Machine learning‐based multi‐pool Voigt fitting of <scp>CEST</scp> , <scp>rNOE</scp> , and <scp>MTC</scp> in Z‐spectra
Gradient boosting decision trees fitting of multi-pool Z-spectra significantly reduces fitting times compared to traditional LS approaches, allowing fast data processing while upholding fitting quality. Along with the short training times, this makes the method suitable for clinical settings and for large cohort research applications. The FPV-ML approach provides a significant improvement of goodness of fit compared to FPL-ML.
Authors
- Linda Knutsson (ORCID: https://orcid.org/0000-0002-4263-113X)
- Nirbhay N. Yadav (ORCID: https://orcid.org/0000-0003-0802-9791)
- Sajad Mohammed Ali (ORCID: https://orcid.org/0000-0002-4707-8206)
- Jannik Prasuhn (ORCID: https://orcid.org/0000-0003-4184-9409)
- Ronnie Wirestam (ORCID: https://orcid.org/0000-0003-2628-0760)
- Peter C. M. van Zijl
Institutions
- Kennedy Krieger Institute (US)
- Johns Hopkins University (US)
- Lund University (SE)
- Johns Hopkins Medicine (US)
- University Hospital Schleswig-Holstein (DE)
- University of Lübeck (DE)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2025-02-18
- DOI
- https://doi.org/10.1002/mrm.30460
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Cancerfonden
- Vetenskapsrådet
- National Institutes of Health