{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:12:52Z","timestamp":1764785572276,"version":"build-2065373602"},"reference-count":23,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIH","award":["U01CA264039 (HS)"],"award-info":[{"award-number":["U01CA264039 (HS)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background: Spectroscopic MRI (sMRI) is a quantitative imaging technique that maps infiltrated tumors in the brain without contrast injections. In a previous study (NCT03137888), sMRI-guided radiation treatment extended patient survival, showing promise for clinical translation. The spectral fitting of individual voxels in an sMRI dataset generate metabolite concentration maps that guide treatment. The established spectral analysis methods use iterative least-squares fitting (FITT) that are computationally demanding. This study compares the performance of NNFit, a neural network-based, accelerated spectral fitting model, to the established FITT for metabolite quantification and radiation treatment planning. Methods: NNFit is a self-supervised deep learning model trained on 50 ms echo-time (TE) sMRI data to estimate metabolite levels of choline (Cho), creatine (Cr), and NAA. We trained the model on 30 GBM patients (56 scans) and tested it on 17 GBM patients (29 scans). NNFit\u2019s performance was compared to the FITT using structural similarity indices (SSIM) and the Dice coefficient. Results: NNFit significantly improved processing speed while maintaining strong agreement with FITT. The radiation target volumes defined by Cho\/NAA \u2265 2x were visually comparable, with fewer artifacts in NNFit. Structural similarity indices (SSIM) indicated minimal bias and high consistency across methods. Conclusions: This study highlights NNFit\u2019s potential for rapid, accurate, and artifact-reduced metabolic imaging, enabling faster radiotherapy planning.<\/jats:p>","DOI":"10.3390\/cancers17030423","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T09:42:23Z","timestamp":1737970943000},"page":"423","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Accelerated Spectroscopic MRI Metabolite Quantification Based on a Deep Learning Method for Radiation Therapy Planning in Brain Tumor Patients"],"prefix":"10.3390","volume":"17","author":[{"given":"Alexander S.","family":"Giuffrida","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology, Emory University School of Medicine, Atlanta, GA 30322, USA"},{"name":"Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA 30332, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karthik","family":"Ramesh","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Emory University School of Medicine, Atlanta, GA 30322, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4792-4484","authenticated-orcid":false,"given":"Sulaiman","family":"Sheriff","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Miller School of Medicine, University of Miami, Miami, FL 45056, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7653-3063","authenticated-orcid":false,"given":"Andrew A.","family":"Maudsley","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Miller School of Medicine, University of Miami, Miami, FL 45056, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7992-1747","authenticated-orcid":false,"given":"Brent D.","family":"Weinberg","sequence":"additional","affiliation":[{"name":"Winship Cancer Institute, Emory University School of Medicine, Atlanta, GA 30322, USA"},{"name":"Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA 30322, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3504-4965","authenticated-orcid":false,"given":"Lee A. D.","family":"Cooper","sequence":"additional","affiliation":[{"name":"Department of Pathology, Northwestern University Feinberg School of Medicine, Chicago, IL 60657, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8313-2612","authenticated-orcid":false,"given":"Hyunsuk","family":"Shim","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Emory University School of Medicine, Atlanta, GA 30322, USA"},{"name":"Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA 30332, USA"},{"name":"Winship Cancer Institute, Emory University School of Medicine, Atlanta, GA 30322, USA"},{"name":"Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA 30322, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2306","DOI":"10.1001\/jama.2017.18718","article-title":"Effect of Tumor-Treating Fields Plus Maintenance Temozolomide vs Maintenance Temozolomide Alone on Survival in Patients with Glioblastoma","volume":"318","author":"Stupp","year":"2017","journal-title":"JAMA"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"4085","DOI":"10.1200\/JCO.2013.49.6968","article-title":"Dose-dense temozolomide for newly diagnosed glioblastoma: A randomized phase III clinical trial","volume":"31","author":"Gilbert","year":"2013","journal-title":"J. Clin. Oncol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2535","DOI":"10.1001\/jama.2015.16669","article-title":"Maintenance Therapy with Tumor-Treating Fields Plus Temozolomide vs Temozolomide Alone for Glioblastoma: A Randomized Clinical Trial","volume":"314","author":"Stupp","year":"2015","journal-title":"JAMA"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.prro.2015.12.002","article-title":"Glioblastoma: Radiation treatment margins, how small is large enough?","volume":"6","author":"Wernicke","year":"2016","journal-title":"Pract. Radiat. Oncol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1093\/neuonc\/now036","article-title":"Whole-brain