EUVIMEDEUVIMED entdecken
Crossref

Optimizing renal mass histology prediction with artificial intelligence using handcrafted radiomics

Teodora Boblea Podasca, Mahdi Ait Lhaj Loutfi, Marc-Antoine Blais, Marie-Lou Gadoury-Campbell, Stéphanie Boulet, Martin Vallières, Patrick O Richard

World Journal of Urology · 2026

DOI: 10.1007/s00345-026-06296-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift World Journal of Urology, 2026. Verfasst von Teodora Boblea Podasca und 6 weiteren Autor:innen. Beteiligte Einrichtung: Division of Urology, Department of Surgery, Centre Hospitalier Universitaire de Sherbrooke, Sherbrooke, Canada. Hauptthemen laut MEDLINE: Radiomics, Kidney Neoplasms, Carcinoma, Renal Cell, Tomography, X-Ray Computed. Die Arbeit nennt 30 Literaturangaben. Gefördert von: Faculty of Medicine and Healthcare Sciences Scholarship, Canadian Urological Association Scholarship Fund, Fonds de recherche du Québec salary award.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To determine the histology of a renal mass, physicians cannot rely on imaging alone. Radiomics—the extraction of quantitative data from medical imaging—could help address this challenge. This study aimed to build a classification model using CT-scan radiomics and/or clinical features to distinguish clear cell renal cell carcinoma (ccRCC) from other histologies. METHODS: We included patients who underwent surgery for suspected localized RCC. A total of 345 masses were included (72% ccRCC, 28% other histologies). Clinical data were extracted and each renal mass was manually segmented on CT and CECT (contrast enhanced CT). Then, 171 radiomics features were extracted from each lesion. The dataset was randomly split into a learning set (80%) and a hold-out set (20%). The learning set was further portioned into 10 subsets; each subset was split into training (80%) and testing (20%) sets and used to train and test 10 independent machine learning models using the XGBoost algorithm. The best model was subsequently validated on the hold-out set. RESULTS: The CECT-based radiomics model showed the best performance: AUC = 0.80, sensitivity = 67% and specificity = 77%. Adding clinical features to the model did not improve its performance. Using the hold-out set, the final model achieved an AUC of 0.88, with 56% sensitivity and 93% specificity. CONCLUSIONS: Our radiomics-based classification model showed high performance in differentiating ccRCC from other histologies using CECT scans. These findings support the role of radiomics as a potential non-invasive tool in kidney cancer management. However, external validation on independent cohorts is needed before clinical application.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadiomicsKidney NeoplasmsCarcinoma, Renal CellTomography, X-Ray ComputedArtificial IntelligenceMachine LearningHumansFemaleMaleMiddle AgedClassification AlgorithmsRetrospective StudiesAged

Stichwörter der Autor:innen

Clear-cell renal cell carcinomaContrast-enhanced CT (CECT)Kidney cancerMachine learningNon-invasive tumor characterizationQuantitative imaging biomarkersRadiomicsRenal mass differentiation

Autor:innen und Institutionen

  • Division of Urology, Department of Surgery, Centre Hospitalier Universitaire de Sherbrooke, Sherbrooke, Canada.
  • Department of Computer Science, Université de Sherbrooke, Sherbrooke, Canada.
  • Faculty of Medicine and Health Sciences, Université de Sherbrooke, Sherbrooke, Canada.
  • Division of Urology, Department of Surgery, Centre Hospitalier Universitaire de l'Université Laval, Québec, Canada.
  • Medical Physics Unit, Department of Oncology, Faculty of Medicine and Health Sciences, McGill University, Montreal, Canada.
  • Division of Urology, Department of Surgery, Centre Hospitalier Universitaire de Sherbrooke, Sherbrooke, Canada. patrick.richard@usherbrooke.ca.

Förderung

  • Faculty of Medicine and Healthcare Sciences Scholarship
  • Canadian Urological Association Scholarship Fund
  • Fonds de recherche du Québec salary award

Zitieren

APA

Podasca, T. B., Loutfi, M. A. L., Blais, M. A., Gadoury-Campbell, M. L., Boulet, S., Vallières, M., & Richard, P. O. (2026). Optimizing renal mass histology prediction with artificial intelligence using handcrafted radiomics. World Journal of Urology. https://doi.org/10.1007/s00345-026-06296-2

Vancouver

Podasca TB, Loutfi MAL, Blais MA, Gadoury-Campbell ML, Boulet S, Vallières M, et al. Optimizing renal mass histology prediction with artificial intelligence using handcrafted radiomics. World Journal of Urology. 2026. doi:10.1007/s00345-026-06296-2

BibTeX
@article{Podasca2026,
  author = {Podasca, Teodora Boblea and Loutfi, Mahdi Ait Lhaj and Blais, Marc-Antoine and Gadoury-Campbell, Marie-Lou and Boulet, Stéphanie and Vallières, Martin and Richard, Patrick O},
  title = {Optimizing renal mass histology prediction with artificial intelligence using handcrafted radiomics},
  journal = {World Journal of Urology},
  year = {2026},
  doi = {10.1007/s00345-026-06296-2}
}
Kostenlos starten →