Assessing robustness of quantitative susceptibility-based MRI radiomic features in patients with multiple sclerosis

Abstract

Multiple Sclerosis (MS) is an autoimmune demyelinating disease characterised by changes in iron and myelin content. These biomarkers are detectable by Quantitative Susceptibility Mapping (QSM), an advanced Magnetic Resonance Imaging technique detecting magnetic properties. When analysed with radiomic techniques that exploit its intrinsic quantitative nature, QSM may furnish biomarkers to facilitate early diagnosis of MS and timely assessment of progression. In this work, we explore the robustness of QSM radiomic features by varying the number of grey levels (GLs) and echo times (TEs), in a sample of healthy controls and patients with MS. We analysed the white matter in total and within six clinically relevant tracts, including the cortico-spinal tract and the optic radiation. After optimising the number of GLs (n = 64), at least 65% of features were robust for each Volume of Interest (VOI), with no difference (p > .05) between left and right hemispheres. Different outcomes in feature robustness among the VOIs depend on their characteristics, such as volume and variance of susceptibility values. This study validated the processing pipeline for robustness analysis and established the reliability of QSM-based radiomics features against GLs and TEs. Our results provide important insights for future radiomics studies using QSM in clinical applications.

Multiparametric MRI dataset for susceptibility-based radiomic feature extraction and analysis

“…Feature extraction was conducted with 64 as the number of gray levels (GLs), a parameter determined from the outcomes of a prior optimization study 23 . Categories 3 to 7 are referred to as texture and offer insights into the spatial distribution of intensity levels in the image.…”

“…The dataset 22 we provide in this work includes QSM-based radiomic features from Normal Appearing White Matter (NAWM) and its tracts, extracted in a mixed group of patients with MS and healthy controls, and all the different MR sequences necessary to implement the pipeline: for each subject, morphological T 1 w and T 2 w, QSM and Diffusion Weighted Imaging (DWI) for Diffusion Tractography Imaging (DTI). An example of an application based on those data 23 is shown in the last section.…”

“…In 23 , we describe a novel investigation into the robustness of susceptibility-based features derived from QSM. The study involved a cohort of 121 patients with MS and 30 healthy controls.…”