文献速递心血管胸部CT

经导管主动脉瓣置换术前干预前CT的直接深度学习生存预测

Direct deep learning-based survival prediction from pre-interventional CT prior to transcatheter aortic valve replacement.
PubMed 文献 · Eur J Radiol · 2023-10-11

回顾性单中心研究纳入760例TAVR患者,比较直接基于术前CT图像的深度学习生存预测与基于身体成分标量标志物的Cox模型,深度学习模型C指数0.645优于基线Cox模型0.608,二者联合进一步提升至0.668。

要点

  • 直接基于术前CT的深度学习模型生存预测C指数0.645,优于基于身体成分标量标志物的Cox模型0.608。
  • 深度学习与Cox模型联合后C指数达0.668,1年AUC 0.713,2年AUC 0.696。
  • 基线Cox模型使用L3/L4水平椎旁肌分割的脂肪酸肌分数、骨骼肌放射密度和骨骼肌面积。

核心结论

  • 直接基于深度学习的生存预测在TAVR患者风险评估中,相比基于分割的身体成分标量标志物,显示出改善图像特征提取的潜力。

研究设计与样本

  • 回顾性单中心研究,纳入760例接受TAVR的患者(平均年龄81±6岁,女性389例),以C指数和1年、2年生存AUC评估性能,所有方法采用五折交叉验证,并在152例留出测试集上评估。

诊断标准与关键数值

  • 基线Cox比例风险模型基于性别、年龄及L3/L4水平椎旁肌分割的脂肪酸肌分数、骨骼肌放射密度和骨骼肌面积;深度学习模型编码器在自编码器场景下预训练,分聚焦椎旁肌与不聚焦两种;评估指标为C指数及1年、2年生存AUC。

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

PURPOSE: To investigate survival prediction in patients undergoing transcatheter aortic valve replacement (TAVR) using deep learning (DL) methods applied directly to pre-interventional CT images and to compare performance with survival models based on scalar markers of body composition.

METHOD: This retrospective single-center study included 760 patients undergoing TAVR (mean age 81 ± 6 years; 389 female). As a baseline, a Cox proportional hazards model (CPHM) was trained to predict survival on sex, age, and the CT body composition markers fatty muscle fraction (FMF), skeletal muscle radiodensity (SMRD), and skeletal muscle area (SMA) derived from paraspinal muscle segmentation of a single slice at L3/L4 level. The convolutional neural network (CNN) encoder of the DL model for survival prediction was pre-trained in an autoencoder setting with and without a focus on paraspinal muscles. Finally, a combination of DL and CPHM was evaluated. Performance was assessed by C-index and area under the receiver operating curve (AUC) for 1-year and 2-year survival. All methods were trained with five-fold cross-validation and were evaluated on 152 hold-out test cases.

RESULTS: The CNN for direct image-based survival prediction, pre-trained in a focussed autoencoder scenario, outperformed the baseline CPHM (CPHM: C-index = 0.608, 1Y-AUC = 0.606, 2Y-AUC = 0.594 vs. DL: C-index = 0.645, 1Y-AUC = 0.687, 2Y-AUC = 0.692). Combining DL and CPHM led to further improvement (C-index = 0.668, 1Y-AUC = 0.713, 2Y-AUC = 0.696).

CONCLUSIONS: Direct DL-based survival prediction shows potential to improve image feature extraction compared to segmentation-based scalar markers of body composition for risk assessment in TAVR patients.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Theis M, Block W, Luetkens JA, et al. Direct deep learning-based survival prediction from pre-interventional CT prior to transcatheter aortic valve replacement. Eur J Radiol. 2023. PMID: 37844428. doi:10.1016/j.ejrad.2023.111150

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。