首页 文献索引 SCI期刊 AI助手
首页 正文

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology. 2025 Jun 6;51(9):110219. doi: 10.1016/j.ejso.2025.110219 Q23.52024

Improved diagnostic decision making for microvascular invasion in HCC using a novel nomogram incorporating delta radiomics and body composition factors: A multicenter study

一种新的列线图结合增量组学和体组成因素可改善HCC微血管侵犯的诊断决策：一项多中心研究 翻译改进

Li Zhang  1, Houying Li  2, Zhengjun Dai  3, Fang Zhao  4, Xiaoxiao Liu  5, Yifan Yu  6, Guodong Pang  7

作者单位 +展开

作者单位

  • 1 Department of Radiology,The Second Hospital of Shangdong University,jinan, shangdong 250033, China. Electronic address: m510417@126.com.
  • 2 Department of Radiology,The Second Hospital of Shangdong University,jinan, shangdong 250033, China. Electronic address: 280494368@qq.com.
  • 3 Department of Scientific Research Department, Huiying Medical Technology Co, Ltd, Beijing, 100192, China. Electronic address: daizhengjun@huiyihuiying.com.
  • 4 Department of Radiology, Qilu Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, 250012, China. Electronic address: zhaofang27@126.com.
  • 5 Department of Radiology, Shandong Provincial Hospital, Cheeloo College of Medicine, Shandong University, Jinan, Shandong, 250021, China. Electronic address: 18866502028@163.com.
  • 6 Department of Epidemiology and Health Statistics, School of Public Health, Cheeloo College of Medicine, Shandong University, Jinan, shangdong, 250000, China; Institute for Medical Dataology, Cheeloo College of Medicine, Shandong University, Jinan, shangdong, 250000, China. Electronic address: yuyifan@163.com.
  • 7 Department of Radiology,The Second Hospital of Shangdong University,jinan, shangdong 250033, China. Electronic address: pgd226@aliyun.com.

    • DOI: 10.1016/j.ejso.2025.110219 PMID: 40505357

    摘要 中英对照阅读

    Objective: To develop and validate machine learning(ML) models based on delta-radiomics features and body composition factors for early prediction of microvascular invasion(MVI) in patients with hepatocellular carcinoma(HCC) using a multicenter cohort,and to identify differentially expressed genes(DEGs).

    Methods: This retrospective study included pathologically-confirmed HCC patients diagnosed at three centers.Radiomic features were extracted from MRI images,and delta-radiomics features were calculated.Clinical-radiological features, body composition factors and delta-radiomics score were selected through various feature selection methods and a nomogram was built based on the independent risk factors.The performance of the nomogram was assessed with the area under the receiver operating characteristic curve (AUC).Recurrence-free survival(RFS) analysis was assessed by the Kaplan-Meier analysis and compared using the log-rank test.Additionally, gene expression analysis was conducted to explore molecular mechanisms underlying MVI.

    Results: The nomogram demonstrated numerically superior predictive performance in both external test sets, achieving AUCs of 0.853 (test set1) and 0.852 (test set2). The Delong test revealed the nomogram demonstrated robust predictive performance across both external test set, compared to the clinical model (test set1: 0.853 vs 0.790; test set2: 0.852 vs 0.774; both p < 0.05). No statistically significant difference was observed between the nomogram and delta-radiomics model(p > 0.05).The nomogram's implementation enhanced radiologists' diagnostic accuracy for MVI by up to 13.4 percentage points.The nomogram can categorize recurrence-free survival.DEGs associated with MVI are related to cell proliferation and glucose metabolism.

    Conclusion: The ML models established via body composition factors and delta-radiomics scores had the best performance to predict MVI status,and help improve the diagnostic capability of radiologists.

    Keywords: Body composition factors; Delta-radiomics; Hepatocellular carcinoma; Microvascular invasion.

    Keywords：diagnostic decision making; microvascular invasion; HCC; nomogram; radiomics

    目标：基于多中心队列，利用变化放射组学特征和身体组成因素开发并验证用于早期预测肝细胞癌（HCC）患者微血管侵犯（MVI）的机器学习（ML）模型，并识别差异表达基因。

    方法：这项回顾性研究包括在三个中心确诊的病理证实的HCC患者。从MRI图像中提取放射组学特征并计算变化放射组学特征。通过各种特征选择方法选择临床-影像学特征、身体组成因素和变化放射组学评分，并基于独立风险因素构建预测模型（nomogram）。使用受试者工作特征曲线下的面积（AUC）评估nomogram的性能。无复发生存期（RFS）分析采用Kaplan-Meier分析并通过log-rank检验进行比较。此外，还进行了基因表达分析以探讨MVI的分子机制。

    结果：nomogram在两个外部测试集中表现出数值上更优越的预测性能，在测试集1中AUC为0.853，在测试集2中AUC为0.852。Delong检验显示，相比临床模型（测试集1：0.853 vs 0.790；测试集2：0.852 vs 0.774；p值均小于0.05），nomogram在两个外部测试集中表现出强大的预测性能。nomogram与delta放射组学模型之间无统计学显著差异（p > 0.05）。Nomogram的实施可将放射科医生对MVI诊断准确率提高最多13.4个百分点。Nomogram可以分类无复发生存期。与MVI相关的差异表达基因与细胞增殖和葡萄糖代谢有关。

    结论：基于身体组成因素和变化放射组学评分建立的ML模型预测MVI状态的效果最佳，有助于提高放射科医生的诊断能力。

    关键词：身体组成因素；变化放射组学；肝细胞癌；微血管侵犯。

    关键词：诊断决策制定; 微血管侵犯; 肝细胞癌; 预测模型; 影像组学

    翻译效果不满意？ 用Ai改进或 寻求AI助手帮助 ，对摘要进行重点提炼
    Copyright © European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology. 中文内容为AI机器翻译，仅供参考！

    相关内容

    期刊名：Ejso

    缩写：EJSO-EUR J SURG ONC

    ISSN：0748-7983

    e-ISSN：1532-2157

    IF/分区：3.5/Q2

    文章目录 更多期刊信息

    全文链接
    官方链接
    PMC全文
    引文链接
    复制
    已复制！
    推荐内容
    Improved diagnostic decision making for microvascular invasion in HCC using a novel nomogram incorporating delta radiomics and body composition factors: A multicenter study