Academic Journal
Real-Time, Inline Quantitative MRI Enabled by Scanner-Integrated Machine Learning: A Proof of Principle With NODDI.
| Τίτλος: | Real-Time, Inline Quantitative MRI Enabled by Scanner-Integrated Machine Learning: A Proof of Principle With NODDI. |
|---|---|
| Συγγραφείς: | Rot S; Hawkes Institute and Department of Computer Science, UCL, London, UK.; NMR Research Unit, Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, Faculty of Brain Sciences, UCL, London, UK., Dragonu I; Research and Collaborations GBI, Siemens Healthcare Ltd, Camberley, UK., Triantafyllou C; Research and Collaborations GBI, Siemens Healthcare Ltd, Camberley, UK., Grech-Sollars M; Hawkes Institute and Department of Computer Science, UCL, London, UK.; Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UK., Papadaki A; Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UK.; Neuroradiological Academic Unit, Dept of Translational Neuroscience and Stroke, UCL Queen Square Institute of Neurology, UCL, London, UK., Mancini L; Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UK.; Neuroradiological Academic Unit, Dept of Translational Neuroscience and Stroke, UCL Queen Square Institute of Neurology, UCL, London, UK., Wastling S; Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UK.; Neuroradiological Academic Unit, Dept of Translational Neuroscience and Stroke, UCL Queen Square Institute of Neurology, UCL, London, UK., Steeden J; Centre for Cardiovascular Imaging, Institute of Cardiovascular Science, UCL, London, UK., Thornton JS; Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UK.; Neuroradiological Academic Unit, Dept of Translational Neuroscience and Stroke, UCL Queen Square Institute of Neurology, UCL, London, UK., Yousry T; Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, University College London Hospitals NHS Foundation Trust, London, UK.; Neuroradiological Academic Unit, Dept of Translational Neuroscience and Stroke, UCL Queen Square Institute of Neurology, UCL, London, UK., Gandini Wheeler-Kingshott CAM; NMR Research Unit, Queen Square MS Centre, Department of Neuroinflammation, UCL Queen Square Institute of Neurology, Faculty of Brain Sciences, UCL, London, UK.; Department of Brain & Behavioural Sciences, University of Pavia, Pavia, Italy.; Digital Neuroscience Centre, IRCCS Mondino Foundation, Pavia, Italy., Thomas DL; Neuroradiological Academic Unit, Dept of Translational Neuroscience and Stroke, UCL Queen Square Institute of Neurology, UCL, London, UK., Alexander DC; Hawkes Institute and Department of Computer Science, UCL, London, UK., Zhang H; Hawkes Institute and Department of Computer Science, UCL, London, UK. |
| Πηγή: | Magnetic resonance in medicine [Magn Reson Med] 2026 Aug; Vol. 96 (2), pp. 986-995. Date of Electronic Publication: 2026 May 05. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Wiley Country of Publication: United States NLM ID: 8505245 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1522-2594 (Electronic) Linking ISSN: 07403194 NLM ISO Abbreviation: Magn Reson Med Subsets: MEDLINE |
| Imprint Name(s): | Publication: 1999- : New York, NY : Wiley Original Publication: San Diego : Academic Press |
| Ιατρικοί όροι (MeSH): | Image Processing, Computer-Assisted*/methods , Magnetic Resonance Imaging*/methods , Brain*/diagnostic imaging , Machine Learning* , Diffusion Magnetic Resonance Imaging*, Humans ; Neural Networks, Computer ; Algorithms ; Neurites ; Computer Systems |
