Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Iterative Learning for Joint Image Denoising and Motion Artifact Correction of 3D Brain MRI (2403.08162v1)

Published 13 Mar 2024 in eess.IV, cs.CV, and cs.LG

Abstract: Image noise and motion artifacts greatly affect the quality of brain MRI and negatively influence downstream medical image analysis. Previous studies often focus on 2D methods that process each volumetric MR image slice-by-slice, thus losing important 3D anatomical information. Additionally, these studies generally treat image denoising and artifact correction as two standalone tasks, without considering their potential relationship, especially on low-quality images where severe noise and motion artifacts occur simultaneously. To address these issues, we propose a Joint image Denoising and motion Artifact Correction (JDAC) framework via iterative learning to handle noisy MRIs with motion artifacts, consisting of an adaptive denoising model and an anti-artifact model. In the adaptive denoising model, we first design a novel noise level estimation strategy, and then adaptively reduce the noise through a U-Net backbone with feature normalization conditioning on the estimated noise variance. The anti-artifact model employs another U-Net for eliminating motion artifacts, incorporating a novel gradient-based loss function designed to maintain the integrity of brain anatomy during the motion correction process. These two models are iteratively employed for joint image denoising and artifact correction through an iterative learning framework. An early stopping strategy depending on noise level estimation is applied to accelerate the iteration process. The denoising model is trained with 9,544 T1-weighted MRIs with manually added Gaussian noise as supervision. The anti-artifact model is trained on 552 T1-weighted MRIs with motion artifacts and paired motion-free images. Experimental results on a public dataset and a clinical study suggest the effectiveness of JDAC in both tasks of denoising and motion artifact correction, compared with several state-of-the-art methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. FONDUE: Robust resolution-invariant denoising of MR images using nested UNets. bioRxiv , 2023–06.
  2. Statistical analysis of noise in MRI. Switzerland: Springer International Publishing .
  3. Stacked U-Nets with self-assisted priors towards robust correction of rigid motion artifact in brain MRI. NeuroImage 259, 119411.
  4. Advanced Normalization Tools (ANTS). Insight J 2, 1–35.
  5. Quality control of structural MRI images applied using FreeSurfer—A hands-on workflow to rate motion artifacts. Frontiers in Neuroscience 10, 558.
  6. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends® in Machine learning 3, 1–122.
  7. Artifacts in magnetic resonance imaging: How it can really affect diagnostic image quality and confuse clinical diagnosis? Journal of Vibroengineering 20, 1202–1213.
  8. PreQual: An automated pipeline for integrated preprocessing and quality assurance of diffusion weighted MRI images. Magnetic Resonance in Medicine 86, 456–470.
  9. Monai: An open-source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701 .
  10. Plug-and-play ADMM for image restoration: Fixed-point convergence and applications. IEEE Transactions on Computational Imaging 3, 84–98.
  11. Deep learning-based rigid motion correction for magnetic resonance imaging: A survey. Meta-Radiology , 100001.
  12. 3D U-Net: Learning dense volumetric segmentation from sparse annotation, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19, Springer. pp. 424–432.
  13. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing 16, 2080–2095.
  14. Denoising prior driven deep neural network for image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence 41, 2305–2318.
  15. Retrospective correction of motion artifact affected structural MRI images using deep learning of simulated motion, in: Medical Imaging with Deep Learning.
  16. Retrospective motion artifact correction of structural MRI images using deep learning improves the quality of cortical surface reconstructions. NeuroImage 230, 117756.
  17. Adaptive removal of high-density salt-and-pepper noise (ARSPN) for robust ROI detection used in watermarking of MRI images of the brain. Computers in Biology and Medicine 137, 104831.
  18. FreeSurfer. NeuroImage 62, 774–781.
  19. PET image denoising based on denoising diffusion probabilistic model. European Journal of Nuclear Medicine and Molecular Imaging , 1–11.
  20. Body MRI artifacts in clinical practice: A physicist’s and radiologist’s perspective. Journal of Magnetic Resonance Imaging 38, 269–287.
  21. The Rician distribution of noisy MRI data. Magnetic Resonance in Medicine 34, 910–914.
  22. Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model. Magnetic Resonance in Medicine 82, 1452–1461.
  23. Review on deep learning methodologies in medical image restoration and segmentation. Current Medical Imaging 19, 844–854.
  24. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems 33, 6840–6851.
  25. Truncated residual based plug-and-play ADMM algorithm for MRI reconstruction. IEEE Transactions on Computational Imaging 8, 96–108.
