Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 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

Neural Implicit Surface Reconstruction of Freehand 3D Ultrasound Volume with Geometric Constraints (2401.05915v4)

Published 11 Jan 2024 in eess.IV

Abstract: Three-dimensional (3D) freehand ultrasound (US) is a widely used imaging modality that allows non-invasive imaging of medical anatomy without radiation exposure. Surface reconstruction of US volume is vital to acquire the accurate anatomical structures needed for modeling, registration, and visualization. However, traditional methods cannot produce a high-quality surface due to image noise. Despite improvements in smoothness, continuity, and resolution from deep learning approaches, research on surface reconstruction in freehand 3D US is still limited. This study introduces FUNSR, a self-supervised neural implicit surface reconstruction method to learn signed distance functions (SDFs) from US volumes. In particular, FUNSR iteratively learns the SDFs by moving the 3D queries sampled around volumetric point clouds to approximate the surface, guided by two novel geometric constraints: sign consistency constraint and onsurface constraint with adversarial learning. Our approach has been thoroughly evaluated across four datasets to demonstrate its adaptability to various anatomical structures, including a hip phantom dataset, two vascular datasets and one publicly available prostate dataset. We also show that smooth and continuous representations greatly enhance the visual appearance of US data. Furthermore, we highlight the potential of our method to improve segmentation performance, and its robustness to noise distribution and motion perturbation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. M. Jiang and B. Chiu, “A dual-stream centerline-guided network for segmentation of the common and internal carotid arteries from 3D ultrasound images,” IEEE Transactions on Medical Imaging, pp. 1–1, 2023.
  2. X. Yang, H. Dou, R. Huang, W. Xue, Y. Huang, J. Qian, Y. Zhang, H. Luo, H. Guo, T. Wang, Y. Xiong, and D. Ni, “Agent With Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound,” IEEE Transactions on Medical Imaging, vol. 40, no. 7, pp. 1950–1961, Jul. 2021.
  3. R. W. Prager, U. Z. Ijaz, A. H. Gee, and G. M. Treece, “Three-dimensional ultrasound imaging,” Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, vol. 224, no. 2, pp. 193–223, Feb. 2010.
  4. M. Luo, X. Yang, H. Wang, H. Dou, X. Hu, Y. Huang, N. Ravikumar, S. Xu, Y. Zhang, Y. Xiong, W. Xue, A. F. Frangi, D. Ni, and L. Sun, “RecON: Online learning for sensorless freehand 3D ultrasound reconstruction,” Medical Image Analysis, vol. 87, p. 102810, Jul. 2023.
  5. R. Rohling, A. Gee, and L. Berman, “A comparison of freehand three-dimensional ultrasound reconstruction techniques,” Medical Image Analysis, vol. 3, no. 4, pp. 339–359, Dec. 1999.
  6. M. H. Mozaffari and W.-S. Lee, “Freehand 3-D Ultrasound Imaging: A Systematic Review,” Ultrasound in Medicine & Biology, vol. 43, no. 10, pp. 2099–2124, Oct. 2017.
  7. Q. Huang and Z. Zeng, “A Review on Real-Time 3D Ultrasound Imaging Technology,” BioMed Research International, vol. 2017, pp. 1–20, 2017.
  8. G. Chen, J. Qin, B. B. Amor, W. Zhou, H. Dai, T. Zhou, H. Huang, and L. Shao, “Automatic Detection of Tooth-Gingiva Trim Lines on Dental Surfaces,” IEEE Transactions on Medical Imaging, vol. 42, no. 11, pp. 3194–3204, Nov. 2023.
  9. H. Zhou and J. Jagadeesan, “Real-Time Dense Reconstruction of Tissue Surface From Stereo Optical Video,” IEEE Transactions on Medical Imaging, vol. 39, no. 2, pp. 400–412, Feb. 2020.
