Advances in low-dose cone-beam computed tomography image reconstruction methods based on deep learning_Journal of Biomedical Engineering

Authors：

SHI Jiangyuan ,  SONG Ying , LI Guangjun , BAI Sen

Department of Radiotherapy Physics & Technology, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;

Corresponding author：

SONG Ying, Email: songying_Wch@163.com

Keywords：

Low-dose cone-beam computed tomography; Image reconstruction; Deep learning

DOI：

10.7507/1001-5515.202409021

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Cone-beam computed tomography (CBCT) is widely used in dentistry, surgery, radiotherapy and other medical fields. However, repeated CBCT scans expose patients to additional radiation doses, increasing the risk of secondary malignant tumors. Low-dose CBCT image reconstruction technology, which employs advanced algorithms to reduce radiation dose while enhancing image quality, has emerged as a focal point of recent research. This review systematically examined deep learning-based methods for low-dose CBCT reconstruction. It compared different network architectures in terms of noise reduction, artifact removal, detail preservation, and computational efficiency, covering three approaches: image-domain, projection-domain, and dual-domain techniques. The review also explored how emerging technologies like multimodal fusion and self-supervised learning could enhance these methods. By summarizing the strengths and weaknesses of current approaches, this work provides insights to optimize low-dose CBCT algorithms and support their clinical adoption.

