Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
12 tokens/sec
GPT-4o
12 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
37 tokens/sec
DeepSeek R1 via Azure Pro
33 tokens/sec
2000 character limit reached

Two-and-a-half Order Score-based Model for Solving 3D Ill-posed Inverse Problems (2308.08511v3)

Published 16 Aug 2023 in eess.IV, cs.CV, and cs.LG

Abstract: Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are crucial technologies in the field of medical imaging. Score-based models have proven to be effective in addressing different inverse problems encountered in CT and MRI, such as sparse-view CT and fast MRI reconstruction. However, these models face challenges in achieving accurate three dimensional (3D) volumetric reconstruction. The existing score-based models primarily focus on reconstructing two dimensional (2D) data distribution, leading to inconsistencies between adjacent slices in the reconstructed 3D volumetric images. To overcome this limitation, we propose a novel two-and-a-half order score-based model (TOSM). During the training phase, our TOSM learns data distributions in 2D space, which reduces the complexity of training compared to directly working on 3D volumes. However, in the reconstruction phase, the TOSM updates the data distribution in 3D space, utilizing complementary scores along three directions (sagittal, coronal, and transaxial) to achieve a more precise reconstruction. The development of TOSM is built on robust theoretical principles, ensuring its reliability and efficacy. Through extensive experimentation on large-scale sparse-view CT and fast MRI datasets, our method demonstrates remarkable advancements and attains state-of-the-art results in solving 3D ill-posed inverse problems. Notably, the proposed TOSM effectively addresses the inter-slice inconsistency issue, resulting in high-quality 3D volumetric reconstruction.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. Spectral2spectral: Image-spectral similarity assisted deep spectral ct reconstruction without reference. IEEE Transactions on Computational Imaging, 2023.
  2. Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images. Scientific Reports, 11(1):10930, 2021.
  3. An attention-based deep convolutional neural network for ultra-sparse-view ct reconstruction. Computers in Biology and Medicine, 161:106888, 2023.
  4. Kumar, Ashwani. Light propagation through biological tissue: comparison between Monte Carlo simulation and deterministic models. International Journal of Biomedical Engineering and Technology, 2(4):344–351, 2009.
  5. Aggarwal, Ashwani. Light Propagation in Biological tissue using Monte Carlo Simulation. In Recent Advances In Computational Science And Engineering, pages 19–22. World Scientific, 2002.
  6. A cascade-based dual-domain data correction network for sparse view ct image reconstruction. Computers in Biology and Medicine, 165:107345, 2023.
  7. Low-dose ct with a residual encoder-decoder convolutional neural network. IEEE Transactions on Medical Imaging, 36(12):2524–2535, 2017.
  8. Drone: dual-domain residual-based optimization network for sparse-view CT reconstruction. IEEE Transactions on Medical Imaging, 40(11):3002–3014, 2021.
  9. Deep embedding-attention-refinement for sparse-view ct reconstruction. IEEE Transactions on Instrumentation and Measurement, 72:1–11, 2022.
  10. Dagan: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Transactions on Medical Imaging, 37(6):1310–1321, 2017.
  11. Solving 3d inverse problems using pre-trained 2d diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22542–22551, 2023.
  12. Deep learning based spectral ct imaging. Neural Networks, 144:342–358, 2021.
  13. Camera position estimation using 2D image dataset. Int. J. Innov. Eng. Technol., 10:199–203, 2018.
  14. Experimental analysis of effect of tuning parameters on the performance of diversity-driven multi-parent evolutionary algorithm. In 2021 IEEE 2Nd international conference on electrical power and energy systems (ICEPES), pages 1–6. IEEE, 2021.
  15. A deep learning approach for robust, multi-oriented, and curved text detection. Cognitive computation, pages 1–13, 2022.
  16. Neural network-based tracking control of uncertain robotic systems: predefined-time nonsingular terminal sliding-mode approach. IEEE transactions on Industrial Electronics, 69(10):10510–10520, 2022.
  17. HECON: Weight assessment of the product loyalty criteria considering the customer decision’s halo effect using the convolutional neural networks. Information Sciences, 623:184–205, 2023.
  18. Review of deep learning approaches for thyroid cancer diagnosis. Mathematical Problems in Engineering, 2022:1–8, 2022.
  19. Cnn-based projected gradient descent for consistent ct image reconstruction. IEEE Transactions on Medical Imaging, 37(6):1440–1453, 2018.
  20. ME-CCNN: Multi-encoded images and a cascade convolutional neural network for breast tumor segmentation and recognition. Artificial Intelligence Review, pages 1–38, 2023.
  21. Glioma Brain Tumor Segmentation in Four MRI Modalities Using a Convolutional Neural Network and Based on a Transfer Learning Method. In Brazilian Technology Symposium, pages 386–402. Springer, 2021.
  22. X2ct-gan: reconstructing ct from biplanar x-rays with generative adversarial networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10619–10628, 2019.
  23. Multi-domain integrative swin transformer network for sparse-view tomographic reconstruction. Patterns, page 100498, 2022.
