列线图与深度学习模型预测肝细胞癌病理分级的稳健性:双侧跨中心验证
本研究回顾性分析两个中心601例病理确诊HCC患者的2404张术前超声图像,比较列线图与深度学习模型预测病理分级的性能。列线图内外验证AUC分别为0.771/0.762(中心1训练)和0.814/0.818(中心2训练),而深度学习模型外部验证AUC降至0.599-0.646和0.620-0.657。结论认为列线图在异质人群中的稳健性和泛化性优于深度学习模型。
要点
- 列线图跨中心外部验证AUC保持0.762-0.818,稳健性优于深度学习模型。
- 深度学习模型内部验证AUC可达0.809,但外部验证显著下降至0.599-0.657。
- 基于超声影像特征联合临床变量的列线图更适合数据分布多变场景。
核心结论
- 列线图在异质临床人群中预测HCC病理分级的稳健性和泛化性优于深度学习模型。
- 深度学习模型外部验证性能显著下降,提示数据多样性有限时基于特征的方法更有价值。
研究设计与样本
- 回顾性分析两个医疗中心601例病理确诊HCC患者的2404张术前超声图像。
- 建模策略包括两个整合超声影像特征(B模式和CEUS)与临床变量的列线图,以及基于B模式、CEUS动脉期、门脉期、延迟期和B+CEUS联合的系列深度学习模型。
- 采用双侧交叉中心验证:中心1数据按7:3分为训练集和内部验证集,中心2全部数据作为外部测试集,并反向重复此过程。
- 模型性能评估采用AUC、校准曲线和决策曲线分析。
诊断标准与关键数值
- 列线图训练于中心1时内部验证AUC为0.771,外部验证AUC为0.762。
- 列线图训练于中心2时内部验证AUC为0.814,外部验证AUC为0.818。
- 深度学习模型训练于中心1时内部验证AUC为0.632-0.809,外部验证AUC为0.599-0.646。
- 深度学习模型训练于中心2时内部验证AUC为0.692-0.767,外部验证AUC为0.620-0.657。
临床应用与阅片要点
- 在数据分布多变或跨中心场景下,可优先考虑基于超声影像特征联合临床变量的列线图进行HCC病理分级预测。
- 深度学习模型内部性能高但外部泛化性有限,临床部署前需充分外部验证。
局限性
- 原文未明确报告研究局限性。
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: This study aimed to compare the performance of nomograms and deep learning (DL) models in predicting the pre-operative pathological grade of hepatocellular carcinoma (HCC) using clinical data and ultrasound images, with an emphasis on model robustness and generalizability across institutions.
METHODS: We retrospectively analyzed 2404 pre-operative ultrasound images from 601 patients with pathologically confirmed HCC across two medical centers. Two distinct modeling strategies were employed: two nomograms integrating ultrasound imaging features (B-mode and contrast-enhanced ultrasound [CEUS]) with clinical variables, and a series of DL models based on B-mode, CEUS at arterial phases, portal phases and delayed phases, and a combined B + CEUS modality. Independent predictors of pathological grade were identified using univariate, Least Absolute Shrinkage and Selection Operator and logistic regression and incorporated into the nomograms. To rigorously assess generalizability, bilateral training and a cross-center validation strategy were implemented: data from Center 1 were split 7:3 for training and internal validation, while all data from Center 2 served as an external test set. This process was reversed (i.e., training on Center 2 and testing on Center 1) to complete the bilateral cross-center validation. Model performance was evaluated using the area under the curve (AUC), calibration curves and decision curve analysis.
RESULTS: The nomograms demonstrated strong and consistent performance in predicting HCC pathological grade, with AUCs of 0.771 (internal validation) and 0.762 (external validation) when trained on Center 1 data, and AUCs of 0.814 (internal) and 0.818 (external) when trained on Center 2 data. In contrast, DL models showed high internal performance (AUCs: 0.632-0.809 for Center 1; 0.692-0.767 for Center 2) but experienced significant degradation on external validation (AUCs: 0.599-0.646 and 0.620-0.657, respectively).
CONCLUSION: The nomogram exhibited superior robustness and generalizability compared to DL models in heterogeneous clinical populations. These findings highlight the practical advantage of interpretable statistical models in settings with variable data distributions and reinforce the value of feature-based approaches when data diversity is limited.
引用
- Zhao Z, Zhang W, Zhu Y, et al. Robustness of Nomogram Versus Deep Learning Models for Hepatocarcinoma Grading: Insights From a Bilateral Cross-Center Validation. Ultrasound Med Biol. 2026. PMID: 42888053. doi:10.1016/j.ultrasmedbio.2026.09.014
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。