文献速递心血管MR

基于非增强电影心脏磁共振影像组学鉴别缺血性与扩张型心肌病

Radiomics for differential diagnosis of ischemic and dilated cardiomyopathy using non-contrast-enhanced cine cardiac magnetic resonance imaging.
PubMed 文献 · Radiol Med · 2025-03-10

回顾性纳入200例缺血性心肌病(ICM)与扩张型心肌病(DCM)患者,从短轴电影心脏磁共振(CMR)心肌和血池提取影像组学特征,构建3个逻辑回归模型分别鉴别ICM vs DCM、ICM中有无瘢痕、DCM中有无瘢痕。三个模型训练集AUC分别为0.964±0.008、0.989±0.004、0.996±0.004,测试集分别为0.918±0.040、0.955±0.045、0.935±0.052(p<0.0001),ROC曲线显示影像组学模型优于放射科医师。

要点

  • 非增强电影CMR影像组学模型可鉴别ICM与DCM,测试集AUC为0.918±0.040。
  • 模型可检测心肌瘢痕:ICM中测试集AUC为0.955±0.045,DCM中为0.935±0.052。
  • ROC曲线显示三个影像组学模型性能均优于放射科医师判读电影CMR。

核心结论

  • 影像组学结合电影CMR在鉴别ICM与DCM及检测心肌瘢痕方面显示出潜力,为钆对比剂禁忌患者提供了一种ICM与DCM鉴别的替代方法。

研究设计与样本

  • 回顾性纳入200例年龄≥18岁、诊断为ICM和DCM(伴或不伴心肌瘢痕)且拥有完整、心脏区域无伪影短轴电影CMR图像的患者;从短轴电影CMR的心肌和血池提取影像组学特征,采用组内相关系数和交叉验证递归特征消除(RFECV)进行特征选择,以逻辑回归多变量分析构建3个影像组学模型(ICM vs DCM、ICM中瘢痕 vs 无瘢痕、DCM中瘢痕 vs 无瘢痕),以ROC曲线下面积(AUC)评价模型性能并与放射科医师基于电影CMR图像的判读性能比较。

诊断标准与关键数值

  • 三个模型分别选择21、14和19个影像组学特征;训练集AUC分别为0.964±0.008、0.989±0.004、0.996±0.004,测试集AUC分别为0.918±0.040、0.955±0.045、0.935±0.052(p<0.0001);ROC曲线显示影像组学模型优于放射科医师。

临床应用与阅片要点

  • 对于钆对比剂禁忌患者,可考虑以非增强电影CMR影像组学作为ICM与DCM鉴别的替代方法(作者结论)。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVE: Our study investigated the effectiveness of using radiomics and non-gadolinium cine cardiac magnetic resonance (CMR) imaging for differential diagnosis between ischemic and dilated cardiomyopathy (ICM vs. DCM) and detecting myocardial scar without relying on gadolinium-based contrast agents.

MATERIALS AND METHODS: We retrospectively enrolled 200 patients with age ≥ 18 who were diagnosed with ICM and DCM, both with and without myocardial scars, and had complete short-axis cine CMR images without artifacts over the heart area. Radiomic features were extracted from the myocardium and blood pools in short-axis cine CMR images. Feature selection was performed using intraclass correlation coefficient and recursive feature elimination with cross-validation (RFECV). Multivariate analysis with logistic regression was utilized to construct 3 radiomic models (ICM vs DCM, Scar vs NoScar in ICM and in DCM). Model performance was evaluated using area under the receiver operating characteristic (ROC) curve (AUC) and compared with radiologist's performance using cine CMR images.

RESULTS: For each of the three models, 21, 14, and 19 radiomic features were selected. The AUC values of each model were 0.964 ± 0.008, 0.989 ± 0.004, and 0.996 ± 0.004, respectively, in the training set and 0.918 ± 0.040, 0.955 ± 0.045, and 0.935 ± 0.052, respectively, in the test set (p < 0.0001). The radiomic models outperformed the radiologist as shown by the ROC curve.

CONCLUSIONS: Radiomics showed promise in differentiating between ICM and DCM and detecting myocardial scar with cine CMR images, which offered an alternative for ICM and DCM differentiation in patients with gadolinium contraindication.

来源:Radiol Med,查看原文。版权归原作者所有。

引用

  1. Lasode J, Chantaksinopas W, Khongwirotphan S, et al. Radiomics for differential diagnosis of ischemic and dilated cardiomyopathy using non-contrast-enhanced cine cardiac magnetic resonance imaging. Radiol Med. 2025. PMID: 40063167. doi:10.1007/s11547-025-01979-z

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。