  10. R. Palomar, F. A. Cheikh, B. Edwin, A. Beghdadhi, and O. J. Elle, “Surface reconstruction for planning and navigation of liver resections,” Computerized Medical Imaging and Graphics, vol. 53, pp. 30–42, Oct. 2016.
  11. G. Treece, R. Prager, and A. Gee, “Regularised marching tetrahedra: Improved iso-surface extraction,” Computers & Graphics, vol. 23, no. 4, pp. 583–598, Aug. 1999.
  12. D. V. Nguyen, Q. N. Vo, L. H. Le, and E. H. M. Lou, “Validation of 3D surface reconstruction of vertebrae and spinal column using 3D ultrasound data – A pilot study,” Medical Engineering & Physics, vol. 37, no. 2, pp. 239–244, Feb. 2015.
  13. A. Farshian, M. Götz, G. Cavallaro, C. Debus, M. Nießner, J. A. Benediktsson, and A. Streit, “Deep-Learning-Based 3-D Surface Reconstruction—A Survey,” Proceedings of the IEEE, vol. 111, no. 11, pp. 1464–1501, Nov. 2023.
  14. A. Molaei, A. Aminimehr, A. Tavakoli, A. Kazerouni, B. Azad, R. Azad, and D. Merhof, “Implicit Neural Representation in Medical Imaging: A Comparative Survey,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 2381–2391.
  15. W. Y. Zhang, R. N. Rohling, and D. K. Pai, “Surface extraction with a three-dimensional freehand ultrasound system,” Ultrasound in Medicine & Biology, vol. 30, no. 11, pp. 1461–1473, Nov. 2004.
  16. Y. Zhang, R. Rohling, and D. Pai, “Direct surface extraction from 3D freehand ultrasound images,” in IEEE Visualization, 2002. VIS 2002., Oct. 2002, pp. 45–52.
  17. W. Kerr, P. Rowe, and S. G. Pierce, “Accurate 3D reconstruction of bony surfaces using ultrasonic synthetic aperture techniques for robotic knee arthroplasty,” Computerized Medical Imaging and Graphics, vol. 58, pp. 23–32, Jun. 2017.
  18. M. Nakao, F. Tong, M. Nakamura, and T. Matsuda, “Image-to-Graph Convolutional Network for Deformable Shape Reconstruction from a Single Projection Image,” in Medical Image Computing and Computer Assisted Intervention – MICCAI 2021, ser. Lecture Notes in Computer Science, M. de Bruijne, P. C. Cattin, S. Cotin, N. Padoy, S. Speidel, Y. Zheng, and C. Essert, Eds.   Cham: Springer International Publishing, 2021, pp. 259–268.
  19. U. Wickramasinghe, E. Remelli, G. Knott, and P. Fua, “Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data,” in Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, ser. Lecture Notes in Computer Science, A. L. Martel, P. Abolmaesumi, D. Stoyanov, D. Mateus, M. A. Zuluaga, S. K. Zhou, D. Racoceanu, and L. Joskowicz, Eds.   Cham: Springer International Publishing, 2020, pp. 299–308.
  20. Q. Ma, L. Li, E. C. Robinson, B. Kainz, D. Rueckert, and A. Alansary, “CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs,” IEEE Transactions on Medical Imaging, vol. 42, no. 2, pp. 430–443, Feb. 2023.
  21. F. Laumer, M. Amrani, L. Manduchi, A. Beuret, L. Rubi, A. Dubatovka, C. M. Matter, and J. M. Buhmann, “Weakly supervised inference of personalized heart meshes based on echocardiography videos,” Medical Image Analysis, vol. 83, p. 102653, 2023.
  22. J. Xu, D. Moyer, B. Gagoski, J. E. Iglesias, P. E. Grant, P. Golland, and E. Adalsteinsson, “NeSVoR: Implicit Neural Representation for Slice-to-Volume Reconstruction in MRI,” IEEE Transactions on Medical Imaging, vol. 42, no. 6, pp. 1707–1719, Jun. 2023.
  23. B. Song, L. Shen, and L. Xing, “PINER: Prior-Informed Implicit Neural Representation Learning for Test-Time Adaptation in Sparse-View CT Reconstruction,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 1928–1938.
  24. H. Li, H. Chen, W. Jing, Y. Li, and R. Zheng, “3D Ultrasound Spine Imaging with Application of Neural Radiance Field Method,” in 2021 IEEE International Ultrasonics Symposium (IUS), Sep. 2021, pp. 1–4.
