Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Neural Ordinary Differential Equation based Sequential Image Registration for Dynamic Characterization (2404.02106v1)

Published 2 Apr 2024 in cs.CV and cs.CE

Abstract: Deformable image registration (DIR) is crucial in medical image analysis, enabling the exploration of biological dynamics such as organ motions and longitudinal changes in imaging. Leveraging Neural Ordinary Differential Equations (ODE) for registration, this extension work discusses how this framework can aid in the characterization of sequential biological processes. Utilizing the Neural ODE's ability to model state derivatives with neural networks, our Neural Ordinary Differential Equation Optimization-based (NODEO) framework considers voxels as particles within a dynamic system, defining deformation fields through the integration of neural differential equations. This method learns dynamics directly from data, bypassing the need for physical priors, making it exceptionally suitable for medical scenarios where such priors are unavailable or inapplicable. Consequently, the framework can discern underlying dynamics and use sequence data to regularize the transformation trajectory. We evaluated our framework on two clinical datasets: one for cardiac motion tracking and another for longitudinal brain MRI analysis. Demonstrating its efficacy in both 2D and 3D imaging scenarios, our framework offers flexibility and model agnosticism, capable of managing image sequences and facilitating label propagation throughout these sequences. This study provides a comprehensive understanding of how the Neural ODE-based framework uniquely benefits the image registration challenge.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. Characterizing the human hippocampus in aging and alzheimer’s disease using a computational atlas derived from ex vivo mri and histology. Proceedings of the National Academy of Sciences 115, 4252–4257.
  2. An unsupervised learning model for deformable medical image registration, in: CVPR, pp. 9252–9260.
  3. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International journal of computer vision 61, 139–157.
  4. IEEE transactions on medical imaging 37, 2514–2525.
  5. 3d whole-heart isotropic sub-millimeter resolution coronary magnetic resonance angiography with non-rigid motion-compensated prost. Journal of Cardiovascular Magnetic Resonance 22, 24.
  6. Assessing atrophy measurement techniques in dementia: Results from the miriad atrophy challenge. Neuroimage 123, 149–164.
  7. Construction of a statistical model for cardiac motion analysis using nonrigid image registration, in: Information Processing in Medical Imaging: 18th International Conference, IPMI 2003, Ambleside, UK, July 20-25, 2003. Proceedings 18, Springer. pp. 599–610.
  8. Neural ordinary differential equations. Advances in Neural Information Processing Systems (NeurIPS) .
  9. A viscous fluid model for multimodal non-rigid image registration using mutual information. Medical image analysis 7, 565–575.
  10. Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces. Medical image analysis 57, 226–236.
  11. Learning conditional deformable templates with convolutional networks. IEEE TMI: Transactions on Medical Imaging .
  12. Measuring longitudinal change in the hippocampal formation from in vivo high-resolution t2-weighted mri. Neuroimage 60, 1266–1279.
  13. Deepatrophy: Teaching a neural network to detect progressive changes in longitudinal mri of the hippocampal region in alzheimer’s disease. Neuroimage 243, 118514.
  14. Regional deep atrophy: a self-supervised learning method to automatically identify regions associated with alzheimer’s disease progression from longitudinal mri. ArXiv .
  15. Research criteria for the diagnosis of alzheimer’s disease: revising the nincds–adrda criteria. The Lancet Neurology 6, 734–746.
  16. Statistical modeling of 4d respiratory lung motion using diffeomorphic image registration. IEEE transactions on medical imaging 30, 251–265.
  17. Respiration-correlated spiral ct: a method of measuring respiratory-induced anatomic motion for radiation treatment planning. Medical physics 30, 88–97.
  18. The boundary shift integral: an accurate and robust measure of cerebral volume changes from registered repeat mri. IEEE transactions on medical imaging 16, 623–629.
  19. Elastically deforming a three-dimensional atlas to match anatomical brain images .
  20. Dynamic ventilation imaging from four-dimensional computed tomography. Physics in Medicine & Biology 51, 777.
  21. Diffeomorphic image registration with neural velocity field, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1869–1879.
  22. Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778.
  23. 3d characterization of brain atrophy in alzheimer’s disease and mild cognitive impairment using tensor-based morphometry. Neuroimage 41, 19–34.
  24. Nia-aa research framework: toward a biological definition of alzheimer’s disease. Alzheimer’s & Dementia 14, 535–562.
  25. Knowledge-based learning of nonlinear dynamics and chaos. Chaos: An Interdisciplinary Journal of Nonlinear Science .
  26. Learning compositional representation for 4d captures with neural ode, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5340–5350.
  27. Multiresolution registration of coronary artery image sequences. International journal of medical informatics 44, 93–104.
  28. Learning a generative motion model from image sequences based on a latent motion matrix. IEEE Transactions on Medical Imaging 40, 1405–1416.
