Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University Hospital, 377-2 Ohno-Higashi, Osakasayama, Osaka, 589-8511, Japan; Radiology Center, Kindai University Hospital, 377-2 Ohno-Higashi, Osakasayama, Osaka, 589-8511, Japan.
Radiology Center, Kindai University Hospital, 377-2 Ohno-Higashi, Osakasayama, Osaka, 589-8511, Japan.
Comput Biol Med. 2021 Oct;137:104824. doi: 10.1016/j.compbiomed.2021.104824. Epub 2021 Sep 2.
Patient movement during bolus tracking (BT) impairs the accuracy of Hounsfield unit (HU) measurements. This study assesses the accuracy of measuring HU values in the internal carotid artery (ICA) using an original deep learning (DL)-based method as compared with using the conventional region of interest (ROI) setting method.
A total of 722 BT images of 127 patients who underwent cerebral computed tomography angiography were selected retrospectively and divided into groups for training data, validation data, and test data. To segment the ICA using our proposed method, DL was performed using a convolutional neural network. The HU values in the ICA were obtained using our DL-based method and the ROI setting method. The ROI setting was performed with and without correcting for patient body movement (corrected ROI and settled ROI). We compared the proposed DL-based method with settled ROI to evaluate HU value differences from the corrected ROI, based on whether or not patients experienced involuntary movement during BT image acquisition.
Differences in HU values from the corrected ROI in the settled ROI and the proposed method were 23.8 ± 12.7 HU and 9.0 ± 6.4 HU in patients with body movement and 1.1 ± 1.6 HU and 3.9 ± 4.7 HU in patients without body movement, respectively. There were significant differences in both comparisons (P < 0.01).
DL-based method can improve the accuracy of HU value measurements for ICA in BT images with patient involuntary movement.
在团注追踪（BT）期间，患者运动可损害亨氏单位（HU）测量的准确性。本研究评估了使用原始基于深度学习（DL）的方法与使用传统的感兴趣区域（ROI）设置方法相比，在颈内动脉（ICA）中测量 HU 值的准确性。
回顾性选择了 127 名接受脑 CT 血管造影检查的患者的 722 个 BT 图像，并将其分为训练数据、验证数据和测试数据组。为了使用我们提出的方法分割 ICA，使用卷积神经网络进行了 DL。使用我们的基于 DL 的方法和 ROI 设置方法获得 ICA 中的 HU 值。在没有（校正 ROI）和有（ settled ROI）校正患者身体运动的情况下进行 ROI 设置。我们比较了基于 DL 的方法与 settled ROI，以评估基于 BT 图像采集期间患者是否经历不自主运动，HU 值与校正 ROI 的差异。
在有身体运动的患者中， settled ROI 和提议方法中与校正 ROI 的 HU 值差异分别为 23.8±12.7 HU 和 9.0±6.4 HU，在无身体运动的患者中，分别为 1.1±1.6 HU 和 3.9±4.7 HU。两种比较均有显著差异（P<0.01）。
基于 DL 的方法可以提高有患者不自主运动的 BT 图像中 ICA 的 HU 值测量的准确性。
