EUVIMEDEUVIMED entdecken
Crossref

Radiomics and Machine Learning for Differentiating Oncocytoma from Chromophobe Renal Cell Carcinoma on Nephrographic Phase CT

Bökebatur Ahmet Raşit Mendi, Halitcan Batur, Sarper Ökten, Mehmet Yıldızhan

Archives of Current Medical Research · 02.06.2026 · 7 (2) · 381-392

DOI: 10.47482/acmr.1865942 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Archives of Current Medical Research, online erschienen am 02.06.2026. Verfasst von Bökebatur Ahmet Raşit Mendi und 3 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Gefördert von: None..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

This study investigated a radiomics and machine learning methodology for differentiating chromophobe renal cell carcinoma (ChRCC) from renal oncocytoma (RO) using nephrographic phase computed tomography (CT) im-ages, aiming to enhance preoperative diagnostic strategies.

Methods

A retrospective cohort of 66 patients (36 ChRCC, 30 RO) undergoing contrast-enhanced CT was analyzed. Man-ual 3D segmentation of renal masses on nephrographic phase images yielded 107 radiomics features. LASSO regression identified the most discriminative features for dimensionality reduction. Four machine learning algorithms (RFC, SVM, Decision Tree, XGBoost) were trained and validated using a 70:30 data split and 10-fold cross-validation. Diagnostic per-formance was quantified by sensitivity, specificity, and AUC.

Results

LASSO regression identified 10 pivotal radiomics parameters, including first- and second-order features (e.g., GLCM, GLRLM), reflecting subtle architectural differences. XGBoost showed superior diagnostic performance (AUC: 0.979, 95% CI: 0.967–0.991, sensitivity: 89.75%, specificity: 94.55%). SVM achieved an AUC of 0.939 (95% CI: 0.909–0.968, sensitivity: 91.5%, specificity: 89.25%). Decision Tree (AUC: 0.906, sensitivity: 92.44%, specificity: 91.75%) and RFC (AUC: 0.90, sensitivity: 91.3%, specificity: 88.2%) also performed well. No significant age or gender differences were noted be-tween cohorts (p > 0.05).

Conclusion

Integrating CT-based radiomics with machine learning, particularly XGBoost, offers a highly accurate, non-invasive paradigm for preoperative ChRCC and RO differentiation. This approach holds substantial promise for optimizing clinical decision-making, supporting nephron-sparing interventions and potentially reducing overtreatment of benign renal oncocytomas.

Förderung

  • None.

Zitieren

APA

Mendi, B. A. R., Batur, H., Ökten, S., & Yıldızhan, M. (2026). Radiomics and Machine Learning for Differentiating Oncocytoma from Chromophobe Renal Cell Carcinoma on Nephrographic Phase CT. Archives of Current Medical Research, 7(2), 381-392. https://doi.org/10.47482/acmr.1865942

Vancouver

Mendi BAR, Batur H, Ökten S, Yıldızhan M. Radiomics and Machine Learning for Differentiating Oncocytoma from Chromophobe Renal Cell Carcinoma on Nephrographic Phase CT. Archives of Current Medical Research. 2026;7(2):381-392. doi:10.47482/acmr.1865942

BibTeX
@article{Mendi2026,
  author = {Mendi, Bökebatur Ahmet Raşit and Batur, Halitcan and Ökten, Sarper and Yıldızhan, Mehmet},
  title = {Radiomics and Machine Learning for Differentiating Oncocytoma from Chromophobe Renal Cell Carcinoma on Nephrographic Phase CT},
  journal = {Archives of Current Medical Research},
  year = {2026},
  volume = {7},
  number = {2},
  pages = {381--392},
  doi = {10.47482/acmr.1865942}
}
Kostenlos starten →