Abstract
To evaluate the relative contribution of different Magnetic Resonance Imaging (MRI) sequences for the extraction of radiomics features in a cohort of patients with lacrimal gland tumors. This prospective study was approved by the Institutional Review Board and signed informed consent was obtained from all participants. From December 2015 to April 2017, 37 patients with lacrimal gland lesions underwent MRI before surgery, including axial T1-WI, axial Diffusion-WI, coronal DIXON-T2-WI and coronal post-contrast DIXON-T1-WI. Two readers manually delineated both lacrimal glands to assess inter-observer reproducibility, and one reader performed two successive delineations to assess intra-observer reproducibility. Radiomics features were extracted using an in-house software to calculate 85 features per region-of-interest (510 features/patient). Reproducible features were defined as features presenting both an intra-class correlation coefficient ≥0.8 and a concordance correlation coefficient ≥0.9 across combinations of the three delineations. Among these features, the ones yielding redundant information were identified as clusters using hierarchical clustering based on the Spearman correlation coefficient. All the MR sequences provided reproducible radiomics features (range 14(16%)−37(44%)) and non-redundant clusters (range 5–14). The highest numbers of features and clusters were provided by the water and in-phase DIXON T2-WI and water and in-phase post-contrast DIXON T1-WI (37, 26, 26 and 26 features and 14,12, 9 and 11 clusters, respectively). A total of 145 reproducible features grouped into 51 independent clusters was provided by pooling all the MR sequences. All MRI sequences provided reproducible radiomics features yielding independent information which could potentially serve as biomarkers.
Highlights
Of data dimensionality reduction to reduce the imbalance between the number of parameters and the size of the dataset and to allow more robust and reliable future statistical analyses
Many studies have focused on the analysis of multi-parametric data provided by PET-CT scans, but to the best of our knowledge, no one has yet evaluated the relative contribution of each MR sequence when performing a radiomics analysis, nor does the literature indicate whether there was an added value of using multiple MR sequences vs. only one[5,7,11,13,14,15,16]
Our study showed that all Magnetic Resonance Imaging (MRI) sequences could provide reproducible radiomics features and non-redundant clusters of features and that the different MRI sequences provided additional independent information
Summary
Of data dimensionality reduction to reduce the imbalance between the number of parameters and the size of the dataset and to allow more robust and reliable future statistical analyses. There is currently no consensus on the best way to perform data dimensionality reduction, the majority agrees that there is a global need for validating the radiomics techniques, including the assessment of repeatability, reproducibility, robustness or accuracy to provide strong biomarkers, as recommended by the Imaging Biomarkers Alliances[7,8,9,10,11,12]. Another stumbling block surrounding the radiomics pipeline is integrating multi-parametric data[7]. We explored the interactions between features extracted from different MR sequences and proposed a pipeline to rationally reduce feature dimensionality
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
