Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma by Integrating Multimodal Ultrasound and Clinical Data: A Multicenter Study

📄 arXiv: 2609.24524v1 📥 PDF

作者: Jun Cheng, Yuanyuan Kong, Qing Huang, Xiaotong Tan, Licong Dong, Yulong Han, Wufeng Xue, Ruobing Huang, Dong Ni, Qi Yang, Jie Yu, Ping Liang

分类: cs.CV

发布日期: 2026-09-21

备注: Main manuscript: 37 pages, 5 figures, and 4 tables; supplemental material: 18 pages, 6 figure, and 9 tables


💡 一句话要点

提出多模态超声与临床数据融合模型以预测肝细胞癌微血管侵犯

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 微血管侵犯 肝细胞癌 多模态融合 动态对比增强超声 临床数据 术前预测 机器学习

📋 核心要点

  1. 现有的微血管侵犯诊断依赖术后组织病理学,缺乏有效的术前预测方法,限制了临床决策。
  2. 本文提出了一种多模态信息融合网络,通过整合超声成像和临床数据,提升术前MVI预测的准确性。
  3. 在外部验证中,融合模型的AUC达到0.8953,显著高于单一模态,展示了该方法的有效性和潜力。

📝 摘要(中文)

微血管侵犯(MVI)是肝细胞癌(HCC)复发和生存的预测因子,但目前需要术后组织病理学诊断。本文开发并验证了一种融合多模态超声和临床数据的模型,以实现术前MVI预测。研究纳入了来自八个中心的489名HCC患者,采用B超、彩色多普勒流动成像、动态对比增强超声及临床信息。模型开发使用了七个中心的数据(n=421),并通过五折交叉验证,剩余中心的数据(n=68)用于独立外部验证。结果显示,动态对比增强超声在单一模态下的AUC最高(0.8545),而融合模型的AUC达到了0.8953,准确率为81.18%。

🔬 方法详解

问题定义:本研究旨在解决肝细胞癌(HCC)术前微血管侵犯(MVI)预测的不足,现有方法依赖术后病理学,缺乏实时、有效的预测手段。

核心思路:通过整合多模态超声成像(包括B超、彩色多普勒流动成像和动态对比增强超声)与临床数据,构建一个综合模型,以提高MVI的术前预测能力。

技术框架:研究采用了多模态信息融合网络,包含模态特定编码器、血流动力学时间变化模块和表示一致性学习模块,最后通过Transformer进行融合。

关键创新:提出的模型通过引入时间变化模块和像素差异采样,显著提升了对动态对比增强超声数据的利用效率,与传统方法相比具有更好的性能。

关键设计:模型使用了五折交叉验证进行训练,损失函数设计为适应多模态数据的特性,网络结构中采用了Transformer以增强信息融合能力。具体参数设置和网络结构细节在实验中进行了优化。

🖼️ 关键图片

img_0
img_1
img_2

📊 实验亮点

在外部验证中,动态对比增强超声的AUC为0.8545,而融合模型的AUC达到了0.8953,准确率为81.18%。该模型在敏感性和特异性方面均表现出色,分别为86.40%和78.14%。

🎯 应用场景

该研究的成果可广泛应用于肝细胞癌的术前评估,帮助医生进行风险分层和个性化治疗决策,提升患者的生存率和生活质量。未来,该模型也可能推广到其他类型肿瘤的预测和诊断中。

📄 摘要(原文)

Background: Microvascular invasion (MVI) predicts recurrence and survival in hepatocellular carcinoma (HCC) but requires postoperative histopathology for diagnosis. We developed and validated a model integrating multimodal ultrasound and clinical data for preoperative MVI prediction. Methods: This multicenter study included 489 patients with HCC from eight centers. All patients had B-mode ultrasound (BUS), color Doppler flow imaging (CDFI), dynamic contrast-enhanced ultrasound (DCE-US), and clinical information. Data from seven centers (n = 421) were used for model development with five-fold cross-validation; data from the remaining center (n = 68) formed an independent external validation cohort. The proposed multimodal information fusion network used modality-specific encoders, a hemodynamic temporal change module for bidirectional DCE-US perfusion changes, and a representation consistency learning module to align heterogeneous ultrasound representations before Transformer-based fusion. Results: In external validation, DCE-US achieved the highest single-modality area under the receiver operating characteristic curve (AUC; 0.8545+/-0.0198), versus clinical information (0.6715+/-0.0156), CDFI (0.6435+/-0.0344), and BUS (0.6087+/-0.0417). Pixel-difference sampling and the proposed temporal module outperformed alternative sampling and video representation methods. The full model achieved the best performance, with an AUC of 0.8953+/-0.0180, accuracy of 81.18%+/-2.83%, sensitivity of 86.40%+/-6.69%, and specificity of 78.14%+/-6.28. Conclusions: Integrating multimodal ultrasound and clinical information enabled promising preoperative MVI prediction in HCC. DCE-US was the main source of predictive information, while BUS, CDFI, and clinical information provided complementary value. The proposed framework may support preoperative risk stratification and individualized clinical decision-making.