1.	Kim S H, Kim K B, Choo H. New frontier in advanced dentistry: CBCT, intraoral scanner, sensors, and artificial intelligence in dentistry. Sensors (Basel), 2022, 22(8): 2942.
2.	Kaasalainen T, Ekholm M, Siiskonen T, et al. Dental cone beam CT: An updated review. Phys Med, 2021, 88: 193-217.
3.	Privalov M, Bullert B, Gierse J, et al. Effect of changing the acquisition trajectory of the 3D C-arm (CBCT) on image quality in spine surgery: experimental study using an artificial bone model. J Orthop Surg Res, 2023, 18(1): 924.
4.	Han M, Kim H J, Choi J W, et al. Diagnostic usefulness of cone-beam computed tomography versus multi-detector computed tomography for sinonasal structure evaluation. Laryngoscope Investig Otolaryngol, 2022, 7(3): 662-670.
5.	Vorbau R, Hulthen M, Omar A. Task-based image quality assessment of an intraoperative CBCT for spine surgery compared with conventional CT. Phys Med, 2024, 124: 103426.
6.	Dartus J, Jacques T, Martinot P, et al. The advantages of cone-beam computerised tomography (CT) in pain management following total knee arthroplasty, in comparison with conventional multi-detector CT. Orthop Traumatol Surg Res, 2021, 107(3): 102874.
7.	Doan M K, Long J R, Verhey E, et al. Cone-beam CT of the extremities in clinical practice. Radiographics, 2024, 44(3): e230143.
8.	Grassi R, Guerra E, Berritto D. Bone fractures difficult to recognize in emergency: May be cone beam computed tomography (CBCT) the solution?. Radiol Med, 2023, 128(1): 1-5.
9.	Jacques T, Morel V, Dartus J, et al. Impact of introducing extremity cone-beam CT in an emergency radiology department: A population-based study. Orthopaedics & traumatology, surgery & research, 2021, 107(2): 102834.
10.	Xu D, Xie F, Zhang J, et al. Chinese expert consensus on cone-beam CT-guided diagnosis, localization and treatment for pulmonary nodules. Thorac Cancer, 2024, 15(7): 582-597.
11.	Pogatchnik B P, Swenson K E, Duong D K, et al. Immediate and follow-up imaging findings after cone-beam CT-guided transbronchial lung cryobiopsy. Radiol Cardiothorac Imaging, 2023, 5(2): e220149.
12.	Washio H, Ohira S, Funama Y, et al. Dose reduction and low-contrast detectability using iterative CBCT reconstruction algorithm for radiotherapy. Technol Cancer Res Treat, 2022, 21: 2091158096.
13.	Kench P L, Rogers L, Esteves A, et al. Imaging prior to radiotherapy impacts in-vitro survival. Phys Imaging Radiat Oncol, 2020, 16: 138-143.
14.	Galdi A, Farkas G, Gazdag-Hegyesi S, et al. Combined biological effects of CBCT and therapeutic X-ray dose on chromosomal aberrations of lymphocytes. Radiat Oncol, 2024, 19(1): 109.
15.	Nahir C B, Citir M, Colak S, et al. Assessment of cone beam computed tomography use in pediatric and adolescent patients: a cross-sectional study. BMC Oral Health, 2024, 24(1): 1068.
16.	Ding G X, Alaei P, Curran B, et al. Image guidance doses delivered during radiotherapy: Quantification, management, and reduction: Report of the AAPM Therapy Physics Committee Task Group 180. Med Phys, 2018, 45(5): e84-e99.
17.	Jiang Z, Zhang Z, Chang Y, et al. Prior image-guided cone-beam computed tomography augmentation from under-sampled projections using a convolutional neural network. Quant Imaging Med Surg, 2021, 11(12): 4767-4780.
18.	Olch A J, Alaei P. How low can you go? A CBCT dose reduction study. J Appl Clin Med Phys, 2021, 22(2): 85-89.
19.	Park J C, Song B, Liang X, et al. A high-resolution cone beam computed tomography (HRCBCT) reconstruction framework for CBCT-guided online adaptive therapy. Med Phys, 2023, 50(10): 6490-6501.
20.	Lee H, Sung J, Choi Y, et al. Mutual information-based non-local total variation denoiser for low-dose cone-beam computed tomography. Front Oncol, 2021, 11: 751057.
21.	Teyfouri N, Rabbani H, Kafieh R, et al. An exact and fast CBCT reconstruction via Pseudo-Polar Fourier transform based discrete Grangeat’s formula. IEEE Trans Image Process, 2020, 29: 5832-5847.
22.	Qi H, Long C, Li H, et al. Direct filter learning from iterative reconstructed images for high-quality analytical CBCT reconstruction using FDK-based neural network. IEEE Access, 2024, 12: 121495-121506.
23.	Kim H, Choi J, Lee Y. Assessment of Feldkamp-Davis-Kress reconstruction parameters in overall image quality in cone beam computed tomography. Applied sciences, 2024, 14(16): 7058.
24.	Azad R, Kazerouni A, Heidari M, et al. Advances in medical image analysis with vision Transformers: A comprehensive review. Med Image Anal, 2024, 91: 103000.
