Papers
Topics
Authors
Recent
Search
2000 character limit reached

A Flow-based Truncated Denoising Diffusion Model for Super-resolution Magnetic Resonance Spectroscopic Imaging

Published 25 Oct 2024 in eess.IV, cs.CV, and cs.LG | (2410.19288v1)

Abstract: Magnetic Resonance Spectroscopic Imaging (MRSI) is a non-invasive imaging technique for studying metabolism and has become a crucial tool for understanding neurological diseases, cancers and diabetes. High spatial resolution MRSI is needed to characterize lesions, but in practice MRSI is acquired at low resolution due to time and sensitivity restrictions caused by the low metabolite concentrations. Therefore, there is an imperative need for a post-processing approach to generate high-resolution MRSI from low-resolution data that can be acquired fast and with high sensitivity. Deep learning-based super-resolution methods provided promising results for improving the spatial resolution of MRSI, but they still have limited capability to generate accurate and high-quality images. Recently, diffusion models have demonstrated superior learning capability than other generative models in various tasks, but sampling from diffusion models requires iterating through a large number of diffusion steps, which is time-consuming. This work introduces a Flow-based Truncated Denoising Diffusion Model (FTDDM) for super-resolution MRSI, which shortens the diffusion process by truncating the diffusion chain, and the truncated steps are estimated using a normalizing flow-based network. The network is conditioned on upscaling factors to enable multi-scale super-resolution. To train and evaluate the deep learning models, we developed a 1H-MRSI dataset acquired from 25 high-grade glioma patients. We demonstrate that FTDDM outperforms existing generative models while speeding up the sampling process by over 9-fold compared to the baseline diffusion model. Neuroradiologists' evaluations confirmed the clinical advantages of our method, which also supports uncertainty estimation and sharpness adjustment, extending its potential clinical applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. Analyzing inverse problems with invertible neural networks, in: International Conference on Learning Representations.
  2. Accelerated mr spectroscopic imaging—a review of current and emerging techniques. NMR in Biomedicine 34, e4314.
  3. Mri reconstruction based on generative models. US Patent App. 17/891,702.
  4. Systems and methods for processing medical images with invertible neural networks. US Patent App. 17/891,668.
  5. Correlation between subjective and objective assessment of magnetic resonance (mr) images. Magnetic resonance imaging 34, 820–831.
  6. Score-based diffusion models for accelerated mri. Medical image analysis 80, 102479.
  7. Deuterium metabolic imaging (dmi) for mri-based 3d mapping of metabolism in vivo. Science advances 4, eaat7314.
  8. In vivo NMR spectroscopy: principles and techniques. John Wiley & Sons.
  9. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34, 8780–8794.
  10. Data-Driven Methods for Super-Resolution Magnetic Resonance Spectroscopic Imaging. Ph.D. thesis. Yale University.
  11. Invertible sharpening network for mri reconstruction enhancement, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 582–592.
  12. A deep learning method for sensitivity enhancement in deuterium metabolic imaging (dmi), in: Proceedings of the 28th Annual Meeting of ISMRM.
  13. Preserved edge convolutional neural network for sensitivity enhancement of deuterium metabolic imaging (dmi). arXiv:2309.04100.
  14. High-resolution magnetic resonance spectroscopic imaging using a multi-encoder attention u-net with structural and adversarial loss, in: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE. pp. 2891--2895.
  15. Multi-scale super-resolution magnetic resonance spectroscopic imaging with adjustable sharpness, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 410--420.
  16. Flow-based visual quality enhancer for super-resolution magnetic resonance spectroscopic imaging, in: MICCAI Workshop on Deep Generative Models, Springer. pp. 3--13.
  17. High-resolution extracellular ph imaging of liver cancer with multiparametric mr using deep image prior. NMR in Biomedicine , e5145.
  18. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks 107, 3--11.
  19. Generative adversarial networks. Communications of the ACM 63, 139--144.
  20. High-resolution metabolic imaging of high-grade gliomas using 7t-crt-fid-mrsi. NeuroImage: Clinical 28, 102433.
