@article {Bretzner2021.01.24.427986, author = {Martin Bretzner and Anna K. Bonkhoff and Markus D. Schirmer and Sungmin Hong and Adrian V. Dalca and Kathleen L. Donahue and Anne-Katrin Giese and Mark R. Etherton and Pamela M Rist and Marco Nardin and Razvan Marinescu and Clinton Wang and Robert W. Regenhardt and Xavier Leclerc and Renaud Lopes and Oscar R. Benavente and John W. Cole and Amanda Donatti and Christoph J. Griessenauer and Laura Heitsch and Lukas Holmegaard and Katarina Jood and Jordi Jimenez-Conde and Steven J. Kittner and Robin Lemmens and Christopher R. Levi and Patrick F. McArdle and Caitrin W. McDonough and James F. Meschia and Chia-Ling Phuah and Arndt Rolfs and Stefan Ropele and Jonathan Rosand and Jaume Roquer and Tatjana Rundek and Ralph L. Sacco and Reinhold Schmidt and Pankaj Sharma and Agnieszka Slowik and Alessandro Sousa and Tara M. Stanne and Daniel Strbian and Turgut Tatlisumak and Vincent Thijs and Achala Vagal and Johan Wasselius and Daniel Woo and Ona Wu and Ramin Zand and Bradford B. Worrall and Jane Maguire and Arne Lindgren and Christina Jern and Polina Golland and Gr{\'e}gory Kuchcinski and Natalia S. Rost}, editor = {,}, title = {MRI Radiomic Signature of White Matter Hyperintensities Is Associated with Clinical Phenotypes}, elocation-id = {2021.01.24.427986}, year = {2021}, doi = {10.1101/2021.01.24.427986}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Introduction Neuroimaging measurements of brain structural integrity are thought to be surrogates for brain health, but precise assessments require dedicated advanced image acquisitions. By means of describing the texture of conventional images beyond what meets the naked eye, radiomic analyses hold potential for evaluating brain health. We sought to: 1) evaluate this novel approach to assess brain structural integrity by predicting white matter hyperintensities burdens (WMH) and 2) uncover associations between predictive radiomic features and patients{\textquoteright} clinical phenotypes.Methods Our analyses were based on a multi-site cohort of 4,163 acute ischemic strokes (AIS) patients with T2-FLAIR MR images and corresponding deep-learning-generated total brain and WMH segmentation. Radiomic features were extracted from normal-appearing brain tissue (brain mask{\textendash}WMH mask). Radiomics-based prediction of personalized WMH burden was done using ElasticNet linear regression. We built a radiomic signature of WMH with the most stable selected features predictive of WMH burden and then related this signature to clinical variables (age, sex, hypertension (HTN), atrial fibrillation (AF), diabetes mellitus (DM), coronary artery disease (CAD), and history of smoking) using canonical correlation analysis.Results Radiomic features were highly predictive of WMH burden (R2=0.855{\textpm}0.011). Seven pairs of canonical variates (CV) significantly correlated the radiomics signature of WMH and clinical traits with respective canonical correlations of 0.81, 0.65, 0.42, 0.24, 0.20, 0.15, and 0.15 (FDR-corrected p-valuesCV1-6\<.001, p-valueCV7=.012). The clinical CV1 was mainly influenced by age, CV2 by sex, CV3 by history of smoking and DM, CV4 by HTN, CV5 by AF and DM, CV6 by CAD, and CV7 by CAD and DM.Conclusion Radiomics extracted from T2-FLAIR images of AIS patients capture microstructural damage of the cerebral parenchyma and correlate with clinical phenotypes. Further research could evaluate radiomics to predict the progression of WMH.Evidence before this study We did a systematic review on PubMed until December 1, 2020, for original articles and reviews in which radiomics were used to characterize stroke or cerebrovascular diseases. Radiomic analyses cover a broad ensemble of high-throughput quantification methods applicable to digitalized medical images that extract high-dimensional data by describing a given region of interest by its size, shape, histogram, and relationship between voxels. We used the search terms {\textquotedblleft}radiomics{\textquotedblright} or {\textquotedblleft}texture analysis{\textquotedblright}, and {\textquotedblleft}stroke{\textquotedblright}, {\textquotedblleft}cerebrovascular disease{\textquotedblright}, {\textquotedblleft}small vessel disease{\textquotedblright}, or {\textquotedblleft}white matter hyperintensities{\textquotedblright}. Our research identified 24 studies, 18 studying radiomics of stroke lesions and 6 studying cerebrovascular diseases. All the latter six studies were based on MRI (T1-FLAIR, dynamic contrast-enhanced imaging, T1 \& T2-FLAIR, T2-FLAIR post-contrast, T2-FLAIR, and T2-TSE images). Four studies were describing small vessel disease, and two were predicting longitudinal progression of WMH. The average sample size was small with 96 patients included (maximum: 204). One study on 141 patients identified 7 T1-FLAIR radiomic features correlated with cardiovascular risk factors (age and hyperlipidemia) using univariate correlations. All studies were monocentric and performed on a single MRI scanner.Added value of this study To date and to the best of our knowledge, this is the largest radiomics study performed on cerebrovascular disease or any topic, and one of the very few to include a great diversity of participating sites with diverse clinical MRI scanners. This study is the first one to establish a radiomic signature of WMH and to interpret its relationship with common cardiovascular risk factors. Our findings add to the body of evidence that damage caused by small vessel disease extend beyond the visible white matter hyperintensities, but the added value resides in the detection of that subvisible damage on routinely acquired T2-FLAIR imaging. It also suggests that cardiovascular phenotypes might manifest in distinct textural patterns detectable on conventional clinical-grade T2-FLAIR images.Implications of all the available evidence Assessing brain structural integrity has implications for treatment selection, follow-up, prognosis, and recovery prediction in stroke patients but also other neurological disease populations. Measuring cerebral parenchymal structural integrity usually requires advanced imaging such as diffusion tensor imaging or functional MRI. Translation of those neuroimaging biomarkers remains uncommon in clinical practice mainly because of their time-consuming and costly acquisition. Our study provides a potential novel solution to assess brains{\textquoteright} structural integrity applicable to standard, routinely acquired T2-FLAIR imaging.Future research could, for instance, benchmark this radiomics approach against diffusion or functional MRI metrics in the prediction of cognitive or functional outcomes after stroke.Competing Interest StatementThe authors have declared no competing interest.}, URL = {https://www.biorxiv.org/content/early/2021/01/26/2021.01.24.427986}, eprint = {https://www.biorxiv.org/content/early/2021/01/26/2021.01.24.427986.full.pdf}, journal = {bioRxiv} }