Synthetic Data in MR Spectroscopy: Current Practices, Applications, and Considerations
Abstract
The use of synthetic data has emerged as an essential tool in Magnetic Resonance Spectroscopy (MRS) research and applications, providing advantages for optimization of acquisition, software validation, deep learning applications, and enhanced reproducibility. Importantly, synthetic data addresses challenges of limited training data availability, particularly for clinical populations, and offers controlled solutions for investigating uncertainties and unexplained variance with in vivo data. This work provides a review and evaluation of current practices in the use and generation of synthetic data within the MRS field. Conducted by the MRS Synthetic Data Working Group under the Code & Data Sharing Committee of the MRS Study Group of the International Society for Magnetic Resonance in Medicine (ISMRM), this manuscript encompasses existing literature, supplemented by collective experience and in-house methodologies.
Cite
@article{arxiv.2602.23463,
title = {Synthetic Data in MR Spectroscopy: Current Practices, Applications, and Considerations},
author = {John T. LaMaster and Aaron T. Gudmundson and Alireza Abaei and Seyma Alcicek and Arturo Alvarado and Ovidiu Andronesi and Tiffany K. Bell and Wolfgang Bogner and Hanna Bugler and Alexander R Craven and Cristina Cudalbu and Alma Davidson and Christopher W. Davies-Jenkins and Dinesh Deelchand and Richard A. E. Edden and Morteza Esmaeili and Candace C Fleischer and Abdelrahman Gad and Guglielmo Genovese and Saumya Gurbani and Ashley D. Harris and Pierre-Gilles Henry and Kay Chioma Igwe and Ajin Joy and Margarida Julià-Sapé and Hyeonjin Kim and Roland Kreis and Fan Lam and Karl Landheer and Bernard Lanz and Chu-Yu Lee and Clémence Ligneul and Julian P. Merkofer and Jack J. Miller and Jessie Mosso and Stanislav Motyka and Eloïse Mougel and Paul G. Mullins and Saipavitra Murali-Manohar and Chloé Najac and Shinichiro Nakajima and Georg Oeltzschner and Esin Ozturk-Isik and Marco Palombo and Ulrich Pilatus and Justyna Platek and Emma Van Praagh and Xiaobo Qu and Rudy Rizzo and Christopher T. Rodgers and Esau Poblador Rodriguez and Yeison Rodriguez and Manoj K Sammi and Dennis M. J. van de Sande and Manoj Kumar Sarma and Francesca Saviola and Anouk Schrantee and Amirmohammad Shamaei and Dunja Simicic and Brian J Soher and Nico Sollmann and Yulu Song and Jeffrey A Stanley and Bernhard Strasser and Antonia Susnjar and Kelley M. Swanberg and M. Albert Thomas and Ivan Tkáč and Zhangren Tu and Paul J. Weiser and Mark Widmaier and Martin Wilson and Christopher J. Wu and Lijing Xin and Helge J. Zöllner and İpek Özdemir and MRS Synthetic Data Working Group and Antonia Kaiser},
journal= {arXiv preprint arXiv:2602.23463},
year = {2026}
}
Comments
Word Count: 20,493; Figure Count: 6; Table Count: 0 (All tables are in the supplement)