Scholarlink

Objectives <p>This study aimed to develop an interpretable, domain-generalizable deep learning model for microvascular invasion (MVI) assessment in hepatocellular carcinoma (HCC).</p> Methods <p>Utilizing a retrospective dataset of 546 HCC patients from five centers, we developed and validated a clinical-radiological model and deep learning models aimed at MVI prediction. The models were developed on a dataset of 263 cases consisting of data from three centers, internally validated on a set of 66 patients, and externally tested on two independent sets. An adversarial network-based deep learning (AD-DL) model was developed to learn domain-invariant features from multiple centers within the training set. The area under the receiver operating characteristic curve (AUC) was calculated using pathological MVI status. With the best-performed model, early recurrence-free survival (ERFS) stratification was validated on the external test set by the log-rank test, and the differentially expressed genes (DEGs) associated with MVI status were tested on the RNA sequencing analysis of the Cancer Imaging Archive.</p> Results <p>The AD-DL model demonstrated the highest diagnostic performance and generalizability with an AUC of 0.793 in the internal test set, 0.801 in external test set 1, and 0.773 in external test set 2. The model’s prediction of MVI status also demonstrated a significant correlation with ERFS (<i>p</i> = 0.048). DEGs associated with MVI status were primarily enriched in the metabolic processes and the Wnt signaling pathway, and the epithelial-mesenchymal transition process.</p> Conclusions <p>The AD-DL model allows preoperative MVI prediction and ERFS stratification in HCC patients, which has a good generalizability and biological interpretability.</p> Critical relevance statement <p>The adversarial network-based deep learning model predicts MVI status well in HCC patients and demonstrates good generalizability. By integrating bioinformatics analysis of the model’s predictions, it achieves biological interpretability, facilitating its clinical translation.</p> Key Points <p><UnorderedList Mark="Bullet"> <ItemContent> <p>Current MVI assessment models for HCC lack interpretability and generalizability.</p> </ItemContent> <ItemContent> <p>The adversarial network-based model's performance surpassed clinical radiology and squeeze-and-excitation network-based models.</p> </ItemContent> <ItemContent> <p>Biological function analysis was employed to enhance the interpretability and clinical translatability of the adversarial network-based model.</p> </ItemContent> </UnorderedList></p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Interpretable and generalizable deep learning model for preoperative assessment of microvascular invasion and outcome in hepatocellular carcinoma based on MRI: a multicenter study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月3日

查看全文
  • Xue Dong,
  • Xibin Jia,
  • Wei Zhang,
  • Jingxuan Zhang,
  • Hui Xu,
  • Lixue Xu,
  • Caili Ma,
  • Hongjie Hu,
  • Jiawen Luo,
  • Jingfeng Zhang,
  • Zhenchang Wang,
  • Wenbin Ji,
  • Dawei Yang,
  • Zhenghan Yang

摘要

Objectives

This study aimed to develop an interpretable, domain-generalizable deep learning model for microvascular invasion (MVI) assessment in hepatocellular carcinoma (HCC).

Methods

Utilizing a retrospective dataset of 546 HCC patients from five centers, we developed and validated a clinical-radiological model and deep learning models aimed at MVI prediction. The models were developed on a dataset of 263 cases consisting of data from three centers, internally validated on a set of 66 patients, and externally tested on two independent sets. An adversarial network-based deep learning (AD-DL) model was developed to learn domain-invariant features from multiple centers within the training set. The area under the receiver operating characteristic curve (AUC) was calculated using pathological MVI status. With the best-performed model, early recurrence-free survival (ERFS) stratification was validated on the external test set by the log-rank test, and the differentially expressed genes (DEGs) associated with MVI status were tested on the RNA sequencing analysis of the Cancer Imaging Archive.

Results

The AD-DL model demonstrated the highest diagnostic performance and generalizability with an AUC of 0.793 in the internal test set, 0.801 in external test set 1, and 0.773 in external test set 2. The model’s prediction of MVI status also demonstrated a significant correlation with ERFS (p = 0.048). DEGs associated with MVI status were primarily enriched in the metabolic processes and the Wnt signaling pathway, and the epithelial-mesenchymal transition process.

Conclusions

The AD-DL model allows preoperative MVI prediction and ERFS stratification in HCC patients, which has a good generalizability and biological interpretability.

Critical relevance statement

The adversarial network-based deep learning model predicts MVI status well in HCC patients and demonstrates good generalizability. By integrating bioinformatics analysis of the model’s predictions, it achieves biological interpretability, facilitating its clinical translation.

Key Points

Current MVI assessment models for HCC lack interpretability and generalizability.

The adversarial network-based model's performance surpassed clinical radiology and squeeze-and-excitation network-based models.

Biological function analysis was employed to enhance the interpretability and clinical translatability of the adversarial network-based model.

Graphical Abstract