Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

A Novel Implicit Neural Representation for Volume Data (2403.08566v1)

Published 13 Mar 2024 in eess.IV and cs.CV

Abstract: The storage of medical images is one of the challenges in the medical imaging field. There are variable works that use implicit neural representation (INR) to compress volumetric medical images. However, there is room to improve the compression rate for volumetric medical images. Most of the INR techniques need a huge amount of GPU memory and a long training time for high-quality medical volume rendering. In this paper, we present a novel implicit neural representation to compress volume data using our proposed architecture, that is, the Lanczos downsampling scheme, SIREN deep network, and SRDenseNet high-resolution scheme. Our architecture can effectively reduce training time, and gain a high compression rate while retaining the final rendering quality. Moreover, it can save GPU memory in comparison with the existing works. The experiments show that the quality of reconstructed images and training speed using our architecture is higher than current works which use the SIREN only. Besides, the GPU memory cost is evidently decreased

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Implicit Neural Representations with Periodic Activation Functions. arXiv, 2020, arXiv:2006.09661. [CrossRef]
  2. Lossy compression of multidimensional medical images using sinusoidal activation networks: An evaluation study. arXiv, 2022, arXiv:2208.01602. [CrossRef]
  3. Implicit Neural Representations for Image Compression. arXiv, 2021, arXiv:2112.04267. [CrossRef]
  4. Learning Shape Priors for Single-View 3D Completion and Reconstruction. arXiv, 2018, arXiv:1809.05068. [CrossRef]
  5. Implicit Neural Representations for Medical Imaging Segmentation. In Proceedings of the Medical Image Computing and Computer Assisted Intervention—MICCAI 2022; Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S., Eds.; Springer Nature Switzerland: Cham, Switzerland, 2022; pp. 433–443.
  6. DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation. arXiv, 2019, arXiv:1901.05103. [CrossRef]
  7. Deep Implicit Volume Compression. arXiv, 2020, arXiv:2005.08877. [CrossRef]
  8. MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM). In Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, 10–15 January 2021 ; pp. 2874–2881. [CrossRef]
  9. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. arXiv, 2020, arXiv:2003.08934. [CrossRef]
  10. Occupancy Networks: Learning 3D Reconstruction in Function Space. arXiv, 2018, arXiv:1812.03828. [CrossRef]
  11. COIN: COmpression with Implicit Neural representations. arXiv 2021, arXiv:2103.03123. [CrossRef]
  12. Adversarial Generation of Continuous Images. arXiv 2020, arXiv:2011.12026. [CrossRef]
  13. NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstruction. arXiv 2021, arXiv:2108.10991. [CrossRef]
  14. Neural scene representation and rendering. Science 2018, 360, 1204–1210. [CrossRef] [PubMed]
  15. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 6–12 December 2020; NIPS’20; Curran Associates Inc.: Red Hook, NY, USA, 2022.
  16. A Transfer-Learning Approach for Accelerated MRI Using Deep Neural Networks. Magn. Reson. Med. 2020, 84, 663–685. [CrossRef]
  17. Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction. IEEE Trans. Med Imaging 2019, 38, 280–290. [CrossRef]
  18. Self-attention convolutional neural network for improved MR image reconstruction. Inf. Sci. 2019, 490, 317–328. [CrossRef]
  19. Deep iterative reconstruction estimation (DIRE): Approximate iterative reconstruction estimation for low dose CT imaging. Phys. Med. Biol. 2019, 64, 135007. [CrossRef] [PubMed]
  20. Deep learning based image reconstruction algorithm for limited-angle translational computed tomography. PLoS ONE 2020, 15, e0226963. [CrossRef]
  21. Deep Encoder-Decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-View Data. Bioengineering 2019, 6, 111. [CrossRef]
  22. Artifact removal using improved GoogLeNet for sparse-view CT reconstruction. Sci. Rep. 2018, 8, 6700. [CrossRef]
  23. Low-dose chest X-ray image super-resolution using generative adversarial nets with spectral normalization. Biomed. Signal Process. Control 2020, 55, 101600. [CrossRef]
  24. A deep learning method for high-quality ultra-fast CT image reconstruction from sparsely sampled projections. Nucl. Instruments Methods Phys. Res. Sect. Accel. Spectrometers Detect. Assoc. Equip. 2022, 1029, 166428. [CrossRef]
  25. Learned regularization for image reconstruction in sparse-view photoacoustic tomography. Biomed. Opt. Express 2022, 13, 5721–5737. [CrossRef] [PubMed]
  26. Direct Reconstruction of Linear Parametric Images From Dynamic PET Using Nonlocal Deep Image Prior. IEEE Trans. Med Imaging 2022, 41, 680–689. [CrossRef]
