Department of Mathematics, University of Trento, Trento, Italy.
Department of Experimental Medicine, University of Genoa, Genoa, Italy.
Cardiovasc Eng Technol. 2022 Aug;13(4):535-547. doi: 10.1007/s13239-021-00594-z. Epub 2022 Jan 8.
Although segmentation of Abdominal Aortic Aneurysms (AAA) thrombus is a crucial step for both the planning of endovascular treatment and the monitoring of the intervention's outcome, it is still performed manually implying time consuming operations as well as operator dependency. The present paper proposes a fully automatic pipeline to segment the intraluminal thrombus in AAA from contrast-enhanced Computed Tomography Angiography (CTA) images and to subsequently analyze AAA geometry.
A deep-learning-based pipeline is developed to localize and segment the thrombus from the CTA scans. The thrombus is first identified in the whole sub-sampled CTA, then multi-view U-Nets are combined together to segment the thrombus from the identified region of interest. Polygonal models are generated for the thrombus and the lumen. The lumen centerline is automatically extracted from the lumen mesh and used to compute the aneurysm and lumen diameters.
The proposed multi-view integration approach returns an improvement in thrombus segmentation with respect to the single-view prediction. The thrombus segmentation model is trained over a training set of 63 CTA and a validation set of 8 CTA scans. By comparing the thrombus segmentation predicted by the model with the ground truth data, a Dice Similarity Coefficient (DSC) of 0.89 ± 0.04 is achieved. The AAA geometry analysis provided an Intraclass Correlation Coefficient (ICC) of 0.92 and a mean-absolute difference of 3.2 ± 2.4 mm, for the measurements of the total diameter of the aneurysm. Validation of both thrombus segmentation and aneurysm geometry analysis is performed over a test set of 14 CTA scans.
The developed deep learning models can effectively segment the thrombus from patients affected by AAA. Moreover, the diameters automatically extracted from the AAA show high correlation with those manually measured by experts.
尽管腹主动脉瘤（AAA）血栓的分割对于血管内治疗的规划和干预结果的监测都是至关重要的步骤，但目前仍需要手动进行，这既费时又依赖于操作人员。本文提出了一种全自动的流水线，用于从对比增强计算机断层血管造影（CTA）图像中分割 AAA 中的腔内血栓，并随后分析 AAA 的几何形状。
开发了一种基于深度学习的流水线，用于从 CTA 扫描中定位和分割血栓。首先在整个子采样 CTA 中识别血栓，然后将多视图 U-Net 结合起来，从识别的感兴趣区域中分割血栓。生成了用于血栓和管腔的多边形模型。管腔中心线从管腔网格中自动提取，并用于计算动脉瘤和管腔的直径。
所提出的多视图集成方法在血栓分割方面相对于单视图预测有了改进。血栓分割模型是在 63 个 CTA 的训练集和 8 个 CTA 扫描的验证集上进行训练的。通过将模型预测的血栓分割与地面实况数据进行比较，得到了 0.89 ± 0.04 的 Dice 相似系数（DSC）。AAA 几何形状分析对 14 个 CTA 扫描的测试集进行了验证，得到了 0.92 的组内相关系数（ICC）和 3.2 ± 2.4mm 的平均绝对差异，用于测量动脉瘤的总直径。
所开发的深度学习模型可以有效地从患有 AAA 的患者中分割血栓。此外，从 AAA 中自动提取的直径与专家手动测量的直径高度相关。
