文献速递腹部泌尿生殖US

基于CLIP的多模态直肠腔内超声模型预测直肠癌异时性肝转移

A CLIP-Based Multimodal Endorectal Ultrasound Model for Predicting Metachronous Liver Metastases in Rectal Cancer.
PubMed 文献 · Acad Radiol · 2026-08-06

这项两中心回顾性研究纳入394例直肠癌患者,利用Chinese-CLIP整合治疗前多平面三维直肠腔内超声图像与报告,预测根治术后异时性肝转移。融合模型在训练、内部验证及外部验证队列中AUC分别为0.812、0.850和0.808,较单纯临床模型和多模态模型均有所提升。

要点

  • 多模态模型整合3D-ERUS图像与报告可用于直肠癌术后肝转移风险分层
  • 融合临床病理信息可进一步提高预测效能,尤其内部验证队列AUC达0.850
  • 矢状面、冠状面及横断面3D-ERUS图像均可作为模型输入进行编码分析

核心结论

  • 基于Chinese-CLIP整合多平面3D-ERUS图像与报告的模型对直肠癌异时性肝转移预测具有潜在价值
  • 融合临床病理信息的多模态模型可进一步改善风险分层能力

研究设计与样本

  • 两中心回顾性研究,共纳入394例直肠癌患者,均在治疗前两周内接受3D-ERUS检查并后续行根治性手术
  • 中心1分为训练队列238例和内部验证队列102例,中心2作为外部验证队列54例
  • 训练、内部验证及外部验证队列中发生异时性肝转移的患者数分别为43例、19例和5例
  • 采用Chinese-CLIP对矢状面、冠状面和横断面ERUS图像及对应报告进行编码
  • 经特征选择后构建平衡逻辑回归模型,并进一步建立临床病理融合模型

关键影像表现/征象

  • 模型输入为治疗前多平面三维直肠腔内超声图像,包括矢状面、冠状面和横断面,显示直肠癌原发灶的灰阶超声形态特征
  • 对应ERUS报告中描述的原发灶超声征象与图像信息共同纳入多模态建模

诊断标准与关键数值

  • 多模态模型在训练、内部验证及外部验证队列中的AUC分别为0.779、0.824和0.743
  • 融合模型在训练、内部验证及外部验证队列中的AUC分别为0.812、0.850和0.808
  • 融合模型较临床模型在训练队列中IDI=0.085、连续NRI=0.647,在内部验证队列中IDI=0.114、连续NRI=0.865
  • 与多模态模型比较,融合模型在训练队列和内部验证队列中IDI进一步改善

临床应用与阅片要点

  • 对直肠癌患者治疗前3D-ERUS图像及报告进行系统编码可为术后异时性肝转移风险提供影像组学评估
  • 临床决策中可结合3D-ERUS多模态特征与临床病理因素综合判断转移风险,辅助随访策略制定
  • 矢状面、冠状面和横断面图像均应留存并评估,以保证多平面信息完整用于模型输入

局限性

  • 外部验证队列样本量较小,仅54例,其中发生异时性肝转移的仅5例
  • 两中心回顾性设计本身存在选择偏倚和外部推广性受限的局限

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

OBJECTIVE: To develop and externally validate a contrastive language-image pretraining (CLIP)-based multimodal model integrating pretreatment multiplanar three-dimensional endorectal ultrasound (3D-ERUS) images and ERUS reports for predicting metachronous liver metastasis (MLM) after radical surgery in rectal cancer.

METHODS: This two-center retrospective study included 394 patients with rectal cancer who underwent pretreatment 3D-ERUS within two weeks before treatment and subsequent radical surgery. Patients from center 1 were divided into training (n = 238) and internal validation (n = 102) cohorts, and center 2 served as an external validation cohort (n = 54). MLM occurred in 43, 19, and 5 patients, respectively. Sagittal, coronal, and transverse ERUS images and corresponding reports were encoded using Chinese-CLIP. After feature selection, balanced logistic regression models were developed, and a clinicopathological fusion model was constructed. Performance was assessed using AUC, Brier score, DeLong test, integrated discrimination improvement (IDI), and category-free continuous net reclassification improvement (NRI).

RESULTS: The multimodal model achieved AUCs of 0.779, 0.824, and 0.743 in the three cohorts. The fusion model achieved higher AUCs of 0.812, 0.850, and 0.808. Compared to the clinical model, the fusion model significantly improved IDI and continuous NRI in the training cohort (IDI = 0.085; NRI = 0.647) and internal validation cohort (IDI = 0.114; NRI = 0.865). Compared to the multimodal model, the fusion model further improved IDI in both cohorts.

CONCLUSION: Chinese-CLIP-based integration of multiplanar 3D-ERUS images and reports showed potential for MLM prediction. Clinicopathological fusion may further improve risk stratification, warranting larger external validation.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Yi, Liu, Zhang, et al. A CLIP-Based Multimodal Endorectal Ultrasound Model for Predicting Metachronous Liver Metastases in Rectal Cancer. Acad Radiol. 2026. PMID: 42562717. doi:10.1016/j.acra.2026.07.042

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。