Department of Radiology, First Affiliated Hospital of Kunming Medical University, 295Xichang Road, Wuhua, Kunming, 650032, China.
Department of Radiology, Yunnan Cancer Center, Yunnan Cancer Hospital, The Third Affiliated Hospital of Kunming Medical University, Kunming, 650118, China.
BMC Med Imaging. 2024 Oct 29;24(1):293. doi: 10.1186/s12880-024-01467-2.
This study aims to assess the performance of an established an AI algorithm trained on conventional polychromatic computed tomography (CT) images (CPIs) to detect pulmonary ground-glass nodules (GGNs) on virtual monochromatic images (VMIs), and to screen the optimal virtual monochromatic energy for the clinical evaluation of GGNs.
Non-enhanced chest SDCT images of patients with pulmonary GGNs in our clinic from January 2022 to December 2022 were continuously collected: adenocarcinoma in situ (AIS, n = 40); minimally invasive adenocarcinoma (MIA, n = 44) and invasive adenocarcinoma (IAC, n = 46). A commercial CAD system based on deep convolutional neural networks (DL-CAD) was used to process the CPIs, 40, 50, 60, 70, and 80 keV monochromatic images of 130 spectral CT images. AI-based histogram parameters by logistic regression analysis. The diagnostic performance was evaluated by the receiver operating characteristic (ROC) curves, and Delong's test was used to compare the CPIs group with the VMIs group.
When distinguishing IAC from MIA, the diagnostic efficiency of total mass was obtained at 80 keV, which was superior to those of other energy levels (P < 0.05). And Delong's test indicated that the differences between the area-under-the-curve (AUC) values of the CPIs group and the VMIs group were not statistically significant (P > 0.05).
The AI algorithm trained on CPIs showed consistent diagnostic performance on VMIs. When pulmonary GGNs are encountered in clinical practice, 80 keV could be the optimal virtual monochromatic energy for the identification of preoperative IAC on a non-enhanced chest CT.
本研究旨在评估基于常规多色计算机断层扫描（CT）图像（CPIs）训练的成熟人工智能（AI）算法在虚拟单色图像（VMIs）上检测肺磨玻璃结节（GGNs）的性能，并筛选用于GGN 临床评估的最佳虚拟单色能量。
连续收集我院 2022 年 1 月至 2022 年 12 月期间具有肺 GGN 的患者的非增强胸部 SDCT 图像：原位腺癌（AIS，n=40）；微浸润性腺癌（MIA，n=44）和浸润性腺癌（IAC，n=46）。使用基于深度卷积神经网络（DL-CAD）的商业 CAD 系统处理 CPIs、130 个光谱 CT 图像的 40、50、60、70 和 80keV 单色图像。通过逻辑回归分析 AI 基于直方图的参数。通过接收者操作特征（ROC）曲线评估诊断性能，并使用 Delong 检验比较 CPIs 组和 VMIs 组。
在区分 IAC 与 MIA 时，总质量的诊断效率在 80keV 时最高，优于其他能量水平（P<0.05）。Delong 检验表明 CPIs 组和 VMIs 组的曲线下面积（AUC）值之间的差异无统计学意义（P>0.05）。
基于 CPIs 训练的 AI 算法在 VMIs 上表现出一致的诊断性能。在临床实践中遇到肺 GGN 时，80keV 可能是用于识别非增强胸部 CT 上术前 IAC 的最佳虚拟单色能量。
