Precision of MRI radiomics features in the liver and hepatocellular carcinoma

• Published in: European radiology 2022-03, Vol.32 (3), p.2030-2040
• Main Authors: Carbonell, Guillermo, Kennedy, Paul, Bane, Octavia, Kirmani, Ammar, El Homsi, Maria, Stocker, Daniel, Said, Daniela, Mukherjee, Pritam, Gevaert, Olivier, Lewis, Sara, Hectors, Stefanie, Taouli, Bachir
• Format: Article
• Language: English
• Subjects: Carcinoma, Hepatocellular - diagnostic imaging; Coefficient of variation; Correlation coefficient; Correlation coefficients; Diagnostic Radiology; Diffusion coefficient; Feature extraction; Hepatocellular carcinoma; Humans; Imaging; Internal Medicine; Interventional Radiology; Liver; Liver cancer; Liver Neoplasms - diagnostic imaging; Magnetic Resonance; Magnetic Resonance Imaging; Mathematical analysis; Medical imaging; Medicine; Medicine & Public Health; Neuroradiology; Parenchyma; Population studies; Radiology; Radiomics; Reproducibility; Reproducibility of Results; Retrospective Studies; Sequences; Tumors; Ultrasound
• ISSN: 0938-7994; 1432-1084
• DOI: 10.1007/s00330-021-08282-1

Objectives To assess the precision of MRI radiomics features in hepatocellular carcinoma (HCC) tumors and liver parenchyma. Methods The study population consisted of 55 patients, including 16 with untreated HCCs, who underwent two repeat contrast-enhanced abdominal MRI exams within 1 month to evaluate: (1) test–retest repeatability using the same MRI system ( n  = 28, 10 HCCs); (2) inter-platform reproducibility between different MRI systems ( n  = 27, 6 HCCs); (3) inter-observer reproducibility ( n  = 16, 16 HCCs). Shape and 1st- and 2nd-order radiomics features were quantified on pre-contrast T1-weighted imaging (WI), T1WI portal venous phase (pvp), T2WI, and ADC (apparent diffusion coefficient), on liver regions of interest (ROIs) and HCC volumes of interest (VOIs). Precision was assessed by calculating intraclass correlation coefficient (ICC), concordance correlation coefficient (CCC), and coefficient of variation (CV). Results There was moderate to excellent test–retest repeatability of shape and 1st- and 2nd-order features for all sequences in HCCs (ICC: 0.53–0.99; CV: 3–29%), and moderate to good test–retest repeatability of 1st- and 2nd-order features for T1WI sequences, and 2nd-order features for T2WI in the liver (ICC: 0.53–0.73; CV: 12–19%). There was poor inter-platform reproducibility for all features and sequences, except for shape and 1st-order features on T1WI in HCCs (CCC: 0.58–0.99; CV: 3–15%). Good to excellent inter-observer reproducibility was found for all features and sequences in HCCs (CCC: 0.80–0.99; CV: 4–15%) and moderate to good for liver (CCC: 0.45–0.86; CV: 6–25%). Conclusions MRI radiomics features have acceptable repeatability in the liver and HCC when using the same MRI system and across readers but have low reproducibility across MR systems, except for shape and 1st-order features on T1WI. Data must be interpreted with caution when performing multiplatform radiomics studies. Key Points • MRI radiomics features have acceptable repeatability when using the same MRI system but less reproducible when using different MRI platforms. • MRI radiomics features extracted from T1 weighted-imaging show greater stability across exams than T2 weighted-imaging and ADC. • Inter-observer reproducibility of MRI radiomics features was found to be good in HCC tumors and acceptable in liver parenchyma.