文献速递泌尿生殖腹部MR

基于无监督深度学习影像组学的早期动态对比增强MRI预测肾移植存活

Renal Transplant Survival Prediction From Unsupervised Deep Learning-Based Radiomics on Early Dynamic Contrast-Enhanced MRI.
PubMed 文献 · Acad Radiol · 2025-05-23

本研究为回顾性队列,用108例肾移植患者2013至2015年系统MRI随访数据,训练基于无监督对比学习的深度卷积神经网络模型,从早期动态对比增强MRI提取人工智能影像组学特征,并用惩罚Cox模型和Kaplan-Meier估计做5年移植物存活分析;在48例移植后1个月MRI的验证集中,5年移植物存活一致性指数为72.7%,影像组学特征的无监督聚类可对患者进行统计学显著分层(p=0.029)。

要点

  • 早期动态对比增强MRI提取的无监督深度学习影像组学特征,在验证集中获得72.7%的5年移植物存活一致性指数。
  • 这些影像组学特征的无监督聚类可实现患者分层,原文报告p=0.029。
  • 作者称本研究为概念验证,认为该技术有预测肾移植存活的潜力。

核心结论

  • 作者认为这项概念验证研究显示,人工智能算法有潜力提取相关影像组学特征以预测肾移植存活。
  • 作者指出需进一步研究以证明该技术的稳健性,并确定将其整合到多模态和临床环境中的合适流程。

研究设计与样本

  • 回顾性队列研究,训练集为108例接受系统MRI随访检查(2013至2015年)的移植患者,平均年龄50±15岁,67名男性。
  • 基于无监督对比学习方法训练深度卷积神经网络模型,从早期动态对比增强MRI数据提取人工智能影像组学特征。
  • 验证集为48例移植后1个月接受MRI检查的患者,平均年龄54±13岁,30名男性;用惩罚Cox模型和Kaplan-Meier估计做5年移植物存活分析。

诊断标准与关键数值

  • 验证集48例中,人工智能影像组学特征的5年移植物存活一致性指数为72.7%。
  • 影像组学特征的无监督聚类可对患者进行统计学显著分层,p=0.029。

临床应用与阅片要点

  • 原文结论为概念验证性质,作者指出需进一步研究证明该技术稳健性并确定其整合到多模态与临床环境的合适流程,未据此给出具体阅片或报告推荐。

局限性

  • 作者指出需进一步研究以证明该技术的稳健性,并确定将该方法整合到多模态和临床环境中的合适流程。

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

RATIONALE AND OBJECTIVES: End-stage renal disease is characterized by an irreversible decline in kidney function. Despite a risk of chronic dysfunction of the transplanted kidney, renal transplantation is considered the most effective solution among available treatment options. Clinical attributes of graft survival prediction, such as allocation variables or results of pathological examinations, have been widely studied. Nevertheless, medical imaging is clinically used only to assess current transplant status. This study investigated the use of unsupervised deep learning-based algorithms to identify rich radiomic features that may be linked to graft survival from early dynamic contrast-enhanced magnetic resonance imaging data of renal transplants.

MATERIALS AND METHODS: A retrospective cohort of 108 transplanted patients (mean age 50 +/- 15, 67 men) undergoing systematic magnetic resonance imaging follow-up examinations (2013 to 2015) was used to train deep convolutional neural network models based on an unsupervised contrastive learning approach. 5-year graft survival analysis was performed from the obtained artificial intelligence radiomics features using penalized Cox models and Kaplan-Meier estimates.

RESULTS: Using a validation set of 48 patients (mean age 54 +/- 13, 30 men) having 1-month post-transplantation magnetic resonance imaging examinations, the proposed approach demonstrated promising 5-year graft survival capability with a 72.7% concordance index from the artificial intelligence radiomics features. Unsupervised clustering of these radiomics features enabled statistically significant stratification of patients (p=0.029).

CONCLUSION: This proof-of-concept study exposed the promising capability of artificial intelligence algorithms to extract relevant radiomics features that enable renal transplant survival prediction. Further studies are needed to demonstrate the robustness of this technique, and to identify appropriate procedures for integration of such an approach into multimodal and clinical settings.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Milecki L, Bodard S, Kalogeiton V, et al. Renal Transplant Survival Prediction From Unsupervised Deep Learning-Based Radiomics on Early Dynamic Contrast-Enhanced MRI. Acad Radiol. 2025. PMID: 40413148. doi:10.1016/j.acra.2025.05.001

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。