文献速递肝病消化道肿瘤与早癌消化内镜

可生物学解释的多模态模型预测肝癌局部肿瘤进展与侵袭性

Biologically explicable multimodal model predicting local tumor progression and tumor invasiveness of hepatocellular carcinoma.
PubMed 文献 · Hepatology · 2026-01-15

本研究基于1208个肝细胞癌病灶构建多模态模型,融合超声造影、磁共振、生物学与临床信息,预测热消融后局部肿瘤进展。模型在内外部测试集AUC分别为0.809和0.811,高侵袭组血管生成、应激耐受和转移通路上调,8mm最小消融边缘可降低高侵袭组局部进展率。

要点

  • 多模态模型可分类肝癌侵袭性,内外部测试集AUC分别为0.809和0.811。
  • 高侵袭组CK-7、GPC-3阳性率及VEGFA、MMP-9、HSPA1A表达升高。
  • 8mm最小消融边缘使高侵袭组局部进展率由42.4%降至10.5%。

核心结论

  • 多模态模型在肝癌侵袭性分类上表现满意,并为高侵袭肿瘤提供降低局部进展的有效策略。

研究设计与样本

  • 回顾性收集2015年1月至2023年8月1208个肝细胞癌病灶,分为训练集502例、验证集180例、内部测试集250例和外部测试集276例。
  • 收集超声造影、磁共振、生物学、临床和预后信息构建模型,采用长短期记忆网络和影像组学提取图像特征,逻辑回归整合图像与临床信息。

主要发现

  • 多模态模型在内部和外部测试集的AUC分别为0.809和0.811。
  • 高侵袭组分化更低、微血管侵犯比例更高、巨梁状-团块型肝癌比例更高,CK-7和GPC-3阳性率更高,VEGFA、MMP-9和HSPA1A表达增加(均p<0.05)。
  • KEGG和GSEA分析显示高侵袭组血管生成、应激耐受和肿瘤转移相关通路上调。
  • 外部测试集中,8mm最小消融边缘使高侵袭组局部进展发生率从42.4%降至10.5%(p=0.027),与低侵袭组(10.5% vs. 6.1%,p=0.613)相当。

关键数值与推荐

  • 多模态模型内外部测试集AUC分别为0.809和0.811。
  • 高侵袭组与低侵袭组比较,CK-7、GPC-3阳性率及VEGFA、MMP-9、HSPA1A表达差异均p<0.05。
  • 8mm最小消融边缘使高侵袭组局部进展率从42.4%降至10.5%(p=0.027)。

临床怎么用

  • 可参考多模态模型评估肝癌热消融前侵袭性,对高侵袭且位置安全的肿瘤考虑8mm最小消融边缘以降低局部进展。

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)。

原文

BACKGROUND AND AIMS: Local tumor progression (LTP) of hepatocellular carcinoma (HCC) after thermal ablation (TA) is associated with tumor invasiveness and poses a significant threat to patient outcomes. We aim to build a multimodal model to explicable tumor invasiveness and reduce LTP. APPROACH AND RESULTS: From January 2015 to August 2023, 1208 HCC lesions were collected as training (n=502), validation (n=180), internal test (n=250), and external test (n=276) sets. Contrast-enhanced ultrasound (CEUS), magnetic resonance imaging (MRI), biological, clinical, and prognostic information were collected to build the model. A long short-term memory network and radiomics were used to extract image features. Logistic regression was used to combine image and clinical information. Pathological, immunohistochemical, and RNA sequencing analyses were used to explicable tumor invasiveness. Moderation analysis was applied to determine an appropriate minimum ablation margin (MAM) for high-invasiveness tumors in a safe location to reduce LTP. AUC of the multimodal model was 0.809 and 0.811 in internal and external test sets, respectively. The high-invasiveness group showed lower differentiation, higher microvascular invasion proportion, macrotrabecular-massive HCC proportion, CK-7 and GPC-3 positive rate, and increased expression of VEGFA, MMP-9, and HSPA1A (all p<0.05). KEGG and GSEA analyses revealed the upregulation of pathways related to angiogenesis, tolerance to stress response, and tumor metastasis in high-invasiveness group. The 8-mm MAM ablation strategy can effectively decrease the LTP incidence of high-invasiveness group (from 42.4% to 10.5%, p=0.027) to the level comparable to low-invasiveness group (10.5% vs. 6.1%, p=0.613) in external test set. CONCLUSIONS: The multimodal model achieved satisfactory performance on classifying tumor invasiveness, and provided effective strategy for high-invasiveness tumors to reduce LTP occurrence.

来源:Hepatology,查看原文。版权归原作者所有。

引用

  1. Ding W, Wu J, Dou J, et al. Biologically explicable multimodal model predicting local tumor progression and tumor invasiveness of hepatocellular carcinoma. Hepatology. 2026. PMID: 41538135. doi:10.1097/HEP.0000000000001678

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。