Scholarlink

Purpose <p>This study aimed to develop and validate a robust multicenter deep learning pipeline that integrates radiomic descriptors with deep feature embeddings to enable comprehensive ovarian tumor analysis from ultrasound imaging, encompassing segmentation, multi-class classification, and prognostic prediction.</p> Methods <p>Ultrasound data from 3156 patients across eight centers were retrospectively analyzed. Five segmentation networks (UNETR, nnU-Net, Swin-UNet, SegNet, UNet) were trained to delineate tumors. From segmented regions, handcrafted radiomic features and deep features (ResNet, Vision Transformer (ViT)) were extracted. After reproducibility filtering (intraclass correlation coefficient (ICC) ≥ 0.75) and dimensionality reduction (PCA, RFE, ANOVA), three classifiers (TabTransformer, MLP, XGBoost) were trained for six-class categorization. Progression-free survival (PFS) was predicted using regression models. External validation was performed on 756 patients.</p> Results <p>UNETR achieved the best segmentation performance (DSC: 96.2%). For classification, the combined feature model with RFE and TabTransformer reached the highest accuracy (training AUC: 98.0%; external AUC: 95.8%; accuracy: 94.0%). For prognosis, TabTransformer achieved the best performance (<i>C</i>-index: 0.847), with consistent generalization across centers. Kaplan–Meier analysis confirmed significant survival group separation (<i>p</i> &lt; 0.001).</p> Conclusion <p>The proposed framework shows strong potential to reduce inter-operator variability and support personalized clinical decision-making in ovarian cancer care.</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

A multicenter deep learning framework integrating radiomics and vision transformers for comprehensive ovarian tumor analysis from ultrasound imaging

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月11日

查看全文
  • Xujiao Ji,
  • Caier Liu,
  • Jing Hu,
  • Sufen Li,
  • Lijun Wang,
  • Xin Cheng,
  • Cong Liu,
  • Yanjing Zhang

摘要

Purpose

This study aimed to develop and validate a robust multicenter deep learning pipeline that integrates radiomic descriptors with deep feature embeddings to enable comprehensive ovarian tumor analysis from ultrasound imaging, encompassing segmentation, multi-class classification, and prognostic prediction.

Methods

Ultrasound data from 3156 patients across eight centers were retrospectively analyzed. Five segmentation networks (UNETR, nnU-Net, Swin-UNet, SegNet, UNet) were trained to delineate tumors. From segmented regions, handcrafted radiomic features and deep features (ResNet, Vision Transformer (ViT)) were extracted. After reproducibility filtering (intraclass correlation coefficient (ICC) ≥ 0.75) and dimensionality reduction (PCA, RFE, ANOVA), three classifiers (TabTransformer, MLP, XGBoost) were trained for six-class categorization. Progression-free survival (PFS) was predicted using regression models. External validation was performed on 756 patients.

Results

UNETR achieved the best segmentation performance (DSC: 96.2%). For classification, the combined feature model with RFE and TabTransformer reached the highest accuracy (training AUC: 98.0%; external AUC: 95.8%; accuracy: 94.0%). For prognosis, TabTransformer achieved the best performance (C-index: 0.847), with consistent generalization across centers. Kaplan–Meier analysis confirmed significant survival group separation (p < 0.001).

Conclusion

The proposed framework shows strong potential to reduce inter-operator variability and support personalized clinical decision-making in ovarian cancer care.