  21. High-resolution metabolic mapping of gliomas via patch-based super-resolution magnetic resonance spectroscopic imaging at 7t. Neuroimage 191, 587--595.
  22. Clinical high-resolution 3d-mr spectroscopic imaging of the human brain at 7 t. Investigative radiology 55, 239--248.
  23. Denoising diffusion probabilistic models. Advances in neural information processing systems 33, 6840--6851.
  24. Arbitrary style transfer in real-time with adaptive instance normalization, in: Proceedings of the IEEE international conference on computer vision, pp. 1501--1510.
  25. Super-resolution 1h magnetic resonance spectroscopic imaging utilizing deep learning. Frontiers in oncology 9, 1010.
  26. Patch-based super-resolution of mr spectroscopic images: application to multiple sclerosis. Frontiers in neuroscience 11, 13.
  27. Magnetic resonance spectroscopic imaging at superresolution: overview and perspectives. Journal of Magnetic Resonance 263, 193--208.
  28. Diffusion models for medical image analysis: A comprehensive survey. arXiv preprint arXiv:2211.07804 .
  29. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 .
  30. A subspace approach to high-resolution spectroscopic imaging. Magnetic resonance in medicine 71, 1349--1357.
  31. Srdiff: Single image super-resolution with diffusion probabilistic models. Neurocomputing 479, 47--59.
  32. Deep learning super-resolution magnetic resonance spectroscopic imaging of brain metabolism and mutant isocitrate dehydrogenase glioma. Neuro-oncology advances 4, vdac071.
  33. A review of the deep learning methods for medical images super resolution problems. Irbm 42, 120--133.
  34. Hierarchical conditional flow: A unified framework for image super-resolution and image rescaling, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4076--4085.
  35. Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 .
  36. Srflow: Learning the super-resolution space with normalizing flow, in: Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part V 16, Springer. pp. 715--732.
  37. Results of the 2020 fastmri challenge for machine learning mr image reconstruction. IEEE transactions on medical imaging 40, 2306--2317.
  38. High and ultra-high resolution metabolite mapping of the human brain using 1h fid mrsi at 9.4 t. Neuroimage 168, 211--221.
  39. Improved denoising diffusion probabilistic models, in: International Conference on Machine Learning, PMLR. pp. 8162--8171.
  40. Towards performant and reliable undersampled mr reconstruction via diffusion model sampling, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 623--633.
  41. Regional metabolite concentrations in human brain as determined by quantitative localized proton mrs. Magnetic resonance in medicine 39, 53--60.
  42. Lcmodel & lcmgui user’s manual. LCModel version 6.
  43. Variational inference with normalizing flows, in: International conference on machine learning, PMLR. pp. 1530--1538.
  44. Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4713--4726.
  45. Advances in functional and structural mr image analysis and implementation as fsl. Neuroimage 23, S208--S219.
  46. Deep unsupervised learning using nonequilibrium thermodynamics, in: International conference on machine learning, PMLR. pp. 2256--2265.
  47. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems 32.
  48. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 .
  49. Deep learning for image super-resolution: A survey. IEEE transactions on pattern analysis and machine intelligence 43, 3365--3387.
  50. Multiscale structural similarity for image quality assessment, in: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, Ieee. pp. 1398--1402.
  51. Learning likelihoods with conditional normalizing flows. arXiv preprint arXiv:1912.00042 .
  52. Diffusion models: A comprehensive survey of methods and applications. arXiv preprint arXiv:2209.00796 .
  53. The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 586--595.
  54. Loss functions for image restoration with neural networks. IEEE Transactions on computational imaging 3, 47--57.
  55. Truncated diffusion probabilistic models and diffusion-based adversarial auto-encoders, in: The Eleventh International Conference on Learning Representations.
  56. Dual-domain self-supervised learning for accelerated non-cartesian mri reconstruction. Medical Image Analysis 81, 102538.
  57. Test--retest reproducibility of human brain multi-slice 1h fid-mrsi data at 9.4 t after optimization of lipid regularization, macromolecular model, and spline baseline stiffness. Magnetic resonance in medicine 89, 11--28.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up