  27. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention; Springer: Berlin/Heidelberg, Germany, 2016; pp. 424–432.
  28. DeepPET: A deep encoder–decoder network for directly solving the PET image reconstruction inverse problem. Med Image Anal. 2019, 54, 253–262. [CrossRef] [PubMed]
  29. DUG-RECON: A Framework for Direct Image Reconstruction Using Convolutional Generative Networks. IEEE Trans. Radiat. Plasma Med Sci. 2021, 5, 44–53. [CrossRef]
  30. Dynamic PET Image Reconstruction Using Nonnegative Matrix Factorization Incorporated With Deep Image Prior. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea, 27 October–2 November 2019.
  31. DREAM-Net: Deep Residual Error Iterative Minimization Network for Sparse-View CT Reconstruction. IEEE J. Biomed. Health Inform. 2023, 27, 480–491. [CrossRef]
  32. Deep-Learning-Based Few-Angle Cardiac SPECT Reconstruction Using Transformer. IEEE Trans. Radiat. Plasma Med Sci. 2023, 7, 33–40. [CrossRef]
  33. DIOR: Deep Iterative Optimization-Based Residual-Learning for Limited-Angle CT Reconstruction. IEEE Trans. Med Imaging 2022, 41, 1778–1790. [CrossRef]
  34. Image Super-Resolution Using Deep Convolutional Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2016, 38, 295–307. [CrossRef]
  35. Accurate image super-resolution using very deep convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 1646–1654.
  36. A Review of Image Super-Resolution Approaches Based on Deep Learning and Applications in Remote Sensing. Remote Sens. 2022, 14. [CrossRef]
  37. Multi-image super-resolution for remote sensing using deep recurrent networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, 14–19 June 2020; pp. 206–207.
  38. E-DBPN: Enhanced deep back-projection networks for remote sensing scene image superresolution. IEEE Trans. Geosci. Remote Sens. 2020, 58, 5503–5515. [CrossRef]
  39. Unsupervised image super-resolution with an indirect supervised path. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, 14–19 June 2020; pp. 468–469.
  40. Meta-Transfer Learning for Zero-Shot Super-Resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13–19 June 2020.
  41. Super-resolution reconstruction of single remote sensing images based on residual channel attention. J. Appl. Remote Sens. 2021, 15, 016513. [CrossRef]
  42. RBPNET: An asymptotic Residual Back-Projection Network for super-resolution of very low-resolution face image. Neurocomputing 2020, 376, 119–127. [CrossRef]
  43. Learning Spatial Attention for Face Super-Resolution. IEEE Trans. Image Process. 2021, 30, 1219–1231. [CrossRef]
  44. Lightweight Feedback Convolution Neural Network for Remote Sensing Images Super-Resolution. IEEE Access 2021, 9, 15992–16003. [CrossRef]
  45. TE-SAGAN: An Improved Generative Adversarial Network for Remote Sensing Super-Resolution Images. Remote Sens. 2022, 14, 2425. [CrossRef]
  46. Fused Recurrent Network Via Channel Attention For Remote Sensing Satellite Image Super-Resolution. In Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK, 6–10 June 2020; pp. 1–6. [CrossRef]
  47. Progressive lossless compression of volumetric data using small memory load. Comput. Med. Imaging Graph. 2005, 29, 305–312. . [CrossRef]
  48. Volumetric medical image compression using 3D listless embedded block partitioning. SpringerPlus 2016, 5, 2100. [CrossRef]
  49. GPU-based lossless volume data compression. In Proceedings of the 2016 3DTV-Conference: The True Vision—Capture, Transmission and Display of 3D Video (3DTV-CON), Hamburg, Germany, 4–6 July 2016; pp. 1–4. [CrossRef]
  50. Rapid High Quality Compression of Volume Data for Visualization. Comput. Graph. Forum 2001, 20, 49–57. [CrossRef]
  51. Random-Accessible Volume Data Compression with Regression Function. In Proceedings of the 2015 14th International Conference on Computer-Aided Design and Computer Graphics (CAD/Graphics), Xi’an, China, 26–28 August 2015; pp. 137–142. [CrossRef]
  52. Lossless compression of curated erythrocyte images using deep autoencoders for malaria infection diagnosis. In Proceedings of the 2016 Picture Coding Symposium (PCS), Nuremberg, Germany, 4–7 December 2016; pp. 1–5. [CrossRef]
  53. Lossy Medical Image Compression using Residual Learning-based Dual Autoencoder Model. arXiv, 2021, arXiv:2108.10579. [CrossRef]
  54. Medical image interpolation based on 3D Lanczos filtering. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 2020, 8, 294–300. [CrossRef]
  55. Image Super-Resolution Using Dense Skip Connections. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22–29 October 2017; pp. 4809–4817. [CrossRef]
Citations (5)
View on Semantic Scholar

Summary

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

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