Jump to content

Deep Tomographic Reconstruction

Add links
From Wikipedia, the free encyclopedia

Deep Tomographic Reconstruction is an area where deep learning methods are used for tomographic reconstruction of medical and industrial images. It is a new frontier of the imaging field by utilizing artificial intelligence and machine learning, especially deep artificial neural networks or deep learning, to overcome challenges such as measurement noise, data sparsity, image artifacts, and computational inefficiency. This approach has been applied across various imaging modalities, including CT, MRI, PET, SPECT, ultrasound, and optical imaging. Rapid progress in this field marks a significant shift from traditional reconstruction methods to data-driven approaches since 2016.[1][2]

Historical background

[edit]

Traditional tomographic reconstruction relies on analytic methods such as filtered back-projection, or iterative methods which incrementally compute inverse transformations from measurement data (e.g., Radon or Fourier transform data).[3] However, these approaches are unsatisfactory in challenging scenarios, such as low-dose CT, fast MRI, metal artifacts, patient motion, and so on. In 2016, deep tomographic reconstruction emerged as a new paradigm.[4][5][6]

Advances across imaging modalities

[edit]

Computed Tomography (CT)

[edit]

In CT, deep learning models have been particularly effective in reducing radiation exposure while maintaining image quality.[7][8][9] Deep networks can also reconstruct decent images from sparsely sampled data without sacrificing diagnostic performance.[10] Deep learning-based generative AI models can reduce CT metal artifacts.[11][12]

Magnetic Resonance Imaging (MRI)

[edit]

MRI reconstruction has benefited from deep learning by speeding up acquisition speed, which is also referred to as fast MRI.[13][14] Also, MRI motion artifacts are reduced via deep learning.[15] Deep learning has enabled significant improvements in low-field MRI by enhancing image quality despite lower signal-to-noise ratio (SNR), making these systems clinically viable.[16]

Positron Emission Tomography (PET) and Single Photon Emission CT (SPECT)

[edit]

For PET imaging, deep learning models provide substantial improvements in low-dose imaging[17] and motion artifact correction.[18] Also, deep learning helps SPECT for generation of attenuation background.[19] A notable technique for PET denoising involves integrating MR data through multimodal networks, which leverage anatomical information from MRI to enhance PET image quality.[20]

Ultrasound Imaging

[edit]

Deep learning enhances ultrasound imaging by reducing speckle noise and motion blur.[21] For ultrasound beamforming, deep neural networks, allows superior image quality with limited data at high speed.[22] There are deep learning-based iPad ultrasound probes on the market. Such a device combines ultrasound imaging with AI-powered features for point-of-care applications.

Optical Imaging and Microscopy

[edit]

Diffuse optical tomography,[23] optical coherent tomography[24] and microscopy[25] are improved by deep neural networks beyond traditional methods. Furthermore, deep learning has also enhanced photoacoustic imaging,[26] addressing challenges like high noise, low contrast, and limited resolution.

