Scholarlink

Purpose <p>Accurate preoperative prediction of preserved renal parenchymal volume (RPV) following partial nephrectomy (PN) is critical for individualized postoperative management. However, current assessment approaches remain limited in precision and generalizability. This study aimed to develop and validate a CT-based multilevel feature model for accurate preoperative prediction of postoperative preserved RPV after PN.</p> Methods <p>In this retrospective study, 185 patients who underwent PN at Sun Yat-sen University Cancer Center between 2019 and 2023 were included. A nnUNetV2-based segmentation model was used to automatically delineate renal parenchyma and tumors, generating reference postoperative RPVs. Regions of interest were constructed, and three hierarchical feature sets were extracted: (1) radiomic features using PyRadiomics after variance and correlation filtering, (2) handcrafted features derived from R.E.N.A.L. nephrometry score–weighted image dilation, and (3) deep learning (DL) features obtained from a dedicated network with principal component analysis (PCA) dimensionality reduction. Ten machine and deep learning regressors were trained using five-fold cross-validation and compared against clinician-derived RPV estimates. Feature importance was evaluated using Shapley additive explanations (SHAP).</p> Results <p>The segmentation model achieved a mean Dice similarity coefficient of 0.93, indicating high delineation accuracy. Among all regressors, the TabPFN model yielded the best predictive performance. Models using radiomic features alone achieved an <i>R²</i> of 0.873 and a mean absolute percentage error (<i>MAPE</i>) of 6.8%; performance improved with the inclusion of handcrafted features (<i>R²</i>=0.883, <i>MAPE</i> = 6.7%) and further with DL features (<i>R²</i> = 0.900, <i>MAPE</i> = 6.4%), significantly outperforming manual clinical estimates (<i>R²</i>=0.780, <i>MAPE</i> = 9.7%). SHAP analysis demonstrated that all three feature levels contributed substantially to the overall prediction accuracy.</p> Conclusion <p>The proposed CT-based multilevel feature model enables highly accurate preoperative prediction of postoperative preserved RPV following PN, significantly outperforming conventional clinical assessments. This model offers a robust, interpretable framework to support precision surgical planning and personalized renal function preservation strategies.</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

Preoperative prediction of preserved renal parenchymal volume via multilevel CT feature fusion: a proof-of-concept study

  • 期刊论文

  • 发表日期：

    2026年2月20日

查看全文
  • Zhiming Wu,
  • Wenjie Liang,
  • Jiamin Zeng,
  • Shaohan Yin,
  • Rongliang Zheng,
  • Deling Wang,
  • Chenyu Zhang,
  • Jiahao Wen,
  • Anping Liu,
  • Chunxiu Chen,
  • Yejing Liang,
  • Qiyu Liu,
  • Daqi Chen,
  • Yunlin Ye

摘要

Purpose

Accurate preoperative prediction of preserved renal parenchymal volume (RPV) following partial nephrectomy (PN) is critical for individualized postoperative management. However, current assessment approaches remain limited in precision and generalizability. This study aimed to develop and validate a CT-based multilevel feature model for accurate preoperative prediction of postoperative preserved RPV after PN.

Methods

In this retrospective study, 185 patients who underwent PN at Sun Yat-sen University Cancer Center between 2019 and 2023 were included. A nnUNetV2-based segmentation model was used to automatically delineate renal parenchyma and tumors, generating reference postoperative RPVs. Regions of interest were constructed, and three hierarchical feature sets were extracted: (1) radiomic features using PyRadiomics after variance and correlation filtering, (2) handcrafted features derived from R.E.N.A.L. nephrometry score–weighted image dilation, and (3) deep learning (DL) features obtained from a dedicated network with principal component analysis (PCA) dimensionality reduction. Ten machine and deep learning regressors were trained using five-fold cross-validation and compared against clinician-derived RPV estimates. Feature importance was evaluated using Shapley additive explanations (SHAP).

Results

The segmentation model achieved a mean Dice similarity coefficient of 0.93, indicating high delineation accuracy. Among all regressors, the TabPFN model yielded the best predictive performance. Models using radiomic features alone achieved an R² of 0.873 and a mean absolute percentage error (MAPE) of 6.8%; performance improved with the inclusion of handcrafted features (R²=0.883, MAPE = 6.7%) and further with DL features (R² = 0.900, MAPE = 6.4%), significantly outperforming manual clinical estimates (R²=0.780, MAPE = 9.7%). SHAP analysis demonstrated that all three feature levels contributed substantially to the overall prediction accuracy.

Conclusion

The proposed CT-based multilevel feature model enables highly accurate preoperative prediction of postoperative preserved RPV following PN, significantly outperforming conventional clinical assessments. This model offers a robust, interpretable framework to support precision surgical planning and personalized renal function preservation strategies.