{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:00:27Z","timestamp":1771448427130,"version":"3.50.1"},"posted":{"date-parts":[[2026,2,16]]},"group-title":"Radiology and Imaging","reference-count":32,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,2,16]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>Magnetic Resonance Spectroscopy Imaging (MRSI) offers spatially-resolved, neurometabolic information, acquired non-invasively at whole-brain scales from human subjects. Analysis of MRSI however, is extremely challenging. The metabolic information is highly convolved, and sparsely distributed across millions of spatial-spectral datapoints, allowing for little direct human interpretation. Conversely, the overall low signal-to-noise with high-intensity artifacts can confound unsupervised machine learning approaches. These technical barriers have left much of the potential of MRSI unrealized.<\/jats:p>\n                <jats:p>We acquired MRSI data from 4 human subjects with a diagnosis of multiple sclerosis (MS), incorporating experimental design into an informed machine learning approach. MRSI acquisitions were registered to anatomical MRI to label 105k spectra from brain tissue and 162 spectra from white matter hyperintensities (WMHs), an imaging biomarker associated with MS lesions. Spectral labels were then used in contrastive principal component analysis (cPCA) to filter artifacts and background features in the MRSI data from lesion salient features and clustered into statistically significant states based on features that could be interpreted from the original data. Our approach renders MRSI data into testable representations of neurometabolism, enabling the method for fundamental and clinical research.<\/jats:p>\n                <jats:sec>\n                  <jats:title>Graphical Abstract<\/jats:title>\n                  <jats:p>Analysis workflow for neurometabolic profiling of MS lesions. MRSI and anatomical MRI is acquired and processed in parallel for spectral data and anatomical labels. Spectra are then labeled and separated into experimental vs background data for contrastive PCA. Spectra are clustered for similarity, further labeled, and projected onto a brain atlas for a neurometabolic view.<\/jats:p>\n                  <jats:fig id=\"ufig1\" position=\"float\" fig-type=\"figure\" orientation=\"portrait\">\n                    <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"26346248v1_ufig1\" position=\"float\" orientation=\"portrait\"\/>\n                  <\/jats:fig>\n                <\/jats:sec>","DOI":"10.64898\/2026.02.13.26346248","type":"posted-content","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:25:12Z","timestamp":1771277112000},"source":"Crossref","is-referenced-by-count":0,"title":["Parsing Neurometabolic Signatures of Multiple Sclerosis with MRSI and cPCA"],"prefix":"10.64898","author":[{"given":"Narendiran","family":"Raghu","sequence":"first","affiliation":[{"name":"Arizona State University, School of Biological and Health Systems Engineering. Tempe Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Abbasi","sequence":"additional","affiliation":[{"name":"Arizona State University, School of Biological and Health Systems Engineering. Tempe Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeinab","family":"Tashi","sequence":"additional","affiliation":[{"name":"Arizona State University, School of Biological and Health Systems Engineering. Tempe Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cristian","family":"Zamora","sequence":"additional","affiliation":[{"name":"Arizona State University, School of Biological and Health Systems Engineering. Tempe Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shundene","family":"Key","sequence":"additional","affiliation":[{"name":"Arizona State University, School of Biological and Health Systems Engineering. Tempe Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catherine D.","family":"Chong","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Department of Neurology, Phoenix, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simona","family":"Niklova","sequence":"additional","affiliation":[{"name":"Florida State University, Dept of Psychology, Neurology and Neuroimaging Research, Tallahassee, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Mayo Clinic, Department of Neurology, Phoenix, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"Ofori","sequence":"additional","affiliation":[{"name":"Arizona State University, College of Health Solutions. Phoenix Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5044-369X","authenticated-orcid":false,"given":"Benjamin B.","family":"Bartelle","sequence":"additional","affiliation":[{"name":"Arizona State University, School of Biological and Health Systems Engineering. Tempe Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026021812001039000_2026.02.13.26346248v1.1","unstructured":"Kim JD , Copperi F , Diano S. Microglia in Central Control of Metabolism. ."},{"key":"2026021812001039000_2026.02.13.26346248v1.2","unstructured":"Rana AK , Bhatt B , Gusain C , Biswal SN , Das D , Kumar M. Neuroimmunometabolism: how metabolism orchestrates immune response in healthy and diseased brain. ."