| Περίληψη: | Purpose: The clinical feasibility and translation of many advanced quantitative MRI (qMRI) techniques are inhibited by their restriction to 'research mode', due to resource-intensive, offline parameter estimation. This work aimed to achieve 'clinical mode' qMRI, by real-time, inline parameter estimation with a trained neural network (NN) fully integrated into a vendor's image reconstruction environment, therefore facilitating and encouraging clinical adoption of advanced qMRI techniques. Methods: The Siemens Image Calculation Environment (ICE) pipeline was customized to deploy trained NNs for advanced diffusion MRI parameter estimation with Open Neural Network Exchange (ONNX) Runtime. Two fully-connected NNs were trained offline with data synthesized with the neurite orientation dispersion and density imaging (NODDI) model, using either conventionally estimated (NN Results: NNs were successfully integrated and deployed natively in ICE, performing inline, whole-brain, in vivo NODDI parameter estimation in < 10 s. The proposed workflow was reproducible across protocols, volunteers and rescans. DICOM parametric maps were exported from the scanner for further analyses. Comparisons between NN Conclusion: Real-time, inline parameter estimation with the proposed generalizable framework resolves a key practical barrier to the potential clinical uptake of advanced qMRI methods, enabling their efficient integration into clinical workflows. Next steps include incorporation of pre-processing methods and evaluation in pathology. (© 2026 Siemens Healthcare Ltd and The Author(s). Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.) |
| Σχόλια: | Update of: ArXiv. 2025 Jul 16:arXiv:2507.12632v1.. (PMID: 40709300) |
| References: | H. Zhang, T. Schneider, C. A. Wheeler‐Kingshott, and D. C. Alexander, “NODDI: Practical in Vivo Neurite Orientation Dispersion and Density Imaging of the Human Brain,” NeuroImage 61, no. 4 (2012): 1000–1016, https://doi.org/10.1016/j.neuroimage.2012.03.072. K. Kamiya, M. Hori, and S. Aoki, “NODDI in Clinical Research,” Journal of Neuroscience Methods 346 (2020): 108908, https://doi.org/10.1016/j.jneumeth.2020.108908. C. Granziera, J. Wuerfel, F. Barkhof, et al., “Quantitative Magnetic Resonance Imaging Towards Clinical Application in Multiple Sclerosis,” Brain 144, no. 5 (2021): 1296–1311, https://doi.org/10.1093/brain/awab029. A. Daducci, E. J. Canales‐Rodríguez, H. Zhang, T. B. Dyrby, D. C. Alexander, and J. P. Thiran, “Accelerated Microstructure Imaging via Convex Optimization (AMICO) From Diffusion MRI Data,” NeuroImage 105 (2015): 32–44, https://doi.org/10.1016/j.neuroimage.2014.10.026. E. Manfrini, M. Smits, S. Thust, et al., “From Research to Clinical Practice: A European Neuroradiological Survey on Quantitative Advanced MRI Implementation,” European Radiology 31, no. 8 (2021): 6334–6341, https://doi.org/10.1007/s00330‐020‐07582‐2. N. G. Gyori, M. Palombo, C. A. Clark, H. Zhang, and D. C. Alexander, “Training Data Distribution Significantly Impacts the Estimation of Tissue Microstructure With Machine Learning,” Magnetic Resonance in Medicine 87, no. 2 (2022): 932–947, https://doi.org/10.1002/mrm.29014. S. C. Epstein, T. J. P. Bray, M. Hall‐Craggs, and H. Zhang, “Choice of Training Label Matters: How to Best Use Deep Learning for Quantitative MRI Parameter Estimation,” Machine Learning for Biomedical Imaging 2 (2024): 586–610, https://doi.org/10.59275/j.melba.2024‐geb5. S. Barbieri, O. J. Gurney‐Champion, R. Klaassen, and H. C. Thoeny, “Deep Learning How to Fit an Intravoxel Incoherent Motion Model to Diffusion‐Weighted MRI,” Magnetic Resonance in Medicine 83, no. 1 (2020): 312–321, https://doi.org/10.1002/mrm.27910. J. P. de Almeida Martins, M. Nilsson, B. Lampinen, et al., “Neural Networks for Parameter Estimation in Microstructural MRI: Application to a Diffusion‐Relaxation Model of White Matter,” NeuroImage 244 (2021): 118601, https://doi.org/10.1016/j.neuroimage.2021.118601. S. Sen, S. Singh, H. Pye, et al., “ssVERDICT: Self‐Supervised VERDICT‐MRI for Enhanced Prostate Tumor Characterization,” Magnetic Resonance in Medicine 92, no. 5 (2024): 2181–2192, https://doi.org/10.1002/mrm.30186. T. J. Bray, G. V. Minore, A. Bainbridge, et al., “RAIDER: Rapid, Anatomy‐Independent, Deep Learning‐Based PDFF and R2* Estimation Using Magnitude‐Only Signals, Dual Neural Networks and Training Data Distribution Design,” Machine Learning for Biomedical Imaging 3 (2025): 521–544, https://doi.org/10.59275/j.melba.2025‐bac4. M. Guerreri, S. Epstein, H. Azadbakht, and H. Zhang, “Resolving Quantitative MRI Model Degeneracy With Machine Learning via Training Data Distribution Design,” in Information Processing in Medical Imaging. Vol 13939. Lecture Notes in Computer Science, ed. A. Frangi, M. De Bruijne, D. Wassermann, and N. Navab (Springer Nature, 2023), 3–14, https://doi.org/10.1007/978‐3‐031‐34048‐2_1. G. V. Minore, L. Dwyer‐Hemmings, T. J. P. Bray, and H. Zhang, “Resolving Quantitative MRI Model Degeneracy in Self‐Supervised Machine Learning,” in Information Processing in Medical Imaging. Vol 15830. Lecture Notes in Computer Science, ed. I. Oguz, S. Zhang, and D. N. Metaxas (Springer Nature, 2026), 186–199, https://doi.org/10.1007/978‐3‐031‐96625‐5_13. K. Chow, P. Kellman, and H. Xue, “Prototyping Image Reconstruction and Analysis With FIRE,” in SCMR 24th Annual Scientific Sessions (Society for Cardiovascular Magnetic Resonance, 2021). S. Yoon, S. Nakamori, A. Amyar, et al., “Accelerated Cardiac MRI Cine With Use of Resolution Enhancement Generative Adversarial Inline Neural Network,” Radiology 307, no. 5 (2023): e222878, https://doi.org/10.1148/radiol.222878. M. Vornehm, J. Wetzl, D. Giese, et al., “CineVN: Variational Network Reconstruction for Rapid Functional Cardiac Cine MRI,” Magnetic Resonance in Medicine 93, no. 1 (2025): 138–150, https://doi.org/10.1002/mrm.30260. S. J. Inati, J. D. Naegele, N. R. Zwart, et al., “ISMRM Raw Data Format: A Proposed Standard for MRI Raw Datasets,” Magnetic Resonance in Medicine 77, no. 1 (2017): 411–421, https://doi.org/10.1002/mrm.26089. S. M. Yun, S. B. Hong, N. K. Lee, et al., “Deep Learning‐Based Image Reconstruction for the Multi‐Arterial Phase Images: Improvement of the Image Quality to Assess the Small Hypervascular Hepatic Tumor on Gadoxetic Acid‐Enhanced Liver MRI,” Abdominal Radiology 49, no. 6 (2024): 1861–1869, https://doi.org/10.1007/s00261‐024‐04236‐5. H. K. Jung, Y. Choi, S. Kim, D. Nickel, J. E. Park, and H. S. Kim, “Image Quality Assessment and White Matter Hyperintensity Quantification in Two Accelerated High‐Resolution 3D FLAIR Techniques: Wave‐CAIPI and Deep Learning–Based SPACE,” Clinical Radiology 82 (2025): 106783, https://doi.org/10.1016/j.crad.2024.106783. H. Wei, J. H. Yoon, S. K. Jeon, et al., “Enhancing Gadoxetic Acid‐Enhanced Liver MRI: A Synergistic Approach With Deep Learning CAIPIRINHA‐VIBE and Optimized Fat Suppression Techniques,” European Radiology 34, no. 10 (2024): 6712–6725, https://doi.org/10.1007/s00330‐024‐10693‐9. S. Rot, I. Dragonu, D. Thomas, D. C. Alexander, and H. Zhang, “Real‐Time Quantitative MRI Enabled by Scanner Integrated Machine Learning: A Proof of Principle With NODDI,” in Proceedings of the International Society of Magnetic Resonance in Medicine (2025), 0340. M. S. Hansen and T. S. Sørensen, “Gadgetron: An Open Source Framework for Medical Image Reconstruction,” Magnetic Resonance in Medicine 69, no. 6 (2013): 1768–1776, https://doi.org/10.1002/mrm.24389. H. Xue, R. Davies, D. Hansen, et al., “Gadgetron Inline AI: Effective Model Inference on MR Scanner,” in Proceedings of the International Society of Magnetic Resonance in Medicine, vol. 27 (International Society for Magnetic Resonance in Medicine, 2019), 4837. H. Xue, J. Artico, M. Fontana, J. C. Moon, R. H. Davies, and P. Kellman, “Landmark Detection in Cardiac MRI by Using a Convolutional Neural Network. Radiology,” Artificial Intelligence 