临床问题。虽然专门的高分辨率三维心脏磁共振成像（CMR）序列能够对主动脉进行详细评估，但这些序列耗时较长，限制了它们在常规心脏扫描筛查及人群研究中的应用。
使用一个三维U-Net网络从具有低层面分辨率的标准各向异性二维横轴定位像创建主动脉的三维各向同性分割。通过模拟类似于低分辨率二维定位像（输入图像）的各向异性图像，从高分辨率三维各向同性全心脏图像生成训练数据。这些输入图像与由临床医生从高分辨率各向同性图像创建的三维各向同性“真实”分割掩码（目标图像）配对。使用来自英国生物银行的外部数据集评估分割质量。根据同时采集的心脏触发、呼吸门控的高分辨率三维各向同性全心脏图像的真实分割来测量分割准确性。最后，将所提出的方法与直接在高分辨率三维各向同性图像上训练的三维U-Net网络变体U-Net进行比较。招募了第二位观察者来研究观察者间的变异性。
对180名受试者的外部数据集（英国生物银行）进行的定性验证表明，所提出模型（U-Net）的三维分割中有93%被认为适合临床使用。在定量分析中，所提出的方法（U-Net）与各向同性三维图像的真实分割显示出良好的一致性，平均DICE分数为0.9，这与直接在高分辨率三维各向同性主动脉图像上进行的自动分割（U-Net）没有差异。在比较测量结果时，U-Net和两位临床观察者在升主动脉中部、主动脉弓中部和降主动脉的直径测量上没有显著差异。
一种从常规CMR二维各向异性定位像生成各向同性三维主动脉分割的新方法与直接从三维各向同性图像进行的分割显示出良好的一致性。该方法有潜力用作一种简单的主动脉瘤筛查方法，无需额外的序列。
