Mochizuki Junji, Hata Yoshiki, Nakaura Takeshi, Hashimoto Katsushi, Uetani Hiroyuki, Nagayama Yasunori, Kidoh Masafumi, Funama Yoshinori, Hirai Toshinori
Minamino Cardiovascular Hospital Tokyo Japan.
Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University Kumamoto Japan.
Circ Rep. 2024 Nov 13;6(12):564-572. doi: 10.1253/circrep.CR-24-0086. eCollection 2024 Dec 10.
This study aimed to determine whether spectral imaging with dual-energy computed tomography (CT) can improve diagnostic performance for coronary plaque characterization.
We conducted a retrospective analysis of 30 patients with coronary plaques, using coronary CT angiography (dual-layer CT) and intravascular ultrasound (IVUS) studies. Based on IVUS findings, patients were diagnosed with either vulnerable or stable plaques. We computed 7 histogram parameters for plaque CT numbers in 120 kVp images and virtual monochromatic images ranging from 40 to 140 keV at 5-keV intervals. A predictive model was developed using histogram data of optimal energy, plaque volume or stenosis, and a combination of both. The model's performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC) using 5-fold cross-validation. Peak diagnostic performances for each histogram parameter were observed at various energy levels (40-110 keV) in the univariate logistic regression model. The histogram model demonstrated optimal diagnostic performance at 65 keV, with an AUC of 0.81. The combined model, incorporating histogram data and plaque volume, achieved an AUC of 0.85, which was similar to the performance of qualitative CT characteristics (AUC=0.88; P=0.70).
Spectral imaging with dual-energy CT can enhance the diagnostic performance of machine learning using CT histograms for coronary plaque characterization.
本研究旨在确定双能计算机断层扫描（CT）的光谱成像是否能提高冠状动脉斑块特征的诊断性能。
我们对30例冠状动脉斑块患者进行了回顾性分析，采用冠状动脉CT血管造影（双层CT）和血管内超声（IVUS）研究。根据IVUS结果，患者被诊断为易损斑块或稳定斑块。我们计算了120 kVp图像以及40至140 keV、间隔为5 keV的虚拟单色图像中斑块CT值的7个直方图参数。利用最佳能量、斑块体积或狭窄程度以及两者组合的直方图数据建立了预测模型。通过5折交叉验证计算受试者操作特征曲线（AUC）下面积来评估模型的性能。在单因素逻辑回归模型中，在不同能量水平（40 - 110 keV）观察到每个直方图参数的峰值诊断性能。直方图模型在65 keV时表现出最佳诊断性能，AUC为0.81。结合直方图数据和斑块体积的联合模型AUC为0.85，与定性CT特征的性能相似（AUC = 0.88；P = 0.70）。
双能CT的光谱成像可以提高利用CT直方图进行机器学习对冠状动脉斑块特征的诊断性能。