3, no. 5 (2021): e200197, https://doi.org/10.1148/ryai.2021200197. ONNX Runtime Developers, ONNX Runtime (2021), https://onnxruntime.ai/. M. E. Muller, “A Note on a Method for Generating Points Uniformly on n‐Dimensional Spheres,” Communications of the ACM 2, no. 4 (1959): 19–20, https://doi.org/10.1145/377939.377946. A. Paszke, S. Gross, F. Massa, et al., “PyTorch: An Imperative Style, High‐Performance Deep Learning Library,” in Proceedings of the 33rd International Conference on Neural Information Processing Systems (Curran Associates Inc., 2019). B. Billot, D. N. Greve, O. Puonti, et al., “SynthSeg: Segmentation of Brain MRI Scans of Any Contrast and Resolution Without Retraining,” Medical Image Analysis 86 (2023): 102789, https://doi.org/10.1016/j.media.2023.102789. S. Aja‐Fernández, G. Vegas‐Sánchez‐Ferrero, and A. Tristán‐Vega, “Noise Estimation in Parallel MRI: GRAPPA and SENSE,” Magnetic Resonance Imaging 32, no. 3 (2014): 281–290, https://doi.org/10.1016/j.mri.2013.12.001. K. Sakaie and M. Lowe, “Retrospective Correction of Bias in Diffusion Tensor Imaging Arising From Coil Combination Mode,” Magnetic Resonance Imaging 37 (2017): 203–208, https://doi.org/10.1016/j.mri.2016.12.004. S. N. Sotiropoulos, S. Moeller, S. Jbabdi, et al., “Effects of Image Reconstruction on Fiber Orientation Mapping From Multichannel Diffusion MRI: Reducing the Noise Floor Using SENSE,” Magnetic Resonance in Medicine 70, no. 6 (2013): 1682–1689, https://doi.org/10.1002/mrm.24623. D. Le Bihan, C. Poupon, A. Amadon, and F. Lethimonnier, “Artifacts and Pitfalls in Diffusion MRI,” Journal of Magnetic Resonance Imaging 24, no. 3 (2006): 478–488, https://doi.org/10.1002/jmri.20683. C. Pierpaoli, “Artifacts in Diffusion MRI,” in Diffusion MRI (Oxford University Press, 2010), 303–318, https://doi.org/10.1093/med/9780195369779.003.0018. M. Palombo, A. Ianus, M. Guerreri, et al., “SANDI: A Compartment‐Based Model for Non‐Invasive Apparent Soma and Neurite Imaging by Diffusion MRI,” NeuroImage 215 (2020): 116835, https://doi.org/10.1016/j.neuroimage.2020.116835. S. T. M. Duong, S. L. Phung, A. Bouzerdoum, and M. M. Schira, “An Unsupervised Deep Learning Technique for Susceptibility Artifact Correction in Reversed Phase‐Encoding EPI Images,” Magnetic Resonance Imaging 71 (2020): 1–10, https://doi.org/10.1016/j.mri.2020.04.004. A. Legouhy, M. Graham, M. Guerreri, et al., “Correction of Susceptibility Distortion in EPI: A Semi‐Supervised Approach With Deep Learning,” in Computational Diffusion MRI. Vol. 13722. Lecture Notes in Computer Science, ed. S. Cetin‐Karayumak, D. Christiaens, M. Figini, et al. (Springer Nature Switzerland, 2022), 38–49, https://doi.org/10.1007/978‐3‐031‐21206‐2_4. A. Legouhy, R. Callaghan, W. Stee, P. Peigneux, H. Azadbakht, and H. Zhang, “Eddeep: Fast Eddy‐Current Distortion Correction for Diffusion MRI With Deep Learning,” in Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. Vol. 15002. Lecture Notes in Computer Science, ed. M. G. Linguraru, Q. Dou, A. Feragen, et al. (Springer Nature Switzerland, 2024), 152–161, https://doi.org/10.1007/978‐3‐031‐72069‐7_15. |
| Grant Information: | 1R01MH130362 United States NH NIH HHS; University College London Hospitals Biomedical Research Centre; MR/S032290/1 UK Research and Innovation; EP/S021930/1 Engineering and Physical Sciences Research Council; EP/X525649/1 Engineering and Physical Sciences Research Council |
| Contributed Indexing: | Keywords: NODDI; diffusion MRI; inline reconstruction; machine learning; neural networks; quantitative MRI |
| Entry Date(s): | Date Created: 20260505 Date Completed: 20260615 Latest Revision: 20260726 |
| Update Code: | 20260726 |
| PubMed Central ID: | PMC13269190 |
| DOI: | 10.1002/mrm.70388 |
| PMID: | 42083803 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!