spectroscopic MRI biomarkers identify infiltrating margins in glioblastoma patients","volume":"18","author":"Cordova","year":"2016","journal-title":"Neuro Oncol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"vdac006","DOI":"10.1093\/noajnl\/vdac006","article-title":"A multi-institutional pilot clinical trial of spectroscopic MRI-guided radiation dose escalation for newly diagnosed glioblastoma","volume":"4","author":"Ramesh","year":"2022","journal-title":"Neuro-Oncol. Adv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1186\/s13014-023-02219-2","article-title":"Delineation of recurrent glioblastoma by whole brain spectroscopic magnetic resonance imaging","volume":"18","author":"Bell","year":"2023","journal-title":"Radiat. Oncol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"633","DOI":"10.3390\/tomography9020051","article-title":"Spectroscopic MRI-Guided Proton Therapy in Non-Enhancing Pediatric High-Grade Glioma","volume":"9","author":"Huang","year":"2023","journal-title":"Tomography"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"428","DOI":"10.3390\/tomography10030033","article-title":"The Utility of Spectroscopic MRI in Stereotactic Biopsy and Radiotherapy Guidance in Newly Diagnosed Glioblastoma","volume":"10","author":"Rejimon","year":"2024","journal-title":"Tomography"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"omaa006","DOI":"10.1093\/omcr\/omaa006","article-title":"Remarkable response of a patient with secondary glioblastoma to a histone deacetylase inhibitor","volume":"3","author":"Gurbani","year":"2020","journal-title":"Oxf. Med. Case Rep."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1002\/nbm.1025","article-title":"Comprehensive processing, display and analysis for in vivo MR spectroscopic imaging","volume":"19","author":"Maudsley","year":"2006","journal-title":"NMR Biomed."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3346","DOI":"10.1002\/mrm.27641","article-title":"Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting","volume":"81","author":"Gurbani","year":"2019","journal-title":"Magn. Reson. Med."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hatami, N., Sdika, M., and Ratiney, H. (2018). Magnetic Resonance Spectroscopy Quantification Using Deep Learning. Medical Image Computing and Computer Assisted Intervention\u2014MICCAI 2018, Springer International Publishing.","DOI":"10.1007\/978-3-030-00928-1_53"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1002\/mrm.29214","article-title":"Bayesian deep learning\u2013based H-MRS of the brain: Metabolite quantification with uncertainty estimation using Monte Carlo dropout","volume":"88","author":"Lee","year":"2022","journal-title":"Magn. Reson. Med."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Shamaei, A., Starcukova, J., and Starcuk, Z. (2023). Physics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy data. Comput. Biol. Med., 158.","DOI":"10.1016\/j.compbiomed.2023.106837"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.1002\/mrm.29561","article-title":"Quantification of MR spectra by deep learning in an idealized setting: Investigation of forms of input, network architectures, optimization by ensembles of networks, and training bias","volume":"89","author":"Rizzo","year":"2023","journal-title":"Magn. Reson. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.1002\/mrm.29793","article-title":"A review of machine learning applications for the proton MR spectroscopy workflow","volume":"90","author":"Merkofer","year":"2023","journal-title":"Magn. Reson. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.1002\/mrm.25510","article-title":"Multivendor implementation and comparison of volumetric whole-brain echo-planar MR spectroscopic imaging","volume":"74","author":"Sabati","year":"2015","journal-title":"Magn. Reson. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"184","DOI":"10.18383\/j.tom.2018.00028","article-title":"The Brain Imaging Collaboration Suite (BrICS): A Cloud Platform for Integrating Whole-Brain Spectroscopic MRI into the Radiation Therapy Planning Workflow","volume":"5","author":"Gurbani","year":"2019","journal-title":"Tomography"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1002\/mrm.29686","article-title":"Vespa: Integrated applications for RF pulse design, spectral simulation and MRS data analysis","volume":"90","author":"Soher","year":"2023","journal-title":"Magn. Reson. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the Amount of Ecologic Association Between Species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cohen, I., Huang, Y., Chen, J., Benesty, J., Benesty, J., Chen, J., Huang, Y., and Cohen, I. (2009). Pearson correlation coefficient. Noise Reduction in Speech Processing, Springer.","DOI":"10.1007\/978-3-642-00296-0"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/3\/423\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:37:02Z","timestamp":1759919822000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/3\/423"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,27]]},"references-count":23,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,2]]}},"alternative-id":["cancers17030423"],"URL":"https:\/\/doi.org\/10.3390\/cancers17030423","relation":{},"ISSN":["2072-6694"],"issn-type":[{"type":"electronic","value":"2072-6694"}],"subject":[],"published":{"date-parts":[[2025,1,27]]}}}