Radiomics in Renal Cell Carcinoma—A Systematic Review and Meta-Analysis

• Main Authors: Julia Mühlbauer, Luisa Egen, Karl-Friedrich Kowalewski, Maurizio Grilli, Margarete T. Walach, Niklas Westhoff, Philipp Nuhn, Fabian C. Laqua, Bettina Baessler, Maximilian C. Kriegmair
• Format: Article
• Language: English
• Published: MDPI AG 2021-03-01
• Series: Cancers
• Subjects: renal cell carcinoma; computed tomography; magnetic resonance imaging; machine learning; radiomics
• Online Access: https://www.mdpi.com/2072-6694/13/6/1348

Radiomics may increase the diagnostic accuracy of medical imaging for localized and metastatic RCC (mRCC). A systematic review and meta-analysis was performed. Doing so, we comprehensively searched literature databases until May 2020. Studies investigating the diagnostic value of radiomics in differentiation of localized renal tumors and assessment of treatment response to ST in mRCC were included and assessed with respect to their quality using the radiomics quality score (RQS). A total of 113 out of 1098 identified studies met the criteria and were included in qualitative synthesis. Median RQS of all studies was 13.9% (5.0 points, IQR 0.25–7.0 points), and RQS increased over time. Thirty studies were included into the quantitative synthesis: For distinguishing angiomyolipoma, oncocytoma or unspecified benign tumors from RCC, the random effects model showed a log odds ratio (OR) of 2.89 (95%-CI 2.40–3.39, <i>p</i> < 0.001), 3.08 (95%-CI 2.09–4.06, <i>p</i> < 0.001) and 3.57 (95%-CI 2.69–4.45, <i>p</i> < 0.001), respectively. For the general discrimination of benign tumors from RCC log OR was 3.17 (95%-CI 2.73–3.62, <i>p</i> < 0.001). Inhomogeneity of the available studies assessing treatment response in mRCC prevented any meaningful meta-analysis. The application of radiomics seems promising for discrimination of renal tumor dignity. Shared data and open science may assist in improving reproducibility of future studies.