扩散峰度成像的放射组学分析：鉴别脑胶质母细胞瘤和单发脑转移瘤。
Radiomics Analysis of Diffusion Kurtosis Imaging: Distinguishing Between Glioblastoma and Single Brain Metastasis.
机构信息
Department of Magnetic Resonance Imaging, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan, China (E.G., P.W., J.B., X.M., J.Q., K.Z., G.Z., J.C.); Henan Engineering Research Center of Medical Imaging Intelligent Diagnosis and Treatment, Zhengzhou, Henan, China (E.G., P.W., J.B., X.M., J.Q., K.Z., G.Z., J.C.).
School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou, Henan, China (Y.G.).
出版信息
Acad Radiol. 2024 Mar;31(3):1036-1043. doi: 10.1016/j.acra.2023.07.023. Epub 2023 Sep 9.
RATIONALE AND OBJECTIVES
This study aimed to assess the value of diffusion kurtosis imaging (DKI)-based radiomics models in differentiating glioblastoma (GB) from single brain metastasis (SBM) and compare their diagnostic performance with that of routine magnetic resonance imaging (MRI) models.
MATERIALS AND METHODS
A total of 110 patients who underwent DKI and were pathologically diagnosed with GB (n = 58) or SBM (n = 52) were enrolled in this study. Radiomics features were extracted from the manually delineated region of interest of the lesion. A training set for model development was constructed from the images of 88 random patients, and 22 patients were reserved for independent validation. Seven single-DKI-parametric models and a multi-DKI-parametric model were constructed using six classifiers, whereas four single-routine-sequence models (based on T2 weighted imaging, apparent diffusion coefficient, T2-dark-fluid, and contrast-enhanced T1 magnetization prepared rapid gradient echo) and a multisequence routine MRI model were constructed for comparison. Receiver operating characteristic curve analysis was conducted to assess the diagnostic performance. The areas under the curve (AUCs) of different models were compared using the DeLong test.
RESULTS
The AUCs of the single-DKI-parametric models ranged from 0.800 to 0.933 (mean kurtosis [MK] model). The multi-DKI-parametric model had a slightly higher AUC (0.958) than the MK model; however, the difference was not statistically significant (P = 0.688). In comparison, the AUCs of the routine MRI models ranged from 0.633 to 0.733 (multisequence routine MRI model). The AUC of the multi-DKI-parametric model was significantly higher than that of the multisequence routine MRI model (P = 0.042).
CONCLUSION
The multi-DKI-parametric radiomics model exhibited better performance than that of the single-DKI-parametric models and routine MRI models in distinguishing GB from SBM.
背景与目的
本研究旨在评估基于扩散峰度成像（DKI）的放射组学模型在鉴别胶质母细胞瘤（GB）与单发脑转移瘤（SBM）中的价值，并比较其与常规磁共振成像（MRI）模型的诊断性能。
材料与方法
本研究共纳入 110 例经 DKI 检查并经病理诊断为 GB（n=58）或 SBM（n=52）的患者。从病变的手动勾画感兴趣区提取放射组学特征。从 88 例随机患者的图像中构建模型开发的训练集，并保留 22 例患者用于独立验证。使用 6 种分类器构建了 7 种单-DKI 参数模型和一种多-DKI 参数模型，而构建了 4 种单常规序列模型（基于 T2 加权成像、表观扩散系数、T2 暗液和对比增强 T1 磁化准备快速梯度回波）和一种多序列常规 MRI 模型进行比较。采用受试者工作特征曲线分析评估诊断性能。采用 DeLong 检验比较不同模型的曲线下面积（AUCs）。
结果
单-DKI 参数模型的 AUC 范围为 0.800 至 0.933（平均峰度[MK]模型）。多-DKI 参数模型的 AUC 略高于 MK 模型（0.958），但差异无统计学意义（P=0.688）。相比之下，常规 MRI 模型的 AUC 范围为 0.633 至 0.733（多序列常规 MRI 模型）。多-DKI 参数模型的 AUC 明显高于多序列常规 MRI 模型（P=0.042）。
结论
多-DKI 参数放射组学模型在鉴别 GB 与 SBM 方面的性能优于单-DKI 参数模型和常规 MRI 模型。
Zotero 插件