25.	Chen X, Wang X, Zhang K, et al. Recent advances and clinical applications of deep learning in medical image analysis. Med Image Anal, 2022, 79: 102444.
26.	Yaqub M, Jinchao F, Arshid K, et al. Deep learning-based image reconstruction for different medical imaging modalities. Comput Math Methods Med, 2022, 2022: 8750648.
27.	Yu Z, Wen X, Yang Y. Reconstruction of sparse-view X-ray computed tomography based on adaptive total variation minimization. Micromachines (Basel), 2023, 14(12): 2245.
28.	Teyfouri N, Rabbani H, Jabbari I. Low-dose cone-beam computed tomography reconstruction through a fast three-dimensional compressed sensing method based on the three-dimensional Pseudo-polar Fourier transform. J Med Signals Sens, 2022, 12(1): 8-24.
29.	Jiang Z, Chen Y, Zhang Y, et al. Augmentation of CBCT reconstructed from under-sampled projections using deep learning. IEEE Trans Med Imaging, 2019, 38(11): 2705-2715.
30.	Hyun C M, Bayaraa T, Yun H S, et al. Deep learning method for reducing metal artifacts in dental cone-beam CT using supplementary information from intra-oral scan. Phys Med Biol, 2022, 67(17): 175007.
31.	Gao L, Xie K, Wu X, et al. Generating synthetic CT from low-dose cone-beam CT by using generative adversarial networks for adaptive radiotherapy. Radiat Oncol, 2021, 16(1): 202.
32.	Chan Y, Li M, Parodi K, et al. Feasibility of CycleGAN enhanced low dose CBCT imaging for prostate radiotherapy dose calculation. Phys Med Biol, 2023, 68(10): 105014.
33.	Wang Y, Chao L, Shan W, et al. Improving the quality of sparse-view cone-beam computed tomography via reconstruction-friendly interpolation network// Sato I, Gall J, Wang L, et al. Computer Vision – ACCV 2022. Switzerland: Springer, 2023: 86-100.
34.	Choi K, Kim S H, Kim S. Self-supervised denoising of projection data for low-dose cone-beam CT. Med Phys, 2023, 50(10): 6319-6333.
35.	Choi K. A comparative study between image- and projection-domain self-supervised learning for ultra low-dose CBCT. Annu Int Conf IEEE Eng Med Biol Soc, 2022, 2022: 2076-2079.
36.	Zhao X, Du Y, Yue H, et al. Deep learning-based projection synthesis for low-dose cone-beam computed tomography imaging in image-guided radiotherapy. Quant Imaging Med Surg, 2024, 14(1): 231-250.
37.	Hansen D C, Landry G, Kamp F, et al. ScatterNet: A convolutional neural network for cone-beam CT intensity correction. Med Phys, 2018, 45(11): 4916-4926.
38.	Wu W, Hu D, Niu C, et al. DRONE: Dual-domain residual-based optimization network for sparse-view CT reconstruction. IEEE T Med Imaging, 2021, 40(11): 3002-3014.
39.	Hu D, Liu J, Lv T, et al. Hybrid-domain neural network processing for sparse-view CT reconstruction. IEEE T Radiat Plasma, 2021, 5(1): 88-98.
40.	Chao L, Wang Z, Zhang H, et al. Sparse-view cone beam CT reconstruction using dual CNNs in projection domain and image domain. Neurocomputing (Amsterdam), 2022, 493: 536-547.
41.	Chao L, Zhang P, Wang Y, et al. Dual-domain attention-guided convolutional neural network for low-dose cone-beam computed tomography reconstruction. Knowledge-based systems, 2022, 251: 109295.
42.	Ketcha M D, Marrama M, Souza A, et al. Sinogram + image domain neural network approach for metal artifact reduction in low-dose cone-beam computed tomography. J Med Imaging (Bellingham), 2021, 8(5): 52103.
43.	Chao L, Wang Y, Zhang T, et al. Joint denoising and interpolating network for low-dose cone-beam CT reconstruction under hybrid dose-reduction strategy. Comput Biol Med, 2024, 168: 107830.
44.	Lu K, Ren L, Yin F F. A geometry-guided deep learning technique for CBCT reconstruction. Phys Med Biol, 2021, 66(15): 15LT01.
45.	Liao S, Mo Z, Zeng M, et al. Fast and low-dose medical imaging generation empowered by hybrid deep-learning and iterative reconstruction. Cell Rep Med, 2023, 4(7): 101119.
46.	Chen M S, Zhang Z, Lu K, et al. Improving liver SBRT target localization with hybrid MRI/CBCT technology. Int J Radiat Oncol, 2024, 120(2): e109.
47.	Lei Y, Wang T, Tian S, et al. Male pelvic multi-organ segmentation aided by CBCT-based synthetic MRI. Phys Med Biol, 2020, 65(3): 35013.
48.	Huang S, Pareek A, Jensen M, et al. Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ Digit Med, 2023, 6(1): 74.
49.	Lazaros K, Koumadorakis D E, Vrahatis A G, et al. Federated Learning: Navigating the landscape of collaborative intelligence. Electronics (Basel), 2024, 13(23): 4744.

