Flexible and cost-effective deep learning for accelerated multi-parametric relaxometry using phase-cycled bSSFP
Abstract To accelerate the clinical adoption of quantitative magnetic resonance imaging (qMRI), frameworks are needed that not only allow for rapid acquisition, but also flexibility, cost efficiency, and high accuracy in parameter mapping. In this study, feed-forward deep neural network (DNN)- and i...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-88579-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862531579445248 |
|---|---|
| author | Florian Birk Lucas Mahler Julius Steiglechner Qi Wang Klaus Scheffler Rahel Heule |
| author_facet | Florian Birk Lucas Mahler Julius Steiglechner Qi Wang Klaus Scheffler Rahel Heule |
| author_sort | Florian Birk |
| collection | DOAJ |
| description | Abstract To accelerate the clinical adoption of quantitative magnetic resonance imaging (qMRI), frameworks are needed that not only allow for rapid acquisition, but also flexibility, cost efficiency, and high accuracy in parameter mapping. In this study, feed-forward deep neural network (DNN)- and iterative fitting-based frameworks are compared for multi-parametric (MP) relaxometry based on phase-cycled balanced steady-state free precession (pc-bSSFP) imaging. The performance of supervised DNNs (SVNN), self-supervised physics-informed DNNs (PINN), and an iterative fitting framework termed motion-insensitive rapid configuration relaxometry (MIRACLE) was evaluated in silico and in vivo in brain tissue of healthy subjects, including Monte Carlo sampling to simulate noise. DNNs were trained on three distinct in silico parameter distributions and at different signal-to-noise-ratios. The PINN framework, which incorporates physical knowledge into the training process, ensured more consistent inference and increased robustness to training data distribution compared to the SVNN. Furthermore, DNNs utilizing the full information of the underlying complex-valued MR data demonstrated ability to accelerate the data acquisition by a factor of 3. Whole-brain relaxometry using DNNs proved to be effective and adaptive, suggesting the potential for low-cost DNN retraining. This work emphasizes the advantages of in silico DNN MP-qMRI pipelines for rapid data generation and DNN training without extensive dictionary generation, long parameter inference times, or prolonged data acquisition, highlighting the flexible and rapid nature of lightweight machine learning applications for MP-qMRI. |
| format | Article |
| id | doaj-art-f446f5acc38c4b88b287ad49dec690a2 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-f446f5acc38c4b88b287ad49dec690a22025-02-09T12:29:00ZengNature PortfolioScientific Reports2045-23222025-02-0115111610.1038/s41598-025-88579-zFlexible and cost-effective deep learning for accelerated multi-parametric relaxometry using phase-cycled bSSFPFlorian Birk0Lucas Mahler1Julius Steiglechner2Qi Wang3Klaus Scheffler4Rahel Heule5Department of Biomedical Magnetic Resonance, University of TübingenHigh-Field Magnetic Resonance, Max Planck Institute for Biological CyberneticsDepartment of Biomedical Magnetic Resonance, University of TübingenHigh-Field Magnetic Resonance, Max Planck Institute for Biological CyberneticsDepartment of Biomedical Magnetic Resonance, University of TübingenDepartment of Biomedical Magnetic Resonance, University of TübingenAbstract To accelerate the clinical adoption of quantitative magnetic resonance imaging (qMRI), frameworks are needed that not only allow for rapid acquisition, but also flexibility, cost efficiency, and high accuracy in parameter mapping. In this study, feed-forward deep neural network (DNN)- and iterative fitting-based frameworks are compared for multi-parametric (MP) relaxometry based on phase-cycled balanced steady-state free precession (pc-bSSFP) imaging. The performance of supervised DNNs (SVNN), self-supervised physics-informed DNNs (PINN), and an iterative fitting framework termed motion-insensitive rapid configuration relaxometry (MIRACLE) was evaluated in silico and in vivo in brain tissue of healthy subjects, including Monte Carlo sampling to simulate noise. DNNs were trained on three distinct in silico parameter distributions and at different signal-to-noise-ratios. The PINN framework, which incorporates physical knowledge into the training process, ensured more consistent inference and increased robustness to training data distribution compared to the SVNN. Furthermore, DNNs utilizing the full information of the underlying complex-valued MR data demonstrated ability to accelerate the data acquisition by a factor of 3. Whole-brain relaxometry using DNNs proved to be effective and adaptive, suggesting the potential for low-cost DNN retraining. This work emphasizes the advantages of in silico DNN MP-qMRI pipelines for rapid data generation and DNN training without extensive dictionary generation, long parameter inference times, or prolonged data acquisition, highlighting the flexible and rapid nature of lightweight machine learning applications for MP-qMRI.https://doi.org/10.1038/s41598-025-88579-zPhase-Cycled bSSFPDeep Neural NetworksMulti-parametric Quantitative MRIRelaxometryMIRACLE |
| spellingShingle | Florian Birk Lucas Mahler Julius Steiglechner Qi Wang Klaus Scheffler Rahel Heule Flexible and cost-effective deep learning for accelerated multi-parametric relaxometry using phase-cycled bSSFP Scientific Reports Phase-Cycled bSSFP Deep Neural Networks Multi-parametric Quantitative MRI Relaxometry MIRACLE |
| title | Flexible and cost-effective deep learning for accelerated multi-parametric relaxometry using phase-cycled bSSFP |
| title_full | Flexible and cost-effective deep learning for accelerated multi-parametric relaxometry using phase-cycled bSSFP |
| title_fullStr | Flexible and cost-effective deep learning for accelerated multi-parametric relaxometry using phase-cycled bSSFP |
| title_full_unstemmed | Flexible and cost-effective deep learning for accelerated multi-parametric relaxometry using phase-cycled bSSFP |
| title_short | Flexible and cost-effective deep learning for accelerated multi-parametric relaxometry using phase-cycled bSSFP |
| title_sort | flexible and cost effective deep learning for accelerated multi parametric relaxometry using phase cycled bssfp |
| topic | Phase-Cycled bSSFP Deep Neural Networks Multi-parametric Quantitative MRI Relaxometry MIRACLE |
| url | https://doi.org/10.1038/s41598-025-88579-z |
| work_keys_str_mv | AT florianbirk flexibleandcosteffectivedeeplearningforacceleratedmultiparametricrelaxometryusingphasecycledbssfp AT lucasmahler flexibleandcosteffectivedeeplearningforacceleratedmultiparametricrelaxometryusingphasecycledbssfp AT juliussteiglechner flexibleandcosteffectivedeeplearningforacceleratedmultiparametricrelaxometryusingphasecycledbssfp AT qiwang flexibleandcosteffectivedeeplearningforacceleratedmultiparametricrelaxometryusingphasecycledbssfp AT klausscheffler flexibleandcosteffectivedeeplearningforacceleratedmultiparametricrelaxometryusingphasecycledbssfp AT rahelheule flexibleandcosteffectivedeeplearningforacceleratedmultiparametricrelaxometryusingphasecycledbssfp |