Scholarlink

Purpose <p>A deep learning model integrating CT radiomics and clinical features was developed to predict perioperative complications and risk grade in patients undergoing partial nephrectomy, and was compared to traditional anatomical classification models.</p> Methods <p>Between June 2014 and July 2024, 1214 patients diagnosed with renal cell carcinoma or renal cysts who underwent partial nephrectomy were included. A deep learning model incorporating CT radiomics (segmented by nnU-Net and extracted by pyradiomics) and clinical features was developed. Logistic regression models using RENAL or PADUA scores were also developed for comparison. An external validation cohort (<i>n</i> = 260) was used to assess the model’s generalizability.</p> Results <p>In predicting complications, the deep learning model achieved an area under the curve (AUC) of 0.87 (95%CI: 0.80–0.93), outperforming the RENAL (0.68, 95%CI: 0.60–0.70) (<i>p</i> &lt; 0.001) and PADUA models (0.69, 95%CI: 0.55–0.71) (<i>p</i> &lt; 0.001). For risk grades, the deep learning model outperformed RENAL/PADUA models for the no-risk group (AUC = 0.83 [95%CI: 0.81–0.87] vs. 0.68 [95%CI: 0.58–0.71], <i>p</i> = 0.01; 0.66 [95%CI: 0.65–0.67], <i>p</i> &lt; 0.001) and low-risk group (AUC = 0.79 [95%CI: 0.75–0.82] vs. 0.64 [95%CI: 0.60–0.74], <i>p</i> = 0.03; 0.66 [95%CI: 0.63–0.73], <i>p</i> = 0.04). However, no significant differences were found for moderate- and high-risk groups (<i>p</i> &gt; 0.05). In the external validation cohort, the model achieved a prediction accuracy of 0.854 and an AUC of 0.83.</p> Conclusion <p>The CT-based deep learning model showed superior performance in predicting complications and risk grades for no-risk and low-risk patients undergoing partial nephrectomy. No significant differences were found for moderate- and high-risk groups.</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

The CT-based deep learning model outperforms traditional anatomical classification models in preoperatively predicting complications and risk grade in partial nephrectomy

  • 期刊论文

  • 发表日期：

    2025年10月25日

查看全文
  • Lingzhi Du,
  • Jie Cheng,
  • Chenyang Shen,
  • Jiangting Cheng,
  • Guanwen Yang,
  • Chang He,
  • Peirong Xu,
  • Wenyao Lin,
  • Li Liu,
  • Xiaoyi Hu,
  • Jiaqi Huang,
  • Yangyang Pang,
  • Ganzhe Xu,
  • Jianming Guo,
  • Yanjun Zhu,
  • Hang Wang

摘要

Purpose

A deep learning model integrating CT radiomics and clinical features was developed to predict perioperative complications and risk grade in patients undergoing partial nephrectomy, and was compared to traditional anatomical classification models.

Methods

Between June 2014 and July 2024, 1214 patients diagnosed with renal cell carcinoma or renal cysts who underwent partial nephrectomy were included. A deep learning model incorporating CT radiomics (segmented by nnU-Net and extracted by pyradiomics) and clinical features was developed. Logistic regression models using RENAL or PADUA scores were also developed for comparison. An external validation cohort (n = 260) was used to assess the model’s generalizability.

Results

In predicting complications, the deep learning model achieved an area under the curve (AUC) of 0.87 (95%CI: 0.80–0.93), outperforming the RENAL (0.68, 95%CI: 0.60–0.70) (p < 0.001) and PADUA models (0.69, 95%CI: 0.55–0.71) (p < 0.001). For risk grades, the deep learning model outperformed RENAL/PADUA models for the no-risk group (AUC = 0.83 [95%CI: 0.81–0.87] vs. 0.68 [95%CI: 0.58–0.71], p = 0.01; 0.66 [95%CI: 0.65–0.67], p < 0.001) and low-risk group (AUC = 0.79 [95%CI: 0.75–0.82] vs. 0.64 [95%CI: 0.60–0.74], p = 0.03; 0.66 [95%CI: 0.63–0.73], p = 0.04). However, no significant differences were found for moderate- and high-risk groups (p > 0.05). In the external validation cohort, the model achieved a prediction accuracy of 0.854 and an AUC of 0.83.

Conclusion

The CT-based deep learning model showed superior performance in predicting complications and risk grades for no-risk and low-risk patients undergoing partial nephrectomy. No significant differences were found for moderate- and high-risk groups.