References

[edit]
  1. ^ Wang, Ge (2016). "A Perspective on Deep Imaging". IEEE Access. 4: 8914–8924. arXiv:1609.04375. Bibcode:2016IEEEA...4.8914W. doi:10.1109/ACCESS.2016.2624938.
  2. ^ Wang, Ge; Zhang, Yi; Ye, Xiaojing; Mou, Xuanqin (1 December 2019). Machine Learning for Tomographic Imaging. IOP Publishing. ISBN 978-0-7503-2216-4.
  3. ^ P. Suetens, Fundamentals of Medical Imaging, 3rd edition. Cambridge: Cambridge University Press, 2017
  4. ^ Wang, Ge; Ye, Jong Chu; Mueller, Klaus; Fessler, Jeffrey A. (June 2018). "Image Reconstruction is a New Frontier of Machine Learning". IEEE Transactions on Medical Imaging. 37 (6): 1289–1296. doi:10.1109/TMI.2018.2833635. PMID 29870359.
  5. ^ Wang, Ge; Jacob, Mathews; Mou, Xuanqin; Shi, Yongyi; Eldar, Yonina C. (November 2021). "Deep Tomographic Image Reconstruction: Yesterday, Today, and Tomorrow—Editorial for the 2nd Special Issue "Machine Learning for Image Reconstruction"". IEEE Transactions on Medical Imaging. 40 (11): 2956–2964. doi:10.1109/TMI.2021.3115547.
  6. ^ Wang, Ge; Ye, Jong Chul; De Man, Bruno (10 December 2020). "Deep learning for tomographic image reconstruction". Nature Machine Intelligence. 2 (12): 737–748. doi:10.1038/s42256-020-00273-z.
  7. ^ Chen, Hu; Zhang, Yi; Kalra, Mannudeep K.; Lin, Feng; Chen, Yang; Liao, Peixi; Zhou, Jiliu; Wang, Ge (December 2017). "Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network". IEEE Transactions on Medical Imaging. 36 (12): 2524–2535. arXiv:1702.00288. doi:10.1109/TMI.2017.2715284. PMC 5727581. PMID 28622671.
  8. ^ Kang, Eunhee; Min, Junhong; Ye, Jong Chul (October 2017). "A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction". Medical Physics. 44 (10): e360 – e375. arXiv:1610.09736. Bibcode:2017MedPh..44E.360K. doi:10.1002/mp.12344. PMID 29027238.
  9. ^ Shan, Hongming; Padole, Atul; Homayounieh, Fatemeh; Kruger, Uwe; Khera, Ruhani Doda; Nitiwarangkul, Chayanin; Kalra, Mannudeep K.; Wang, Ge (10 June 2019). "Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction". Nature Machine Intelligence. 1 (6): 269–276. arXiv:1811.03691. doi:10.1038/s42256-019-0057-9. PMC 7687920. PMID 33244514.
  10. ^ Chen, Hu; Zhang, Yi; Chen, Yunjin; Zhang, Junfeng; Zhang, Weihua; Sun, Huaiqiang; Lv, Yang; Liao, Peixi; Zhou, Jiliu; Wang, Ge (June 2018). "LEARN: Learned Experts' Assessment-Based Reconstruction Network for Sparse-Data CT". IEEE Transactions on Medical Imaging. 37 (6): 1333–1347. arXiv:1707.09636. doi:10.1109/TMI.2018.2805692. PMC 6019143. PMID 29870363.
  11. ^ Zhang, Yanbo; Yu, Hengyong (June 2018). "Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography". IEEE Transactions on Medical Imaging. 37 (6): 1370–1381. arXiv:1709.01581. doi:10.1109/TMI.2018.2823083. PMC 5998663. PMID 29870366.
  12. ^ Karageorgos, Grigorios M.; Zhang, Jiayong; Peters, Nils; Xia, Wenjun; Niu, Chuang; Paganetti, Harald; Wang, Ge; De Man, Bruno (October 2024). "A Denoising Diffusion Probabilistic Model for Metal Artifact Reduction in CT". IEEE Transactions on Medical Imaging. 43 (10): 3521–3532. doi:10.1109/TMI.2024.3416398. PMC 11657996. PMID 38963746.
  13. ^ Zhu, Bo; Liu, Jeremiah Z.; Cauley, Stephen F.; Rosen, Bruce R.; Rosen, Matthew S. (March 2018). "Image reconstruction by domain-transform manifold learning". Nature. 555 (7697): 487–492. arXiv:1704.08841. Bibcode:2018Natur.555..487Z. doi:10.1038/nature25988. PMID 29565357.
  14. ^ Yang, Guang; Yu, Simiao; Dong, Hao; Slabaugh, Greg; Dragotti, Pier Luigi; Ye, Xujiong; Liu, Fangde; Arridge, Simon; Keegan, Jennifer; Guo, Yike; Firmin, David (June 2018). "DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction". IEEE Transactions on Medical Imaging. 37 (6): 1310–1321. doi:10.1109/TMI.2017.2785879. hdl:10044/1/55724. PMID 29870361.
