Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
166 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 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

The Developing Human Connectome Project: A Fast Deep Learning-based Pipeline for Neonatal Cortical Surface Reconstruction (2405.08783v2)

Published 14 May 2024 in eess.IV

Abstract: The Developing Human Connectome Project (dHCP) aims to explore developmental patterns of the human brain during the perinatal period. An automated processing pipeline has been developed to extract high-quality cortical surfaces from structural brain magnetic resonance (MR) images for the dHCP neonatal dataset. However, the current implementation of the pipeline requires more than 6.5 hours to process a single MRI scan, making it expensive for large-scale neuroimaging studies. In this paper, we propose a fast deep learning (DL) based pipeline for dHCP neonatal cortical surface reconstruction, incorporating DL-based brain extraction, cortical surface reconstruction and spherical projection, as well as GPU-accelerated cortical surface inflation and cortical feature estimation. We introduce a multiscale deformation network to learn diffeomorphic cortical surface reconstruction end-to-end from T2-weighted brain MRI. A fast unsupervised spherical mapping approach is integrated to minimize metric distortions between cortical surfaces and projected spheres. The entire workflow of our DL-based dHCP pipeline completes within only 24 seconds on a modern GPU, which is nearly 1000 times faster than the original dHCP pipeline. The qualitative assessment demonstrates that for 82.5% of the test samples, the cortical surfaces reconstructed by our DL-based pipeline achieve superior (54.2%) or equal (28.3%) surface quality compared to the original dHCP pipeline.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (73)
  1. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 .
  2. A log-euclidean framework for statistics on diffeomorphisms, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2006: 9th International Conference, Copenhagen, Denmark, October 1-6, 2006. Proceedings, Part I 9, Springer. pp. 924–931.
  3. A fast diffeomorphic image registration algorithm. Neuroimage 38, 95–113.
  4. Advanced normalization tools (ANTS). Insight j 2, 1–35.
  5. VoxelMorph: a learning framework for deformable medical image registration. IEEE transactions on medical imaging 38, 1788–1800.
  6. Topology correction using fast marching methods and its application to brain segmentation, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 484–491.
  7. Topology correction of segmented medical images using a fast marching algorithm. Computer methods and programs in biomedicine 88, 182–190.
  8. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International journal of computer vision 61, 139–157.
  9. Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets. Proceedings of the National Academy of Sciences 120, e2216399120.
  10. Vox2Cortex: Fast explicit reconstruction of cortical surfaces from 3D MRI scans with geometric deep neural networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20773–20783.
  11. Construction of a neonatal cortical surface atlas using multimodal surface matching in the developing human connectome project. NeuroImage 179, 11–29.
  12. Three-dimensional motion corrected sensitivity encoding reconstruction for multi-shot multi-slice MRI: application to neonatal brain imaging. Magnetic resonance in medicine 79, 1365–1376.
  13. DeepCSR: A 3D deep learning approach for cortical surface reconstruction, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 806–815.
  14. iBEAT: a toolbox for infant brain magnetic resonance image processing. Neuroinformatics 11, 211–225.
  15. Cortical surface-based analysis I: Segmentation and surface reconstruction. Neuroimage 9, 179–194.
  16. Effect of MRI on preterm infants and their families: a randomised trial with nested diagnostic and economic evaluation. Archives of Disease in Childhood-Fetal and Neonatal Edition 103, F15–F21.
  17. The developing human connectome project neonatal data release. Frontiers in Neuroscience 16.
  18. Texture mapping via spherical multi-dimensional scaling, in: International Conference on Scale-Space Theories in Computer Vision, Springer. pp. 443–455.
  19. A point set generation network for 3D object reconstruction from a single image, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 605–613.
  20. A deep learning approach to segmentation of the developing cortex in fetal brain MRI with minimal manual labeling, in: Medical Imaging with Deep Learning, PMLR. pp. 241–261.
  21. Freesurfer. Neuroimage 62, 774–781.
  22. Cortical surface-based analysis II: Inflation, flattening, and a surface-based coordinate system. Neuroimage 9, 195–207.
  23. High-resolution intersubject averaging and a coordinate system for the cortical surface. Human brain mapping 8, 272–284.
  24. Dynamic patterns of cortical expansion during folding of the preterm human brain. Proceedings of the National Academy of Sciences 115, 3156–3161.
  25. The minimal preprocessing pipelines for the Human Connectome Project. Neuroimage 80, 105–124.
  26. Mapping human cortical areas in vivo based on myelin content as revealed by T1-and T2-weighted MRI. Journal of neuroscience 31, 11597–11616.
  27. Harmonized segmentation of neonatal brain MRI. Frontiers in Neuroscience 15, 662005.
  28. Fastsurfer-a fast and accurate deep learning based neuroimaging pipeline. NeuroImage 219, 117012.
  29. TopoFit: Rapid reconstruction of topologically-correct cortical surfaces, in: Medical Imaging with Deep Learning.
