Division of Cardiovascular Medicine, Department of Health, Medicine and Caring Sciences, Linköping University, Linköping, Sweden.
Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden.
BMC Med Imaging. 2021 Feb 27;21(1):38. doi: 10.1186/s12880-021-00568-6.
Non-invasive imaging is of interest for tracking the progression of atherosclerosis in the carotid bifurcation, and segmenting this region into its constituent branch arteries is necessary for analyses. The purpose of this study was to validate and demonstrate a method for segmenting the carotid bifurcation into the common, internal, and external carotid arteries (CCA, ICA, ECA) in contrast-enhanced MR angiography (CE-MRA) data.
A segmentation pipeline utilizing a convolutional neural network (DeepMedic) was tailored and trained for multi-class segmentation of the carotid arteries in CE-MRA data from the Swedish CardioPulmonsary bioImage Study (SCAPIS). Segmentation quality was quantitatively assessed using the Dice similarity coefficient (DSC), Matthews Correlation Coefficient (MCC), F, F, and True Positive Ratio (TPR). Segmentations were also assessed qualitatively, by three observers using visual inspection. Finally, geometric descriptions of the carotid bifurcations were generated for each subject to demonstrate the utility of the proposed segmentation method.
Branch-level segmentations scored DSC = 0.80 ± 0.13, MCC = 0.80 ± 0.12, F = 0.82 ± 0.14, F = 0.78 ± 0.13, and TPR = 0.84 ± 0.16, on average in a testing cohort of 46 carotid bifurcations. Qualitatively, 61% of segmentations were judged to be usable for analyses without adjustments in a cohort of 336 carotid bifurcations without ground-truth. Carotid artery geometry showed wide variation within the whole cohort, with CCA diameter 8.6 ± 1.1 mm, ICA 7.5 ± 1.4 mm, ECA 5.7 ± 1.0 mm and bifurcation angle 41 ± 21°.
The proposed segmentation method automatically generates branch-level segmentations of the carotid arteries that are suitable for use in further analyses and help enable large-cohort investigations.
无创成像技术在跟踪颈动脉分叉处动脉粥样硬化的进展方面具有重要意义，对该区域进行分支动脉分割是进行分析的必要步骤。本研究旨在验证并展示一种基于卷积神经网络（DeepMedic）的方法，用于对对比增强磁共振血管造影（CE-MRA）数据中的颈动脉分叉进行分割，得到颈总动脉（CCA）、颈内动脉（ICA）和颈外动脉（ECA）。
我们定制并训练了一个分割管道，用于对来自瑞典心肺生物影像研究（SCAPIS）的 CE-MRA 数据中的颈动脉进行多类分割。使用 Dice 相似系数（DSC）、马修斯相关系数（MCC）、F1 分数、F2 分数和真阳性率（TPR）对分割质量进行了定量评估。此外，还通过三位观察者的视觉检查对分割进行了定性评估。最后，为每个受试者生成了颈动脉分叉的几何描述，以展示所提出的分割方法的实用性。
在一个 46 例颈动脉分叉的测试队列中，分支水平的分割平均得到 DSC=0.80±0.13、MCC=0.80±0.12、F1 分数=0.82±0.14、F2 分数=0.78±0.13 和 TPR=0.84±0.16。在一个没有金标准的 336 例颈动脉分叉的队列中，61%的分割在没有调整的情况下被认为可用于分析。颈动脉的几何形状在整个队列中差异很大，CCA 直径为 8.6±1.1mm、ICA 为 7.5±1.4mm、ECA 为 5.7±1.0mm，分叉角度为 41±21°。
该研究提出的分割方法能够自动生成适合进一步分析使用的颈动脉分支水平的分割，有助于开展大样本队列研究。
