文献速递腹部技术与安全CT

基于CT的多模态深度学习模型早期预测肝硬化不良结局

Early prediction of adverse outcomes in liver cirrhosis using a CT-based multimodal deep learning model.
PubMed 文献 · Abdom Radiol (NY) · 2025-06-27

本研究为回顾性两中心研究,纳入243例早期肝硬化患者,开发整合平扫腹部CT图像、肝脾影像组学特征及临床文本的三模态融合深度学习网络TMF-LCNet预测不良结局。训练队列AUC为0.797,外部测试队列AUC为0.747,仅TMF-LCNet在两个队列中均表现出稳健的模型校准,影像模态贡献最大。

要点

  • TMF-LCNet在训练队列AUC为0.797、外部测试队列AUC为0.747。
  • 仅TMF-LCNet在两个队列中均表现出稳健的模型校准。
  • 影像模态贡献最大,影像单模态版本AUC为0.723和0.716,与完整版本无显著差异(p > 0.05)。

核心结论

  • TMF-LCNet通过整合多种数据类型,是预测早期肝硬化不良结局的准确且稳健的工具,具有早期识别高风险患者、指导及时干预并最终改善患者预后的潜力。

研究设计与样本

  • 回顾性研究,纳入两个中心共243例早期肝硬化患者,训练队列184例,外部测试队列59例。

诊断标准与关键数值

  • TMF-LCNet训练队列AUC为0.797,外部测试队列AUC为0.747;影像单模态版本AUC分别为0.723和0.716,与完整版本差异无统计学意义(p > 0.05)。

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: Early-stage cirrhosis frequently presents without symptoms, making timely identification of high-risk patients challenging. We aimed to develop a deep learning-based triple-modal fusion liver cirrhosis network (TMF-LCNet) for the prediction of adverse outcomes, offering a promising tool to enhance early risk assessment and improve clinical management strategies.

METHODS: This retrospective study included 243 patients with early-stage cirrhosis across two centers. Adverse outcomes were defined as the development of severe complications like ascites, hepatic encephalopathy and variceal bleeding. TMF-LCNet was developed by integrating three types of data: non-contrast abdominal CT images, radiomic features extracted from liver and spleen, and clinical text detailing laboratory parameters and adipose tissue composition measurements. TMF-LCNet was compared with conventional methods on the same dataset, and single-modality versions of TMF-LCNet were tested to determine the impact of each data type. Model effectiveness was measured using the area under the receiver operating characteristics curve (AUC) for discrimination, calibration curves for model fit, and decision curve analysis (DCA) for clinical utility.

RESULTS: TMF-LCNet demonstrated superior predictive performance compared to conventional image-based, radiomics-based, and multimodal methods, achieving an AUC of 0.797 in the training cohort (n = 184) and 0.747 in the external test cohort (n = 59). Only TMF-LCNet exhibited robust model calibration in both cohorts. Of the three data types, the imaging modality contributed the most, as the image-only version of TMF-LCNet achieved performance closest to the complete version (AUC = 0.723 and 0.716, respectively; p > 0.05). This was followed by the text modality, with radiomics contributing the least, a pattern consistent with the clinical utility trends observed in DCA.

CONCLUSION: TMF-LCNet represents an accurate and robust tool for predicting adverse outcomes in early-stage cirrhosis by integrating multiple data types. It holds potential for early identification of high-risk patients, guiding timely interventions, and ultimately improving patient prognosis.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Xie N, Liang Y, Luo Z, et al. Early prediction of adverse outcomes in liver cirrhosis using a CT-based multimodal deep learning model. Abdom Radiol (NY). 2025. PMID: 40576670. doi:10.1007/s00261-025-05045-0

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。