  30. A dedicated neonatal brain imaging system. Magnetic resonance in medicine 78, 794–804.
  31. FSL. Neuroimage 62, 782–790.
  32. Automated 3-D extraction and evaluation of the inner and outer cortical surfaces using a Laplacian map and partial volume effect classification. Neuroimage 27, 210–221.
  33. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 .
  34. Reconstruction of fetal brain MRI with intensity matching and complete outlier removal. Medical image analysis 16, 1550–1564.
  35. CorticalFlow: A diffeomorphic mesh transformer network for cortical surface reconstruction. Advances in Neural Information Processing Systems 34, 29491–29505.
  36. Marching cubes: A high resolution 3d surface construction algorithm, in: Seminal graphics: pioneering efforts that shaped the field, pp. 347–353.
  37. Conditional temporal attention networks for neonatal cortical surface reconstruction, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 312–322.
  38. CortexODE: Learning cortical surface reconstruction by neural ODEs. IEEE Transactions on Medical Imaging 42, 430–443.
  39. PialNN: A fast deep learning framework for cortical pial surface reconstruction, in: International Workshop on Machine Learning in Clinical Neuroimaging, Springer. pp. 73–81.
  40. Automated 3-D extraction of inner and outer surfaces of cerebral cortex from MRI. NeuroImage 12, 340–356.
  41. Interactive texture mapping, in: Proceedings of the 20th annual conference on Computer graphics and interactive techniques, pp. 27–34.
  42. Regional growth and atlasing of the developing human brain. Neuroimage 125, 456–478.
  43. Automatic whole brain MRI segmentation of the developing neonatal brain. IEEE transactions on medical imaging 33, 1818–1831.
  44. The developing human connectome project: A minimal processing pipeline for neonatal cortical surface reconstruction. Neuroimage 173, 88–112.
  45. A computational growth model for measuring dynamic cortical development in the first year of life. Cerebral cortex 22, 2272–2284.
  46. Brain volume estimation from post-mortem newborn and fetal MRI. NeuroImage: Clinical 6, 438–444.
  47. Deepsdf: Learning continuous signed distance functions for shape representation, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 165–174.
  48. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32.
  49. Automatic segmentation of mr images of the developing newborn brain. Medical image analysis 9, 457–466.
  50. Accelerating 3D deep learning with PyTorch3D. arXiv preprint arXiv:2007.08501 .
  51. Multimodal surface matching with higher-order smoothness constraints. Neuroimage 167, 453–465.
  52. Msm: a new flexible framework for multimodal surface matching. Neuroimage 100, 414–426.
  53. U-net: Convolutional networks for biomedical image segmentation, in: International Conference on Medical image computing and computer-assisted intervention, Springer. pp. 234–241.
  54. CorticalFlow++: Boosting cortical surface reconstruction accuracy, regularity, and interoperability, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 496–505.
  55. Unbiased construction of a temporally consistent morphological atlas of neonatal brain development. BioRxiv , 251512.
  56. A deformable model for the reconstruction of the neonatal cortex, in: IEEE 14th International Symposium on Biomedical Imaging, IEEE. pp. 800–803.
  57. Geometrically accurate topology-correction of cortical surfaces using nonseparating loops. IEEE transactions on medical imaging 26, 518–529.
  58. BrainSuite: an automated cortical surface identification tool. Medical image analysis 6, 129–142.
  59. Fast robust automated brain extraction. Human brain mapping 17, 143–155.
  60. A signal processing approach to fair surface design, in: Proceedings of the 22nd annual conference on Computer graphics and interactive techniques, pp. 351–358.
  61. N4ITK: improved N3 bias correction. IEEE transactions on medical imaging 29, 1310–1320.
  62. The WU-Minn human connectome project: an overview. Neuroimage 80, 62–79.
  63. Diffeomorphic demons: Efficient non-parametric image registration. NeuroImage 45, S61–S72.
  64. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nature methods 17, 261–272.
  65. ibeat v2. 0: a multisite-applicable, deep learning-based pipeline for infant cerebral cortical surface reconstruction. Nature protocols 18, 1488–1509.
  66. Pixel2Mesh: Generating 3D mesh models from single rgb images, in: Proceedings of the European conference on computer vision (ECCV), pp. 52–67.
  67. Voxel2Mesh: 3D mesh model generation from volumetric data, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part IV 23, Springer. pp. 299–308.
  68. S3reg: superfast spherical surface registration based on deep learning. IEEE transactions on medical imaging 40, 1964–1976.
  69. Spherical deformable u-net: Application to cortical surface parcellation and development prediction. IEEE transactions on medical imaging 40, 1217–1228.
  70. Fast spherical mapping of cortical surface meshes using deep unsupervised learning, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 163–173.
  71. Spherical U-Net on cortical surfaces: methods and applications, in: International Conference on Information Processing in Medical Imaging, Springer. pp. 855–866.
  72. Spherical U-Net for infant cortical surface parcellation, in: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), IEEE. pp. 1882–1886.
  73. Infant FreeSurfer: An automated segmentation and surface extraction pipeline for T1-weighted neuroimaging data of infants 0–2 years. Neuroimage 218, 116946.

Summary

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

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