文献速递主动脉疾病

基于影像组学的风险评估与接受胸主动脉腔内修复术的急性B型主动脉夹层患者结局相关

Radiomics-Based Risk Assessment Correlates With Outcomes in Patients With Acute Type B Aortic Dissection Undergoing Thoracic Endovascular Repair.
PubMed 文献 · J Endovasc Ther · 2024-09-17

本研究为单中心回顾性队列研究,纳入104例于2010年1月至2022年10月在本机构接受胸主动脉腔内修复术的B型主动脉夹层患者,从术前CT降主动脉区域提取影像组学特征并计算风险评分,按中位数分为高、低风险组,用3种模型验证。结果显示影像组学风险评分与TDA-PAR、再干预和总生存期3项结局均显著且独立相关。

要点

  • 基于影像组学的风险评分与TDA-PAR、再干预和总生存期均显著且独立相关。
  • 影像组学特征GLSZM_SmallAreaLowGrayLevelEmphasis和shape_Maximum2DDiameterColumn对再干预和生存结局均有正向影响。
  • GLCM_Idmn对生存有正向影响、对再干预有负向影响,TDA-PAR的影像组学风险与6区PAR相关性最显著。

核心结论

  • 基于影像组学的风险评分与TDA-PAR、再干预和总生存期结局显著相关。
  • 影像组学有潜力对接受TEVAR的TBAD患者结局预测做出重要贡献。

研究设计与样本

  • 单中心、回顾性、队列研究,纳入2010年1月至2022年10月在本机构接受TBAD的TEVAR的104例患者。
  • 分割患者降主动脉区域术前CT图像,从感兴趣区提取包括一阶特征、形状特征(2D和3D)、灰度共生矩阵(GLCM)、灰度尺寸区域矩阵、灰度游程长度矩阵、灰度依赖矩阵、邻域灰度差矩阵在内的综合影像组学特征集。
  • 用LASSO回归筛选与TDA-PAR和再干预相关的影像组学特征,用LASSO-Cox回归筛选与生存相关的特征,计算每位患者的影像组学风险评分。
  • 以评分中位数为截断值将患者分为影像组学高风险组和低风险组,并使用3种不同模型验证影像组学风险评分。

主要发现

  • 达到TDA-PAR与未达到TDA-PAR的患者基线特征无差异。
  • 影像组学风险评分与全部3项结局显著且独立相关。
  • GLSZM_SmallAreaLowGrayLevelEmphasis和shape_Maximum2DDiameterColumn对再干预和生存结局均有正向影响。
  • GLCM_Idmn对生存有正向影响,但对再干预有负向影响。
  • TDA-PAR的影像组学风险与6区PAR相关性最显著。

临床怎么用

  • 作者认为影像组学有潜力作为急性B型主动脉夹层管理中的风险分层和预后工具。

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)。

原文

OBJECTIVES: Our study aimed to investigate the correlations between radiomics-based assessment and outcomes, including positive aortic remodeling (PAR), reintervention for dissection at 1 year, and overall survival, in patients with Type B aortic dissection (TBAD) who underwent thoracic endovascular aortic repair (TEVAR). METHODS: This was a single-center, retrospective, cohort study. The cohort comprised 104 patients who had undergone TEVAR of TBAD in our institution between January 2010 and October 2022. We segmented preoperative computed tomography (CT) images of the patients' descending aorta regions, then extracted a comprehensive set of radiomic features, including first-order features, shape features (2D and 3D), gray-level co-occurrence matrix (GLCM), gray-level size zone matrix, gray-level run length matrix, gray-level dependence matrix, neighborhood gray-tone difference matrix, from the regions of interest. Next, we selected radiomics features associated with total descending aorta positive aortic remodeling (TDA-PAR) and reintervention by least absolute shrinkage and selection operator (LASSO) regression and features associated with survival by LASSO-Cox regression. This enabled us to calculate radiomics-based risk scores for each patient. We then allocated the patients to high and low radiomics-based risk groups, the cutoff being the median score. We used 3 different models to validate the radiomics-based risk scores. RESULTS: The patients' baseline characteristics did not differ between those who achieved TDA-PAR and those who did not. The radiomics-based risk scores were significantly and independently associated with all 3 outcomes. As to the impact of specific radiomics features, we found that GLSZM_SmallAreaLowGrayLevelEmphasis and shape_Maximum2DDiameterColumn had positive impacts on both reintervention and survival outcomes, whereas GLCM_Idmn positively affected survival but negatively affected reintervention. We found that radiomics-based risk for TDA-PAR correlated most significantly with zone 6 PAR. CONCLUSIONS: Radiomics-based risk scores were significantly associated with the outcomes of TDA-PAR, reintervention, and overall survival. Radiomics has the potential to make significant contributions to prediction of outcomes in patients with TBAD undergoing TEVAR.Clinical ImpactIn this study of 104 patients with Type B aortic dissection, we demonstrated associations between radiomics-based risk and postoperative outcomes, including total descending aorta positive aortic remodeling, reintervention and survival. These findings highlight radiomics' potential as a tool for risk stratification and prognostication in acute Type B aortic dissection management.

来源:J Endovasc Ther,查看原文。版权归原作者所有。

引用

  1. Wu Z, Lin J, Guo P, et al. Radiomics-Based Risk Assessment Correlates With Outcomes in Patients With Acute Type B Aortic Dissection Undergoing Thoracic Endovascular Repair. J Endovasc Ther. 2024. PMID: 39287152. doi:10.1177/15266028241275828

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。