Scholarlink

Objective <p>The aim of this study was to develop a multimodal fusion model for accurate risk prediction and clinical decision support for ductal carcinoma in-situ (DCIS).</p> Method <p>By integrating deep learning (DL), radiomics and clinical features, this study constructed the combined model and validated its performance in a multicenter cohort containing 232 patients (103 in the training set, 43 in the validation set and 86 in the external test set).</p> Results <p>Unimodal DL models showed significant overfitting in external tests (e.g., DenseNet201 training set AUC = 0.85 vs. test set 1 AUC = 0.47), whereas the multimodal fusion model achieved optimal predictive performance across cohorts through heterogeneous data synergy (training set AUC = 0.925, test set 2 AUC = 0.801) with the DeLong test confirmed that it significantly outperformed the unimodal model (<i>P</i> &lt; 0.05). Grad-CAM visualization showed that the model focus region was highly consistent with the radiologist annotation (81% overlap, Cohen’s κ = 0.68). Calibration curves (Hosmer-Leeshawn test <i>P</i> &gt; 0.05) and decision curve analysis (DCA) validated the model prediction reliability (error &lt; 5%) with a net clinical benefit advantage (net benefit difference of 7% to 28% at thresholds of 5% to 80%).</p> Conclusion <p>The multimodal fusion strategy could potentially mitigate the limitations of unimodal models, presenting a potential solution with promising high accuracy and interpretability for individualized diagnosis and treatment of DCIS.</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

Prediction of intraductal cancer microinfiltration based on the hierarchical fusion of peri-tumor imaging histology and dual view deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月14日

查看全文
  • Guoyan Yao,
  • Yan Huang,
  • Xiaojing Shang,
  • Lei Guo,
  • Jieping Feng,
  • Zhongqiu Lai,
  • Weikang Huang,
  • Jianye Lu,
  • Lijun Chen,
  • Minan zheng

摘要

Objective

The aim of this study was to develop a multimodal fusion model for accurate risk prediction and clinical decision support for ductal carcinoma in-situ (DCIS).

Method

By integrating deep learning (DL), radiomics and clinical features, this study constructed the combined model and validated its performance in a multicenter cohort containing 232 patients (103 in the training set, 43 in the validation set and 86 in the external test set).

Results

Unimodal DL models showed significant overfitting in external tests (e.g., DenseNet201 training set AUC = 0.85 vs. test set 1 AUC = 0.47), whereas the multimodal fusion model achieved optimal predictive performance across cohorts through heterogeneous data synergy (training set AUC = 0.925, test set 2 AUC = 0.801) with the DeLong test confirmed that it significantly outperformed the unimodal model (P < 0.05). Grad-CAM visualization showed that the model focus region was highly consistent with the radiologist annotation (81% overlap, Cohen’s κ = 0.68). Calibration curves (Hosmer-Leeshawn test P > 0.05) and decision curve analysis (DCA) validated the model prediction reliability (error < 5%) with a net clinical benefit advantage (net benefit difference of 7% to 28% at thresholds of 5% to 80%).

Conclusion

The multimodal fusion strategy could potentially mitigate the limitations of unimodal models, presenting a potential solution with promising high accuracy and interpretability for individualized diagnosis and treatment of DCIS.