  15. ^ Hossbach, Julian; Splitthoff, Daniel Nicolas; Cauley, Stephen; Clifford, Bryan; Polak, Daniel; Lo, Wei-Ching; Meyer, Heiko; Maier, Andreas (April 2023). "Deep learning-based motion quantification from k-space for fast model-based magnetic resonance imaging motion correction". Medical Physics. 50 (4): 2148–2161. Bibcode:2023MedPh..50.2148H. doi:10.1002/mp.16119. PMID 36433748.
  16. ^ Ayde, Reina; Senft, Tobias; Salameh, Najat; Sarracanie, Mathieu (6 July 2022). "Deep learning for fast low-field MRI acquisitions". Scientific Reports. 12 (1): 11394. Bibcode:2022NatSR..1211394A. doi:10.1038/s41598-022-14039-7. PMC 9259619. PMID 35794175.
  17. ^ Gong, Kuang; Guan, Jiahui; Liu, Chih-Chieh; Qi, Jinyi (March 2019). "PET Image Denoising Using a Deep Neural Network Through Fine Tuning". IEEE Transactions on Radiation and Plasma Medical Sciences. 3 (2): 153–161. doi:10.1109/TRPMS.2018.2877644. PMC 7402614. PMID 32754674.
  18. ^ Guo, Xueqi; Shi, Luyao; Chen, Xiongchao; Liu, Qiong; Zhou, Bo; Xie, Huidong; Liu, Yi-Hwa; Palyo, Richard; Miller, Edward J.; Sinusas, Albert J.; Staib, Lawrence; Spottiswoode, Bruce; Liu, Chi; Dvornek, Nicha C. (August 2024). "TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction". Medical Image Analysis. 96: 103190. arXiv:2402.09567. doi:10.1016/j.media.2024.103190. PMC 11180595. PMID 38820677.
  19. ^ Shi, Luyao; Onofrey, John A.; Liu, Hui; Liu, Yi-Hwa; Liu, Chi (September 2020). "Deep learning-based attenuation map generation for myocardial perfusion SPECT". European Journal of Nuclear Medicine and Molecular Imaging. 47 (10): 2383–2395. doi:10.1007/s00259-020-04746-6. PMID 32219492.
  20. ^ Onishi, Yuya; Hashimoto, Fumio; Ote, Kibo; Ohba, Hiroyuki; Ota, Ryosuke; Yoshikawa, Etsuji; Ouchi, Yasuomi (December 2021). "Anatomical-guided attention enhances unsupervised PET image denoising performance". Medical Image Analysis. 74: 102226. arXiv:2109.00802. doi:10.1016/j.media.2021.102226. PMID 34563861.
  21. ^ van Sloun, Ruud J. G.; Cohen, Regev; Eldar, Yonina C. (January 2020). "Deep Learning in Ultrasound Imaging". Proceedings of the IEEE. 108 (1): 11–29. arXiv:1907.02994. doi:10.1109/JPROC.2019.2932116.
  22. ^ Bell, Muyinatu A. Lediju; Huang, Jiaqi; Hyun, Dongwoon; Eldar, Yonina C.; van Sloun, Ruud; Mischi, Massimo (7 September 2020). "Challenge on Ultrasound Beamforming with Deep Learning (CUBDL)". 2020 IEEE International Ultrasonics Symposium (IUS). pp. 1–5. doi:10.1109/IUS46767.2020.9251434. ISBN 978-1-7281-5448-0.
  23. ^ Yoo, Jaejun; Sabir, Sohail; Heo, Duchang; Kim, Kee Hyun; Wahab, Abdul; Choi, Yoonseok; Lee, Seul-I; Chae, Eun Young; Kim, Hak Hee; Bae, Young Min; Choi, Young-Wook; Cho, Seungryong; Ye, Jong Chul (April 2020). "Deep Learning Diffuse Optical Tomography". IEEE Transactions on Medical Imaging. 39 (4): 877–887. arXiv:1712.00912. doi:10.1109/TMI.2019.2936522. PMID 31442973.
  24. ^ Ran, Anran; Cheung, Carol Y. (May 2021). "Deep Learning-Based Optical Coherence Tomography and Optical Coherence Tomography Angiography Image Analysis: An Updated Summary". Asia-Pacific Journal of Ophthalmology. 10 (3): 253–260. doi:10.1097/APO.0000000000000405. PMID 34383717.
  25. ^ Qiao, Chang; Li, Di; Liu, Yong; Zhang, Siwei; Liu, Kan; Liu, Chong; Guo, Yuting; Jiang, Tao; Fang, Chuyu; Li, Nan; Zeng, Yunmin; He, Kangmin; Zhu, Xueliang; Lippincott-Schwartz, Jennifer; Dai, Qionghai; Li, Dong (March 2023). "Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes". Nature Biotechnology. 41 (3): 367–377. doi:10.1038/s41587-022-01471-3. PMID 36203012.
  26. ^ Deng, Handi; Qiao, Hui; Dai, Qionghai; Ma, Cheng (9 April 2021). "Deep learning in photoacoustic imaging: a review". Journal of Biomedical Optics. 26 (4): 040901. Bibcode:2021JBO....26d0901D. doi:10.1117/1.JBO.26.4.040901. PMC 8033250. PMID 33837678.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Deep_Tomographic_Reconstruction&oldid=1277741241"