  25. P.-H. Yeung, L. Hesse, M. Aliasi, M. Haak, W. Xie, A. I. Namburete et al., “Implicitvol: Sensorless 3d ultrasound reconstruction with deep implicit representation,” arXiv preprint arXiv:2109.12108, 2021.
  26. J. J. Park, P. Florence, J. Straub, R. Newcombe, and S. Lovegrove, “DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 165–174.
  27. M. Baorui, H. Zhizhong, L. Yu-Shen, and Z. Matthias, “Neural-pull: Learning signed distance functions from point clouds by learning to pull space onto surfaces,” in International Conference on Machine Learning (ICML), 2021.
  28. R. S. Cruz, L. Lebrat, P. Bourgeat, C. Fookes, J. Fripp, and O. Salvado, “DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction,” in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Jan. 2021, pp. 806–815.
  29. J. Sander, B. D. De Vos, S. Bruns, N. Planken, M. A. Viergever, T. Leiner, and I. Išgum, “Reconstruction and completion of high-resolution 3D cardiac shapes using anisotropic CMRI segmentations and continuous implicit neural representations,” Computers in Biology and Medicine, vol. 164, p. 107266, Sep. 2023.
  30. D. Wiesner, J. Suk, S. Dummer, T. Nečasová, V. Ulman, D. Svoboda, and J. M. Wolterink, “Generative modeling of living cells with SO(3)-equivariant implicit neural representations,” Medical Image Analysis, vol. 91, p. 102991, Jan. 2024.
  31. W. E. Lorensen and H. E. Cline, “Marching cubes: A high resolution 3D surface construction algorithm,” ACM SIGGRAPH Computer Graphics, vol. 21, no. 4, pp. 163–169, Aug. 1987.
  32. F. Bernard, L. Salamanca, J. Thunberg, A. Tack, D. Jentsch, H. Lamecker, S. Zachow, F. Hertel, J. Goncalves, and P. Gemmar, “Shape-aware surface reconstruction from sparse 3D point-clouds,” Medical Image Analysis, vol. 38, pp. 77–89, May 2017.
  33. H.-B. Chen, R. Zheng, L.-Y. Qian, F.-Y. Liu, S. Song, and H.-Y. Zeng, “Improvement of 3-D Ultrasound Spine Imaging Technique Using Fast Reconstruction Algorithm,” IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, vol. 68, no. 10, pp. 3104–3113, Oct. 2021.
  34. F. Zhao, W. Wang, S. Liao, and L. Shao, “Learning Anchored Unsigned Distance Functions With Gradient Direction Alignment for Single-View Garment Reconstruction,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 12 674–12 683.
  35. G. Chou, I. Chugunov, and F. Heide, “Gensdf: Two-stage learning of generalizable signed distance functions,” in Proc. of Neural Information Processing Systems (NeurIPS), 2022.
  36. X. Mao, Q. Li, H. Xie, R. Y. Lau, Z. Wang, and S. Paul Smolley, “Least squares generative adversarial networks,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017.
  37. H. Chen, R. Zheng, E. Lou, and L. H. Le, “Compact and Wireless Freehand 3D Ultrasound Real-time Spine Imaging System: A pilot study,” in 2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC), Jul. 2020, pp. 2105–2108.
  38. J. Li, Y. Huang, S. Song, H. Chen, J. Shi, D. Xu, H. Zhang, M. Chen, and R. Zheng, “Automatic Diagnosis of Carotid Atherosclerosis Using a Portable Freehand 3D Ultrasound Imaging System,” Jan. 2023.
  39. J. Alavi, H. Chen, K.-C. T. Nguyen, T.-G. La, L. Kumaralingam, K. Punithakumar, M. Alexiou, E. H. Lou, M. Noga, P. W. Major, and L. H. Le, “Three-dimensional Intraoral Imaging using a Portable 3D Freehand Ultrasound System: A Phantom Study,” in 2023 IEEE International Ultrasonics Symposium (IUS), Sep. 2023, pp. 1–4.
Citations (1)
View on Semantic Scholar

Summary

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

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