Tumor grade-titude: XGBoost radiomics paves the way for RCC classification

Ellmann S, von Rohr F, Komina S, Bayerl N, Amann KU, Polifka I, Hartmann A, Sikic D, Wullich B, Uder M, Bäuerle T (2025)

Publication Type: Journal article

Publication year: 2025

Journal

European Journal of Radiology Elsevier

Book Volume: 188

Article Number: 112146

DOI: 10.1016/j.ejrad.2025.112146

Abstract

This study aimed to develop and evaluate a non-invasive XGBoost-based machine learning model using radiomic features extracted from pre-treatment CT images to differentiate grade 4 renal cell carcinoma (RCC) from lower-grade tumours. A total of 102 RCC patients who underwent contrast-enhanced CT scans were included in the analysis. Radiomic features were extracted, and a two-step feature selection methodology was applied to identify the most relevant features for classification. The XGBoost model demonstrated high performance in both training (AUC = 0.87) and testing (AUC = 0.92) sets, with no significant difference between the two (p = 0.521). The model also exhibited high sensitivity, specificity, positive predictive value, and negative predictive value. The selected radiomic features captured both the distribution of intensity values and spatial relationships, which may provide valuable insights for personalized treatment decision-making. Our findings suggest that the XGBoost model has the potential to be integrated into clinical workflows to facilitate personalized adjuvant immunotherapy decision-making, ultimately improving patient outcomes. Further research is needed to validate the model in larger, multicentre cohorts and explore the potential of combining radiomic features with other clinical and molecular data.

Authors with CRIS profile

Stephan Ellmann Institute of Radiology Felicitas von Rohr Professur für Multimodale Bildgebung in der präklinischen Forschung Nadine Bayerl Institute of Radiology Kerstin Ute Amann Professur für Nephropathologie Iris Polifka Institute of Pathology Arndt Hartmann Lehrstuhl für Allgemeine Pathologie und Pathologische Anatomie Bernd Wullich Lehrstuhl für Urologie Michael Uder Lehrstuhl für Diagnostische Radiologie Tobias Bäuerle Professur für Multimodale Bildgebung in der präklinischen Forschung

Involved external institutions

Saints Cyril and Methodius University of Skopje / Универзитет „Св. Кирил и Методиј“ во Скопје MK Republic of North Macedonia (MK)

How to cite

APA:

Ellmann, S., von Rohr, F., Komina, S., Bayerl, N., Amann, K.U., Polifka, I.,... Bäuerle, T. (2025). Tumor grade-titude: XGBoost radiomics paves the way for RCC classification. European Journal of Radiology, 188. https://doi.org/10.1016/j.ejrad.2025.112146

MLA:

Ellmann, Stephan, et al. "Tumor grade-titude: XGBoost radiomics paves the way for RCC classification." European Journal of Radiology 188 (2025).

BibTeX: Download