文献速递腹部MR

钆塞酸增强MRI影像组学预测结直肠癌肝转移患者肝切除术后肝衰竭风险

Prediction of post-hepatectomy liver failure risk in patients with colorectal cancer liver metastases utilizing gadoxetic acid-enhanced MRI radiomics with automatic segmentation and image registration.
PubMed 文献 · Abdom Radiol (NY) · 2026-09-26

本研究回顾性分析134例结直肠癌肝转移患者,利用钆塞酸增强MRI肝胆期图像,通过自动分割和图像配准构建影像组学模型预测肝切除术后肝衰竭(PHLF)。临床-影像组学联合模型在训练组和验证组的AUC分别为0.912和0.896,高于其他模型,对PHLF具有良好预测效能。

要点

  • 基于肝胆期MRI的临床-影像组学模型可预测PHLF风险。
  • 自动分割与图像配准有助于构建反映未来残肝功能的模型。
  • 联合模型预测效能优于单独影像组学或临床模型。

局限性

  • 回顾性研究设计。
  • 样本量有限。

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

OBJECTIVES: To develop and validate a radiomics model based on gadoxetic acidenhanced MRI, which can better reflect the future liver remnant (FLR) and its function through automatic segmentation and image registration, thereby predicting the risk of post-hepatectomy liver failure (PHLF) in patients with colorectal cancer liver metastases (CRLM).

METHODS: This retrospective study analyzed 134 CRLM patients who were divided into a training group (n = 93) and a validation group (n = 41). Model-Whole was constructed using the entire liver on preoperative hepatobiliary phase (HBP) obtained by automatic segmentation excluding the region of liver metastases. Model-FLR was constructed using the FLR on the HBP by registering postoperative CT and preoperative MR. Model-Clinical was constructed using general characteristics, preoperative data, intraoperative data and imaging parameters by univariate and multivariate analyses. Model-Clinical-radiomics was constructed using the optimal radiomics model and features from clinical model. The models were used to predict low-grade PHLF (without PHLF or PHLF Grade A) and high-grade PHLF (PHLF Grade B or C).

RESULTS: There were three and five radiomics features used for constructing Model-Whole and Model-FLR. The number of resected lesions and international normalized ratio (INR) were used for constructing Model-Clinical. The AUC of Model-Clinical-radiomics was 0.912 (95%CI: 0.835-0.961) and 0.896 (95%CI: 0.760-0.969) in the training group and the validation group, higher than that of any other models.

CONCLUSION: Model-Clinical-radiomics, which was based on Model-FLR, had good efficacy in predicting PHLF.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Xing Q, Cui Y, Liu M, et al. Prediction of post-hepatectomy liver failure risk in patients with colorectal cancer liver metastases utilizing gadoxetic acid-enhanced MRI radiomics with automatic segmentation and image registration. Abdom Radiol (NY). 2026. PMID: 42799748. doi:10.1007/s00261-026-05801-w

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。