Radiogenomic Associations Clear Cell Renal Cell Carcinoma: An Exploratory Study

Derek H Liu; Komal A Dani; Sharath S Reddy; Xiaomeng Lei; Natalie L Demirjian; Darryl H Hwang; Bino A Varghese; Suhn Kyong Rhie; Felix Y Yap; David I Quinn; Imran Siddiqi; Manju Aron; Ulka Vaishampayan; Haris Zahoor; Steven Y Cen; Inderbir S Gill; Vinay A Duddalwar

doi:10.1159/000530719

Radiogenomic Associations Clear Cell Renal Cell Carcinoma: An Exploratory Study

Oncology. 2023;101(6):375-388. doi: 10.1159/000530719. Epub 2023 Apr 20.

Authors

Derek H Liu¹, Komal A Dani², Sharath S Reddy¹, Xiaomeng Lei³, Natalie L Demirjian³, Darryl H Hwang³, Bino A Varghese³, Suhn Kyong Rhie⁴, Felix Y Yap⁵, David I Quinn⁶, Imran Siddiqi⁷, Manju Aron⁷, Ulka Vaishampayan⁸, Haris Zahoor⁶, Steven Y Cen^{3

9}, Inderbir S Gill¹⁰, Vinay A Duddalwar^{3

10

11}

Affiliations

¹ Keck School of Medicine, University of Southern California, Los Angeles, California, USA.
² Keck School of Medicine, University of Southern California, Los Angeles, California, USA, kadani@usc.edu.
³ Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, California, USA.
⁴ Department of Biochemistry and Molecular Medicine, University of Southern California, Los Angeles, California, USA.
⁵ Radiology Associates of San Luis Obispo, Atascadero, California, USA.
⁶ Department of Medicine, University of Southern California, Los Angeles, California, USA.
⁷ Department of Pathology, University of Southern California, Los Angeles, California, USA.
⁸ Department of Medicine, University of Michigan, Ann Arbor, Michigan, USA.
⁹ Department of Neurology, University of Southern California, Los Angeles, California, USA.
¹⁰ Institute of Urology, University of Southern California, Los Angeles, California, USA.
¹¹ Department of Biomedical Engineering, University of Southern California, Los Angeles, California, USA.

PMID: 37080171
DOI: 10.1159/000530719

Abstract

Introduction: This study investigates how quantitative texture analysis can be used to non-invasively identify novel radiogenomic correlations with clear cell renal cell carcinoma (ccRCC) biomarkers.

Methods: The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma open-source database was used to identify 190 sets of patient genomic data that had corresponding multiphase contrast-enhanced CT images in The Cancer Imaging Archive. 2,824 radiomic features spanning fifteen texture families were extracted from CT images using a custom-built MATLAB software package. Robust radiomic features with strong inter-scanner reproducibility were selected. Random forest, AdaBoost, and elastic net machine learning (ML) algorithms evaluated the ability of the selected radiomic features to predict the presence of 12 clinically relevant molecular biomarkers identified from the literature. ML analysis was repeated with cases stratified by stage (I/II vs. III/IV) and grade (1/2 vs. 3/4). 10-fold cross validation was used to evaluate model performance.

Results: Before stratification by tumor grade and stage, radiomics predicted the presence of several biomarkers with weak discrimination (AUC 0.60-0.68). Once stratified, radiomics predicted KDM5C, SETD2, PBRM1, and mTOR mutation status with acceptable to excellent predictive discrimination (AUC ranges from 0.70 to 0.86).

Conclusions: Radiomic texture analysis can potentially identify a variety of clinically relevant biomarkers in patients with ccRCC and may have a prognostic implication.

Keywords: Clear cell renal cell carcinoma; Machine learning; Radiogenomics; Radiomics.

MeSH terms

Carcinoma, Renal Cell* / diagnostic imaging
Carcinoma, Renal Cell* / genetics
Carcinoma, Renal Cell* / pathology
Humans
Kidney Neoplasms* / diagnostic imaging
Kidney Neoplasms* / genetics
Kidney Neoplasms* / pathology
Machine Learning
Reproducibility of Results
Retrospective Studies
Tomography, X-Ray Computed / methods