  29. Novel breathing motion model for radiotherapy. International Journal of Radiation Oncology* Biology* Physics 63, 921–929.
  30. A continuous 4d motion model from multiple respiratory cycles for use in lung radiotherapy. Medical Physics 33, 3348–3358.
  31. A study of the motion and deformation of the heart due to respiration. IEEE transactions on medical imaging 21, 1142–1150.
  32. Geodesic shooting for computational anatomy. Journal of mathematical imaging and vision 24, 209–228.
  33. Fast symmetric diffeomorphic image registration with convolutional neural networks, in: CVPR, pp. 4644–4653.
  34. Cardiac motion and deformation estimation from tagged mri sequences using a temporal coherent image registration framework, in: Functional Imaging and Modeling of the Heart: 7th International Conference, FIMH 2013, London, UK, June 20-22, 2013. Proceedings 7, Springer. pp. 316–324.
  35. Self-supervised learning of neighborhood embedding for longitudinal mri. Medical image analysis 82, 102571.
  36. Longitudinal brain structural changes in preclinical alzheimer’s disease. Alzheimer’s & Dementia 13, 499–509.
  37. Alzheimer’s disease neuroimaging initiative (adni) clinical characterization. Neurology 74, 201–209.
  38. Measuring brain atrophy with a generalized formulation of the boundary shift integral. Neurobiology of aging 36, S81–S90.
  39. Joint learning of motion estimation and segmentation for cardiac mr image sequences, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 472–480.
  40. Generative myocardial motion tracking via latent space exploration with biomechanics-informed prior. Medical Image Analysis 83, 102682.
  41. Biomechanics-informed neural networks for myocardial motion tracking in mri, in: International conference on medical image computing and computer-assisted intervention, Springer. pp. 296–306.
  42. Registration-based estimates of local lung tissue expansion compared to xenon ct measures of specific ventilation. Medical image analysis 12, 752–763.
  43. Intensity-based non-rigid registration using adaptive multilevel free-form deformation with an incompressibility constraint, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 111–119.
  44. Estimation of large motion in lung ct by integrating regularized keypoint correspondences into dense deformable registration. IEEE transactions on medical imaging 36, 1746–1757.
  45. Cardiovascular magnetic resonance feature-tracking assessment of myocardial mechanics: Intervendor agreement and considerations regarding reproducibility. Clinical radiology 70, 989–998.
  46. Networks for joint affine and non-parametric image registration, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4224–4233.
  47. Implicit neural representations with periodic activation functions. Advances in neural information processing systems 33, 7462–7473.
  48. Deformable medical image registration: A survey. IEEE transactions on medical imaging 32, 1153–1190.
  49. Topology-preserving shape reconstruction and registration via neural diffeomorphic flow, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20845–20855.
  50. Medical image registration via neural fields. arXiv preprint arXiv:2206.03111 .
  51. Data-driven tissue mechanics with polyconvex neural ordinary differential equations. Computer Methods in Applied Mechanics and Engineering 398, 115248.
  52. Shape-based nonrigid correspondence with application to heart motion analysis. IEEE transactions on Medical Imaging 18, 570–579.
  53. Myocardial strain measurement with feature-tracking cardiovascular magnetic resonance: normal values. European Heart Journal–Cardiovascular Imaging 16, 871–881.
  54. Deep image prior, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 9446–9454.
  55. Echocardiography segmentation using neural ode-based diffeomorphic registration field. arXiv preprint arXiv:2306.09687 .
  56. Non-parametric diffeomorphic image registration with the demons algorithm, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 319–326.
  57. Recommendations to improve imaging and analysis of brain lesion load and atrophy in longitudinal studies of multiple sclerosis. Journal of neurology 260, 2458–2471.
  58. Developmental topography of cortical thickness during infancy. Proceedings of the National Academy of Sciences 116, 15855–15860.
  59. Nodeo: A neural ordinary differential equation based optimization framework for deformable image registration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) .
  60. Longitudinal atrophy in early braak regions in preclinical alzheimer’s disease. Human brain mapping 41, 4704–4717.
  61. Automated segmentation of medial temporal lobe subregions on in vivo t1-weighted mri in early stages of alzheimer’s disease. Human brain mapping 40, 3431–3451.
  62. Multi-scale neural odes for 3d medical image registration, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part IV 24, Springer. pp. 213–223.
  63. Quicksilver: Fast predictive image registration–a deep learning approach. NeuroImage 158, 378–396.
  64. Ic-p-174: fast automatic segmentation of hippocampal subfields and medial temporal lobe subregions in 3 tesla and 7 tesla t2-weighted mri. Alzheimer’s & Dementia 12, P126–P127.
  65. Test-time training for deformable multi-scale image registration, in: 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE. pp. 13618–13625.
  66. Adaptive checkpoint adjoint method for gradient estimation in neural ode, in: International Conference on Machine Learning, PMLR. pp. 11639–11649.

Summary

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

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