  24. Point-of-Interest Preference Model Using an Attention Mechanism in a Convolutional Neural Network. Bioengineering, 10(4):495, 2023.
  25. Solving inverse problems in medical imaging with score-based generative models. In International Conference on Learning Representations, 2022.
  26. Score-based generative modeling through stochastic differential equations. In International Conference on Learning Representations, 2021.
  27. Score-based diffusion models for accelerated MRI. Medical Image Analysis, 80:102479, 2022.
  28. Generative modeling in sinogram domain for sparse-view ct reconstruction. IEEE Transactions on Radiation and Plasma Medical Sciences, 2023.
  29. Sparse-view cbct reconstruction via weighted schatten p-norm minimization. Optics Express, 28(24):35469–35482, 2020.
  30. Review of 2-d/3-d reconstruction using statistical shape and intensity models and x-ray image synthesis: Toward a unified framework. IEEE Reviews in Biomedical Engineering, 12:269–286, 2018.
  31. A review of translational medicine. The future paradigm: how can we connect the orthopedic dots better? Current medical research and opinion, 34(7):1217–1229, 2018.
  32. Translational medicine: challenges and new orthopaedic vision (Mediouni-Model). Current orthopaedic practice, 31(2):196–200, 2020.
  33. A methodological review of 3d reconstruction techniques in tomographic imaging. Journal of Medical Systems, 42(10):190, 2018.
  34. 3d reconstruction of medical images from slices automatically landmarked with growing neural models. Neurocomputing, 150:16–25, 2015.
  35. Ivan Selesnick. Total variation denoising (an mm algorithm). NYU Polytechnic School of Engineering Lecture Notes, 32, 2012.
  36. Improving 3d imaging with pre-trained perpendicular 2d diffusion models. arXiv preprint arXiv:2303.08440, 2023.
  37. Fundus-DeepNet: Multi-label deep learning classification system for enhanced detection of multiple ocular diseases through data fusion of fundus images. Information Fusion, 102:102059, 2024.
  38. A hybrid cancer prediction based on multi-omics data and reinforcement learning state action reward state action (SARSA). Computers in Biology and Medicine, 154:106617, 2023.
  39. Classification of breast cancer images using new transfer learning techniques. Iraqi Journal For Computer Science and Mathematics, 4(1):167–180, 2023.
  40. Incorporating a Novel Dual Transfer Learning Approach for Medical Images. Sensors, 23(2):570, 2023.
  41. Median prior constrained tv algorithm for sparse view low-dose ct reconstruction. Computers in biology and medicine, 60:117–131, 2015.
  42. Reconstruction of sparse-view x-ray computed tomography using adaptive iterative algorithms. Computers in biology and medicine, 56:97–106, 2015.
  43. Deep convolutional neural network for inverse problems in imaging. IEEE Transactions on Image Processing, 26(9):4509–4522, 2017.
  44. Image reconstruction with transformer for mask-based lensless imaging. Optics Letters, 47(7):1843–1846, 2022.
  45. Improved techniques for training score-based generative models. Advances in Neural Information Processing Systems, 33:12438–12448, 2020.
  46. A novel method for fast imaging of brain function, non-invasively, with light. Optics express, 2(10):411–423, 1998.
  47. Compressed sensing mri. IEEE Signal Processing Magazine, 25(2):72–82, 2008.
  48. A brief review on: Mri images reconstruction using gan. In 2019 International Conference on Communication and Signal Processing (ICCSP), pages 0139–0142. IEEE, 2019.
  49. Wavelet-improved score-based generative model for medical imaging. IEEE Transactions on Medical Imaging, pages 1–1, 2023.
  50. Generative modeling by estimating gradients of the data distribution. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019.
  51. Point-voxel cnn for efficient 3d deep learning. Advances in Neural Information Processing Systems, 32, 2019.
  52. Diffusion probabilistic models for 3d point cloud generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2837–2845, 2021.
  53. Computational analysis and improvement of sirt. IEEE Transactions on Medical Imaging, 27(7):918–924, 2008.
  54. Projection onto convex sets super-resolution image reconstruction based on wavelet bi-cubic interpolation. In Proceedings of 2011 International Conference on Electronic & Mechanical Engineering and Information Technology, volume 1, pages 351–354. IEEE, 2011.
  55. Deep learning for undersampled mri reconstruction. Physics in Medicine & Biology, 63(13):135007, 2018.
  56. C McCollough. Overview of the low dose ct grand challenge. Medical physics, 43(6Part35):3759–3760, 2016.
  57. The multimodal brain tumor image segmentation benchmark (brats). IEEE Transactions on Medical Imaging, 34(10):1993–2024, 2014.
  58. fastmri: An open dataset and benchmarks for accelerated mri. arXiv preprint arXiv:1811.08839, 2018.
  59. The astra toolbox: A platform for advanced algorithm development in electron tomography. Ultramicroscopy, 157:35–47, 2015.
  60. The noise power spectrum of ct images. Physics in Medicine & Biology, 32(5):565, 1987.
  61. Revisiting 1-wavelet compressed-sensing mri in the era of deep learning. Proceedings of the National Academy of Sciences, 119(33):e2201062119, 2022.
Citations (9)
View on Semantic Scholar

Summary

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

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