1. Kim S H, Kim K B, Choo H. New frontier in advanced dentistry: CBCT, intraoral scanner, sensors, and artificial intelligence in dentistry. Sensors (Basel), 2022, 22(8): 2942.
2. Kaasalainen T, Ekholm M, Siiskonen T, et al. Dental cone beam CT: An updated review. Phys Med, 2021, 88: 193-217.
3. Privalov M, Bullert B, Gierse J, et al. Effect of changing the acquisition trajectory of the 3D C-arm (CBCT) on image quality in spine surgery: experimental study using an artificial bone model. J Orthop Surg Res, 2023, 18(1): 924.
4. Han M, Kim H J, Choi J W, et al. Diagnostic usefulness of cone-beam computed tomography versus multi-detector computed tomography for sinonasal structure evaluation. Laryngoscope Investig Otolaryngol, 2022, 7(3): 662-670.
5. Vorbau R, Hulthen M, Omar A. Task-based image quality assessment of an intraoperative CBCT for spine surgery compared with conventional CT. Phys Med, 2024, 124: 103426.
6. Dartus J, Jacques T, Martinot P, et al. The advantages of cone-beam computerised tomography (CT) in pain management following total knee arthroplasty, in comparison with conventional multi-detector CT. Orthop Traumatol Surg Res, 2021, 107(3): 102874.
7. Doan M K, Long J R, Verhey E, et al. Cone-beam CT of the extremities in clinical practice. Radiographics, 2024, 44(3): e230143.
8. Grassi R, Guerra E, Berritto D. Bone fractures difficult to recognize in emergency: May be cone beam computed tomography (CBCT) the solution?. Radiol Med, 2023, 128(1): 1-5.
9. Jacques T, Morel V, Dartus J, et al. Impact of introducing extremity cone-beam CT in an emergency radiology department: A population-based study. Orthopaedics & traumatology, surgery & research, 2021, 107(2): 102834.
10. Xu D, Xie F, Zhang J, et al. Chinese expert consensus on cone-beam CT-guided diagnosis, localization and treatment for pulmonary nodules. Thorac Cancer, 2024, 15(7): 582-597.
11. Pogatchnik B P, Swenson K E, Duong D K, et al. Immediate and follow-up imaging findings after cone-beam CT-guided transbronchial lung cryobiopsy. Radiol Cardiothorac Imaging, 2023, 5(2): e220149.
12. Washio H, Ohira S, Funama Y, et al. Dose reduction and low-contrast detectability using iterative CBCT reconstruction algorithm for radiotherapy. Technol Cancer Res Treat, 2022, 21: 2091158096.
13. Kench P L, Rogers L, Esteves A, et al. Imaging prior to radiotherapy impacts in-vitro survival. Phys Imaging Radiat Oncol, 2020, 16: 138-143.
14. Galdi A, Farkas G, Gazdag-Hegyesi S, et al. Combined biological effects of CBCT and therapeutic X-ray dose on chromosomal aberrations of lymphocytes. Radiat Oncol, 2024, 19(1): 109.
15. Nahir C B, Citir M, Colak S, et al. Assessment of cone beam computed tomography use in pediatric and adolescent patients: a cross-sectional study. BMC Oral Health, 2024, 24(1): 1068.
16. Ding G X, Alaei P, Curran B, et al. Image guidance doses delivered during radiotherapy: Quantification, management, and reduction: Report of the AAPM Therapy Physics Committee Task Group 180. Med Phys, 2018, 45(5): e84-e99.
17. Jiang Z, Zhang Z, Chang Y, et al. Prior image-guided cone-beam computed tomography augmentation from under-sampled projections using a convolutional neural network. Quant Imaging Med Surg, 2021, 11(12): 4767-4780.
18. Olch A J, Alaei P. How low can you go? A CBCT dose reduction study. J Appl Clin Med Phys, 2021, 22(2): 85-89.
19. Park J C, Song B, Liang X, et al. A high-resolution cone beam computed tomography (HRCBCT) reconstruction framework for CBCT-guided online adaptive therapy. Med Phys, 2023, 50(10): 6490-6501.
20. Lee H, Sung J, Choi Y, et al. Mutual information-based non-local total variation denoiser for low-dose cone-beam computed tomography. Front Oncol, 2021, 11: 751057.
21. Teyfouri N, Rabbani H, Kafieh R, et al. An exact and fast CBCT reconstruction via Pseudo-Polar Fourier transform based discrete Grangeat’s formula. IEEE Trans Image Process, 2020, 29: 5832-5847.
22. Qi H, Long C, Li H, et al. Direct filter learning from iterative reconstructed images for high-quality analytical CBCT reconstruction using FDK-based neural network. IEEE Access, 2024, 12: 121495-121506.
23. Kim H, Choi J, Lee Y. Assessment of Feldkamp-Davis-Kress reconstruction parameters in overall image quality in cone beam computed tomography. Applied sciences, 2024, 14(16): 7058.
24. Azad R, Kazerouni A, Heidari M, et al. Advances in medical image analysis with vision Transformers: A comprehensive review. Med Image Anal, 2024, 91: 103000.
