Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution (2404.04785v1)

Published 7 Apr 2024 in cs.CV

Abstract: Recently, diffusion models (DM) have been applied in magnetic resonance imaging (MRI) super-resolution (SR) reconstruction, exhibiting impressive performance, especially with regard to detailed reconstruction. However, the current DM-based SR reconstruction methods still face the following issues: (1) They require a large number of iterations to reconstruct the final image, which is inefficient and consumes a significant amount of computational resources. (2) The results reconstructed by these methods are often misaligned with the real high-resolution images, leading to remarkable distortion in the reconstructed MR images. To address the aforementioned issues, we propose an efficient diffusion model for multi-contrast MRI SR, named as DiffMSR. Specifically, we apply DM in a highly compact low-dimensional latent space to generate prior knowledge with high-frequency detail information. The highly compact latent space ensures that DM requires only a few simple iterations to produce accurate prior knowledge. In addition, we design the Prior-Guide Large Window Transformer (PLWformer) as the decoder for DM, which can extend the receptive field while fully utilizing the prior knowledge generated by DM to ensure that the reconstructed MR image remains undistorted. Extensive experiments on public and clinical datasets demonstrate that our DiffMSR outperforms state-of-the-art methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Hierarchical integration diffusion model for realistic image deblurring. In NeurIPS, 2023.
  2. Score-based diffusion models for accelerated mri. Medical image analysis, 80:102479, 2022.
  3. Taming transformers for high-resolution image synthesis. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12873–12883, 2021.
  4. Multi-contrast mri super-resolution via a multi-stage integration network. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2021a.
  5. Brain mri super-resolution using coupled-projection residual network. Neurocomputing, 456:190–199, 2021b.
  6. Superformer: Volumetric transformer architectures for mri super-resolution. In International Workshop on Simulation and Synthesis in Medical Imaging, pages 132–141. Springer, 2022.
  7. Semi-implicit denoising diffusion models (siddms). In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  8. Generative adversarial nets. Advances in neural information processing systems, 27, 2014.
  9. Adaptive diffusion priors for accelerated mri reconstruction. Medical Image Analysis, page 102872, 2023.
  10. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020.
  11. Accurate multi-contrast mri super-resolution via a dual cross-attention transformer network. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 313–322. Springer, 2023.
  12. Cola-diff: Conditional latent diffusion model for multi-modal mri synthesis. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 398–408. Springer, 2023.
  13. Super-resolution method for mr images based on multi-resolution cnn. Biomedical Signal Processing and Control, 72:103372, 2022.
  14. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  15. Decomposition-based variational network for multi-contrast mri super-resolution and reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 21296–21306, 2023.
  16. High-resolution pelvic mri reconstruction using a generative adversarial network with attention and cyclic loss. IEEE Access, 9:105951–105964, 2021.
  17. Transformer-empowered multi-scale contextual matching and aggregation for multi-contrast mri super-resolution. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20604–20613, 2022a.
  18. Wavtrans: Synergizing wavelet and cross-attention transformer for multi-contrast mri super-resolution. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022b.
  19. Dudoinet: Dual-domain implicit network for multi-modality mr image arbitrary-scale super-resolution. In Proceedings of the 31st ACM International Conference on Multimedia, page 7335–7344, 2023a.
  20. Rethinking multi-contrast mri super-resolution: Rectangle-window cross-attention transformer and arbitrary-scale upsampling. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 21230–21240, 2023b.
  21. Swinir: Image restoration using swin transformer. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1833–1844, 2021.
  22. Masa-sr: Matching acceleration and spatial adaptation for reference-based image super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6368–6377, 2021.
  23. Dudocaf: Dual-domain cross-attention fusion with recurrent transformer for fast multi-contrast mr imaging. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 474–484. Springer, 2022.
  24. Multicontrast mri super-resolution via transformer-empowered multiscale contextual matching and aggregation. IEEE Transactions on Neural Networks and Learning Systems, 2023a.
  25. Region-focused multi-view transformer-based generative adversarial network for cardiac cine mri reconstruction. Medical Image Analysis, 85:102760, 2023b.
  26. Multi-contrast super-resolution mri through a progressive network. IEEE Transactions on Medical Imaging, 39:2738–2749, 2019.
  27. Non-local mri upsampling. Medical image analysis, 14(6):784–792, 2010.
  28. Disc-diff: Disentangled conditional diffusion model for multi-contrast mri super-resolution. Springer, 2023.
  29. A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis. Scientific Reports, 13(1):12098, 2023.
  30. Unsupervised medical image translation with adversarial diffusion models. IEEE Transactions on Medical Imaging, 2023.
  31. Super-resolution image reconstruction: a technical overview. IEEE signal processing magazine, 20(3):21–36, 2003.
  32. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
  33. Towards performant and reliable undersampled mr reconstruction via diffusion model sampling. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 623–633. Springer, 2022.
  34. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695, 2022.
  35. Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4713–4726, 2022.
  36. Improving the brain image resolution of generalized q-sampling mri revealed by a three-dimensional cnn-based method. Frontiers in Neuroinformatics, 17:956600, 2023.
  37. Going deeper with image transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 32–42, 2021.
  38. Inversesr: 3d brain mri super-resolution using a latent diffusion model. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 438–447. Springer, 2023.
  39. Diffir: Efficient diffusion model for image restoration. ICCV, 2023.
  40. Measurement-conditioned denoising diffusion probabilistic model for under-sampled medical image reconstruction. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 655–664. Springer, 2022.
  41. Image super-resolution via sparse representation. IEEE transactions on image processing, 19(11):2861–2873, 2010.
  42. Sadm: Sequence-aware diffusion model for longitudinal medical image generation. In International Conference on Information Processing in Medical Imaging, pages 388–400. Springer, 2023.
  43. fastmri: An open dataset and benchmarks for accelerated mri. arXiv preprint arXiv:1811.08839, 2018.
  44. On single image scale-up using sparse-representations. In Curves and Surfaces: 7th International Conference, Avignon, France, June 24-30, 2010, Revised Selected Papers 7, pages 711–730. Springer, 2012.
  45. Mr image super-resolution with squeeze and excitation reasoning attention network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13425–13434, 2021.
  46. Srformer: Permuted self-attention for single image super-resolution. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Guangyuan Li (32 papers)
  2. Chen Rao (2 papers)
  3. Juncheng Mo (2 papers)
  4. Zhanjie Zhang (14 papers)
  5. Wei Xing (34 papers)
  6. Lei Zhao (808 papers)
Citations (10)
View on Semantic Scholar

Summary

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

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