Research

• MRS Synthetic Data Working Group. Project Page.

This is a large, concerted community effort to formalize aspects of simulating, validating, reporting, and sharing synthetic MRS data. We currently have almost 90 researchers from around the world split into more than a dozen topics within MRS. We hope to derive a set of current best practices and to build a foundation to guide our research and practices as we move forward. This project is a part of the Code & Data Sharing Committee of ISMRM's Spectroscopy Study Group.

If you are interested in participating in this project, please send me an email.

• LaMaster, J. T., Igwe, K. C., Merkofer, J. P. (2026). Augmentrum: Generating Diverse MR Spectroscopy Training (and Validation) Data Through Augmentation. Accepted to IRSMRM 2026. (Running)

• LaMaster, J. T., Jin, X., Gupta, B., Lasser, T. (2024-now). Denoising for Physical Fidelity: Feature Enhancement via Spatial Conditioning on Multi-Coil Transients Improves Metabolite Quantification of Noisy Spectra. Proffered Oral Presentation at the 2024 ISMRM Workshop on MR Spectroscopy: Frontiers in Molecular & Metabolic Imaging. (Running)

• LaMaster, J. (2024). Uncertainty-Aware Deep Spectral Modeling of Heterogeneous MRS Data. (Paused)

• Swanberg, K., Oeltzschner, G., Fleischer, C., LaMaster, J., Zöllner, H., Kaiser, A., Near, J., and Juchem, C. (2024). 1H-MRS VERI: Proton Magnetic Resonance Spectroscopy Validation Effort Resource Initiative to collect reliable and generalizable data standards for validating in vivo 1H-MRS processing and quantification methods. Project Page. (ISMRM Abstract 2024)

Unfortunately, I do not have any projects currently available.

If you would like to suggest a project (BSc thesis, MSc thesis, semester project, internship, etc.), please send me an email and include your CV, transcript, and a letter of motivation.

• Kopka, Luca. 2025. Deep Learning based Metabolite Quantification for MR Spectroscopic Imaging. (Bachelor Thesis).

• LaMaster, John. 2025. MRS-Sim: Open-Source Framework for Simulating In Vivo-like Magnetic Resonance Spectra. NMR in Biomedicine. 38(10). 1-18. https://doi.org/10.1002/nbm.70130 

• Soher, B. J., LaMaster, J. T., Merkofer, J. P., Strasser, B., van de Sande, D. M. J., and Ma, C.. 2025. Preliminary Results from the 2024 MRSI Data Processing and Quantification Challenge. Proceedings of the International Society for Magnetic Resonance in Medicine. Abstract 4833.

• Jin, Xingyu. 2024. Deep Learning-based Denoising of MRS Data for Improved Spectral Fitting with a Forward Physical Model Loss. (Bachelor Thesis).

• Kofler, F., Ezhov, I., Fidon, L., Horvath, I., de la Rosa, E., LaMaster, J., Li, H., Finck, T., Shit, S., Paetzold, J., Bakas, S., Piraud, M., Kirschke, J., Vercauteren, T., Zimmer, C., Wiestler, B., & Menze, B. (2023). Deep quality estimation: Creating surrogate models for human quality ratings. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, 3–13. https://doi.org/10.1007/978-3-031-33842-7_1 

• Gupta, Basabdatta. (2023). Deep Learning-based Denoising for Improving Metabolite Quantification in Magnetic Resonance Spectroscopy. (Master Thesis)

• Getting started with MRS: a digital collection of community-sourced educational materials. First edition. Edited by Fleischer, C., Oeltzschner, G., LaMaster, J. et al. MRSHub: United States, 2022. https://mrshub.github.io/mre-educational-book/

• Chapter 4 MRS and NMR Glossary; Getting started with MRS: a digital collection of community-sourced educational materials. First edition. Authored by LaMaster, J. et al. MRSHub: United States, 2022. https://mrshub.github.io/mre-educational-book/ 

• LaMaster, J., Das, D., Kofler, F., Crane, J., Li, Y., Lasser, T., Menze, B. (Pending). Improving the Precision of CNNs for Magnetic Resonance Spectral Modeling.

• Kreitner, Linus. (2021). Improving Model Generalizability for MR Spectroscopy through Generative Adversarial Domain Adaptation. (Bachelor Thesis).

• Hu, X., Ren, W., LaMaster, J., Cao, X., Li, X., Li, Z., Menze, B.H., & Liu, W. (2020). Face Super-Resolution Guided by 3D Facial Priors. Computer Vision - ECCV 2020, 763-780. https://doi.org/10.1007.978-3-030-58548-8_44