25. Chen X, Wang X, Zhang K, et al. Recent advances and clinical applications of deep learning in medical image analysis. Med Image Anal, 2022, 79: 102444.
26. Yaqub M, Jinchao F, Arshid K, et al. Deep learning-based image reconstruction for different medical imaging modalities. Comput Math Methods Med, 2022, 2022: 8750648.
27. Yu Z, Wen X, Yang Y. Reconstruction of sparse-view X-ray computed tomography based on adaptive total variation minimization. Micromachines (Basel), 2023, 14(12): 2245.
28. Teyfouri N, Rabbani H, Jabbari I. Low-dose cone-beam computed tomography reconstruction through a fast three-dimensional compressed sensing method based on the three-dimensional Pseudo-polar Fourier transform. J Med Signals Sens, 2022, 12(1): 8-24.
29. Jiang Z, Chen Y, Zhang Y, et al. Augmentation of CBCT reconstructed from under-sampled projections using deep learning. IEEE Trans Med Imaging, 2019, 38(11): 2705-2715.
30. Hyun C M, Bayaraa T, Yun H S, et al. Deep learning method for reducing metal artifacts in dental cone-beam CT using supplementary information from intra-oral scan. Phys Med Biol, 2022, 67(17): 175007.
31. Gao L, Xie K, Wu X, et al. Generating synthetic CT from low-dose cone-beam CT by using generative adversarial networks for adaptive radiotherapy. Radiat Oncol, 2021, 16(1): 202.
32. Chan Y, Li M, Parodi K, et al. Feasibility of CycleGAN enhanced low dose CBCT imaging for prostate radiotherapy dose calculation. Phys Med Biol, 2023, 68(10): 105014.
33. Wang Y, Chao L, Shan W, et al. Improving the quality of sparse-view cone-beam computed tomography via reconstruction-friendly interpolation network// Sato I, Gall J, Wang L, et al. Computer Vision – ACCV 2022. Switzerland: Springer, 2023: 86-100.
34. Choi K, Kim S H, Kim S. Self-supervised denoising of projection data for low-dose cone-beam CT. Med Phys, 2023, 50(10): 6319-6333.
35. Choi K. A comparative study between image- and projection-domain self-supervised learning for ultra low-dose CBCT. Annu Int Conf IEEE Eng Med Biol Soc, 2022, 2022: 2076-2079.
36. Zhao X, Du Y, Yue H, et al. Deep learning-based projection synthesis for low-dose cone-beam computed tomography imaging in image-guided radiotherapy. Quant Imaging Med Surg, 2024, 14(1): 231-250.
37. Hansen D C, Landry G, Kamp F, et al. ScatterNet: A convolutional neural network for cone-beam CT intensity correction. Med Phys, 2018, 45(11): 4916-4926.
38. Wu W, Hu D, Niu C, et al. DRONE: Dual-domain residual-based optimization network for sparse-view CT reconstruction. IEEE T Med Imaging, 2021, 40(11): 3002-3014.
39. Hu D, Liu J, Lv T, et al. Hybrid-domain neural network processing for sparse-view CT reconstruction. IEEE T Radiat Plasma, 2021, 5(1): 88-98.
40. Chao L, Wang Z, Zhang H, et al. Sparse-view cone beam CT reconstruction using dual CNNs in projection domain and image domain. Neurocomputing (Amsterdam), 2022, 493: 536-547.
41. Chao L, Zhang P, Wang Y, et al. Dual-domain attention-guided convolutional neural network for low-dose cone-beam computed tomography reconstruction. Knowledge-based systems, 2022, 251: 109295.
42. Ketcha M D, Marrama M, Souza A, et al. Sinogram + image domain neural network approach for metal artifact reduction in low-dose cone-beam computed tomography. J Med Imaging (Bellingham), 2021, 8(5): 52103.
43. Chao L, Wang Y, Zhang T, et al. Joint denoising and interpolating network for low-dose cone-beam CT reconstruction under hybrid dose-reduction strategy. Comput Biol Med, 2024, 168: 107830.
44. Lu K, Ren L, Yin F F. A geometry-guided deep learning technique for CBCT reconstruction. Phys Med Biol, 2021, 66(15): 15LT01.
45. Liao S, Mo Z, Zeng M, et al. Fast and low-dose medical imaging generation empowered by hybrid deep-learning and iterative reconstruction. Cell Rep Med, 2023, 4(7): 101119.
46. Chen M S, Zhang Z, Lu K, et al. Improving liver SBRT target localization with hybrid MRI/CBCT technology. Int J Radiat Oncol, 2024, 120(2): e109.
47. Lei Y, Wang T, Tian S, et al. Male pelvic multi-organ segmentation aided by CBCT-based synthetic MRI. Phys Med Biol, 2020, 65(3): 35013.
48. Huang S, Pareek A, Jensen M, et al. Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ Digit Med, 2023, 6(1): 74.
49. Lazaros K, Koumadorakis D E, Vrahatis A G, et al. Federated Learning: Navigating the landscape of collaborative intelligence. Electronics (Basel), 2024, 13(23): 4744.

Journal of Biomedical Engineering

Latest ArticlesAdvances in low-dose cone-beam computed tomography image reconstruction methods based on deep learning

Abstract Full text Figures/Tables Video References Cited by

Format

Content