EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-channel multiphase CT-based deep learning and radiomics fusion model for noninvasive pathological grading of clear cell renal cell carcinoma

Chongyang Sun, Qi Chen, Meng Gao, Shiqi He, Ze Zhang, Wei Zhang, Xigang Xiao

Frontiers in Oncology · 15.01.2026 · 15

DOI: 10.3389/fonc.2025.1710329 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 15.01.2026. Verfasst von Chongyang Sun und 6 weiteren Autor:innen. Beteiligte Einrichtung: CT Department of First Affiliated Hospital of Harbin Medical University, Harbin, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purposes To develop a combined model integrating multi-channel deep learning features, radiomics features, and clinical variables for noninvasive pathological grading of clear cell renal cell carcinoma (ccRCC). Material and methods A retrospective study was conducted on 496 patients with pathologically confirmed ccRCC who underwent preoperative triple-phase contrast-enhanced CT. Multi-channel deep learning features were extracted from three ROI settings (conventional, tumor-only, and 5-mm expansion) by stacking arterial, medullary and excretory phases. These were fused with arterial-phase radiomics features and clinical data to construct and compare predictive models.

Results

In the ResNet50 model, the expanded 5mm ROI slice model had an AUC of 0.791 in the training cohort and 0.780 in the testing cohort, indicating that the model could effectively predict the pathological grading of ccRCC. By combining deep learning features with radiomics and clinical features, the integrated model achieved AUCs of 0.855 in the training cohort and 0.849 in the testing cohort, significantly outperforming the individual radiomics and clinical models. Decision curve analysis (DCA) further showed that the clinical-imaging combined model provided a higher net benefit.

Conclusion

Multi-channel, multiphase CT fusion, when integrated with radiomics and clinical features, can significantly enhance predictive accuracy for ccRCC grading, providing a promising and interpretable noninvasive tool to support individualized treatment planning.

Schlagwörter

Stichwörter der Autor:innen

CTccRCCdeep learningmulti-channelpathological grading

Autor:innen und Institutionen

  • CT Department of First Affiliated Hospital of Harbin Medical University, Harbin, China.
  • Ultrasound Department of First Affiliated Hospital of Harbin Medical University, Harbin, China.
  • Urology Department Ward 1 of First Affiliated Hospital of Harbin Medical University, Harbin, China.
  • Graduate Department of First Affiliated Hospital of Harbin Medical University, Harbin, China.

Zitieren

APA

Sun, C., Chen, Q., Gao, M., He, S., Zhang, Z., Zhang, W., & Xiao, X. (2026). Multi-channel multiphase CT-based deep learning and radiomics fusion model for noninvasive pathological grading of clear cell renal cell carcinoma. Frontiers in Oncology, 15. https://doi.org/10.3389/fonc.2025.1710329

Vancouver

Sun C, Chen Q, Gao M, He S, Zhang Z, Zhang W, et al. Multi-channel multiphase CT-based deep learning and radiomics fusion model for noninvasive pathological grading of clear cell renal cell carcinoma. Frontiers in Oncology. 2026;15. doi:10.3389/fonc.2025.1710329

BibTeX
@article{Sun2026,
  author = {Sun, Chongyang and Chen, Qi and Gao, Meng and He, Shiqi and Zhang, Ze and Zhang, Wei and Xiao, Xigang},
  title = {Multi-channel multiphase CT-based deep learning and radiomics fusion model for noninvasive pathological grading of clear cell renal cell carcinoma},
  journal = {Frontiers in Oncology},
  year = {2026},
  volume = {15},
  doi = {10.3389/fonc.2025.1710329}
}
Kostenlos starten →