  26. No new-net, in: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part II 4, Springer. pp. 234–244.
  27. The Alzheimer’s disease neuroimaging initiative (ADNI): MRI methods. Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine 27, 685–691.
  28. FSL. NeuroImage 62, 782–790.
  29. ArtifactID: Identifying artifacts in low-field MRI of the brain using deep learning. Magnetic Resonance Imaging 89, 42–48.
  30. A complete review on image denoising techniques for medical images. Neural Processing Letters 55, 7807–7850.
  31. Denoising diffusion restoration models. Advances in Neural Information Processing Systems 35, 23593–23606.
  32. Noise2score: Tweedie’s approach to self-supervised image denoising without clean images. Advances in Neural Information Processing Systems 34, 864–874.
  33. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 .
  34. Noise2Noise: Learning image restoration without clean data, in: International Conference on Machine Learning, PMLR. pp. 2965–2974.
  35. Motion artifacts reduction in brain MRI by means of a deep residual network with densely connected multi-resolution blocks (DRN-DCMB). Magnetic Resonance Imaging 71, 69–79.
  36. UDC-UNet: Under-display camera image restoration via U-shape dynamic network, in: European Conference on Computer Vision, Springer. pp. 113–129.
  37. Collaborative filtering of correlated noise: Exact transform-domain variance for improved shrinkage and patch matching. IEEE Transactions on Image Processing 29, 8339–8354.
  38. Ring artifact and poisson noise attenuation via volumetric multiscale nonlocal collaborative filtering of spatially correlated noise. Journal of Synchrotron Radiation 29, 829–842.
  39. Towards an optimised processing pipeline for diffusion magnetic resonance imaging data: Effects of artefact corrections on diffusion metrics and their age associations in UK Biobank. Human Brain Mapping 40, 4146–4162.
  40. A survey on the magnetic resonance image denoising methods. Biomedical Signal Processing and Control 9, 56–69.
  41. An image-based approach to understanding the physics of MR artifacts. RadioGraphics 31, 849–866.
  42. MRIquestions.com, 2015. Why do motion artifacts often form into discrete ghosts? URL: https://mriquestions.com/why-discrete-ghosts.html.
  43. Movement-related artefacts (MR-ART) dataset of matched motion-corrupted and clean structural MRI brain scans. Scientific Data 9, 630.
  44. Improved denoising diffusion probabilistic models, in: International Conference on Machine Learning, PMLR. pp. 8162–8171.
  45. Deconvolution and checkerboard artifacts. Distill 1, e3.
  46. TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Computer Methods and Programs in Biomedicine 208, 106236.
  47. A review of wavelet denoising in MRI and ultrasound brain imaging. Current Medical Imaging 2, 247–260.
  48. Plug-and-play methods provably converge with properly trained denoisers, in: International Conference on Machine Learning, PMLR. pp. 5546–5557.
  49. MRI motion artifact reduction using a conditional diffusion probabilistic model (MAR-CDPM). Medical Physics .
  50. A review on medical image denoising algorithms. Biomedical Signal Processing and Control 61, 102036.
  51. MRI k-space motion artefact augmentation: Model robustness and task-specific uncertainty, in: International Conference on Medical Imaging with Deep Learning, PMLR. pp. 427–436.
  52. Correction of motion artifacts using a multiscale fully convolutional neural network. American Journal of Neuroradiology 41, 416–423.
  53. Generative modeling by estimating gradients of the data distribution. Advances in Neural Information Processing Systems 32.
  54. Negative affectivity, aging, and depression: Results from the neurobiology of late-life depression (NBOLD) study. The American Journal of Geriatric Psychiatry 25, 1135–1149.
  55. MRtrix3: A fast, flexible and open software framework for medical image processing and visualisation. NeuroImage 202, 116137.
  56. Plug-and-play priors for model based reconstruction, in: 2013 IEEE Global Conference on Signal and Information Processing, IEEE. pp. 945–948.
  57. DDM22{}^{2}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPT: Self-supervised diffusion MRI denoising with generative diffusion models, in: The Eleventh International Conference on Learning Representations.
  58. CT artifact reduction via U-net CNN, in: Medical Imaging 2018: Image Processing, SPIE. pp. 440–445.
  59. Plug-and-play image restoration with deep denoiser prior. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 6360–6376.
  60. Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Transactions on Medical Imaging 39, 1856–1867.
  61. Denoising diffusion models for plug-and-play image restoration, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1219–1229.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now