Image Contrast, Image Pre-Processing, and T1 Mapping Affect MRI Radiomic Feature Repeatability in Patients with Colorectal Cancer Liver Metastases

Abstract

Imaging biomarkers require technical, biological, and clinical validation to be translated into robust tools in research or clinical settings. This study contributes to the technical validation of radiomic features from magnetic resonance imaging (MRI) by evaluating the repeatability of features from four MR sequences: pre-contrast T1- and T2-weighted images, pre-contrast quantitative T1 maps (qT1), and contrast-enhanced T1-weighted images. Fifty-one patients with colorectal cancer liver metastases were scanned twice, up to 7 days apart. Repeatability was quantified using the intraclass correlation coefficient (ICC) and repeatability coefficient (RC), and the impact of non-Gaussian feature distributions and image normalisation was evaluated. Most radiomic features had non-Gaussian distributions, but Box–Cox transformations enabled ICCs and RCs to be calculated appropriately for an average of 97% of features across sequences. ICCs ranged from 0.30 to 0.99, with volume and other shape features tending to be most repeatable; volume ICC > 0.98 for all sequences. 19% of features from non-normalised images exhibited significantly different ICCs in pair-wise sequence comparisons. Normalisation tended to increase ICCs for pre-contrast T1- and T2-weighted images, and decrease ICCs for qT1 maps. RCs tended to vary more between sequences than ICCs, showing that evaluations of feature performance depend on the chosen metric. This work suggests that feature-specific repeatability, from specific combinations of MR sequence and pre-processing steps, should be evaluated to select robust radiomic features as biomarkers in specific studies. In addition, as different repeatability metrics can provide different insights into a specific feature, consideration of the appropriate metric should be taken in a study-specific context.

Radiomics in Oncology: A Practical Guide

“…This is evaluated by repeating tumor segmentations for a subset of patients by one or more readers. The intraclass correlation coefficient (ICC) can be used to reject nonreproducible features (35,36) below a threshold ICC.…”

Radiomics for Discriminating Benign and Malignant Salivary Gland Tumors; Which Radiomic Feature Categories and MRI Sequences Should Be Used?

“…Three other studies [ 19 , 22 , 51 ] which proposed a radiomic analysis also lacked consensus on the selection of features. At present, most discussion about radiomics variability has focused on image scanner instrumentation manufacturers, parameter settings, tumor segmentation, pre-processing methods and radiomic software packages [ 38 , 52 , 53 , 54 , 55 , 56 , 57 ], but little attention has been paid to the problem of variability caused by the abundance of initial features.…”

Magnetic resonance imaging of tumor response to stroma-modifying pegvorhyaluronidase alpha (PEGPH20) therapy in early-phase clinical trials

“…For patients in whom multiple replicates of the DW-MRI were not available at the baseline scan date, the whole data RC was used instead. Replicate scans were not acquired for T1w-MRI or DCE-MRI; therefore, as recommended by QIBA, RC values were obtained from literature on similar data in tumors; RC = 0.27 s for T1 30 , RC = 32% for iAUC, RC = -45% to 83% for k trans , RC = 0.076 for v e 31 , and RC = 0.0062 for v p 32 . Tumors with a positive or negative (depending on the parameter) significant changes in a parameter were labeled pharmacodynamic responders (P), and otherwise labeled pharmacodynamic non-responders (N).…”