},{"key":"2026021812001039000_2026.02.13.26346248v1.3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar3932"},{"key":"2026021812001039000_2026.02.13.26346248v1.4","doi-asserted-by":"publisher","DOI":"10.1111\/jnc.70294"},{"key":"2026021812001039000_2026.02.13.26346248v1.5","doi-asserted-by":"publisher","DOI":"10.1186\/s12974-024-03296-0"},{"key":"2026021812001039000_2026.02.13.26346248v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.immuni.2017.08.008"},{"key":"2026021812001039000_2026.02.13.26346248v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.07.023"},{"key":"2026021812001039000_2026.02.13.26346248v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-56837-1"},{"key":"2026021812001039000_2026.02.13.26346248v1.9","doi-asserted-by":"publisher","DOI":"10.3390\/ijms26189207"},{"key":"2026021812001039000_2026.02.13.26346248v1.10","doi-asserted-by":"publisher","DOI":"10.1212\/NXI.0000000000200219"},{"key":"2026021812001039000_2026.02.13.26346248v1.11","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.28942"},{"key":"2026021812001039000_2026.02.13.26346248v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.12.065"},{"key":"2026021812001039000_2026.02.13.26346248v1.13","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.29017"},{"key":"2026021812001039000_2026.02.13.26346248v1.14","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-022-02917-w"},{"key":"2026021812001039000_2026.02.13.26346248v1.15","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-022-02918-9"},{"key":"2026021812001039000_2026.02.13.26346248v1.16","doi-asserted-by":"crossref","unstructured":"Ahmed OB , Fezzani S , Guillevin C , Fezai L , Naudin M , Gianelli B , Fernandez-Maloigne C. DeepMRS: An End-to-End Deep Neural Network for Dementia Disease Detection using MRS Data. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). 2020, p. 1459\u20131463.","DOI":"10.1109\/ISBI45749.2020.9098419"},{"key":"2026021812001039000_2026.02.13.26346248v1.17","doi-asserted-by":"publisher","DOI":"10.1007\/s11306-022-01962-z"},{"key":"2026021812001039000_2026.02.13.26346248v1.18","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.29706"},{"key":"2026021812001039000_2026.02.13.26346248v1.19","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.27980"},{"key":"2026021812001039000_2026.02.13.26346248v1.20","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.26019"},{"key":"2026021812001039000_2026.02.13.26346248v1.21","doi-asserted-by":"crossref","unstructured":"Abbasi M , Sanderford CR , Raghu N , Pasha M , Bartelle BB . Sparse Representation Learning Derives Biological Features with Explicit Gene Weights from the Allen Mouse Brain Atlas. bioRxiv: 2021.10.11.464002, 2022.","DOI":"10.1101\/2021.10.11.464002"},{"key":"2026021812001039000_2026.02.13.26346248v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04608-8"},{"key":"2026021812001039000_2026.02.13.26346248v1.23","doi-asserted-by":"crossref","unstructured":"Dai W , Ng K , Severson K , Huang W , Anderson F , Stultz C. Generative Oversampling with a Contrastive Variational Autoencoder. In: 2019 IEEE International Conference on Data Mining (ICDM). 2019 IEEE International Conference on Data Mining (ICDM). IEEE, p. 101\u2013109.","DOI":"10.1109\/ICDM.2019.00020"},{"key":"2026021812001039000_2026.02.13.26346248v1.24","doi-asserted-by":"publisher","DOI":"10.1007\/s10858-013-9718-x"},{"key":"2026021812001039000_2026.02.13.26346248v1.25","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-87564-6"},{"key":"2026021812001039000_2026.02.13.26346248v1.26","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2001.0080401"},{"key":"2026021812001039000_2026.02.13.26346248v1.27","unstructured":"Sofroniew N , Lambert T , Evans K , Nunez-Iglesias J , Bokota G , Winston P , Pe\u00f1a-Castellanos G , Yamauchi K , Bussonnier M , Doncila Pop D , Can Solak A , Liu Z , Wadhwa P , Burt A , Buckley G , Sweet A , Migas L , Hilsenstein V , Gaifas L , Bragantini J , Rodr\u00edguez-Guerra J , Mu\u00f1oz H , Freeman J , Boone P , Lowe A , Gohlke C , Royer L , Pierr\u00e9 A , Har-Gil H , McGovern A. napari: a multi-dimensional image viewer for Python. Zenodo: 2022."},{"key":"2026021812001039000_2026.02.13.26346248v1.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2008.03.006"},{"key":"2026021812001039000_2026.02.13.26346248v1.29","doi-asserted-by":"publisher","DOI":"10.1021\/acs.analchem.5c03274"},{"key":"2026021812001039000_2026.02.13.26346248v1.30","doi-asserted-by":"publisher","DOI":"10.1007\/s11306-024-02090-6"},{"key":"2026021812001039000_2026.02.13.26346248v1.31","doi-asserted-by":"publisher","DOI":"10.1097\/RMR.0000000000000210"},{"key":"2026021812001039000_2026.02.13.26346248v1.32","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-018-07182-7"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.02.13.26346248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T20:00:21Z","timestamp":1771444821000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.02.13.26346248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":32,"URL":"https:\/\/doi.org\/10.64898\/2026.02.13.26346248","relation":{},"subject":[],"published":{"date-parts":[[2026,2,16]]},"subtype":"preprint"}}