Intraoperative cone beam computed tomography (CBCT) is critical for pedicle screw planning; however, image quality is frequently compromised by artifacts and low contrast, potentially leading to adverse clinical outcomes. To address these limitations, we propose the Spatiotemporal Adaptive Warm-Start Diffusion Model (STADW-M), a novel framework aimed to generate high-quality synthetic CT (sCT) images from CBCT data, thereby enhancing surgical precision. The STADW-M integrates an Artifact-Aware Adaptive Diffusion Module to mitigate localized artifact distributions and a Dually-Guided Structural Consistency Module to preserve anatomical integrity. Furthermore, we employ a CBCT Warm-Start strategy alongside composite loss functions to optimize textural fidelity and accelerate model convergence. Quantitative experiments demonstrated significant improvements over original CBCT images: with RMSE decreased from 890.1 to 152.9 HU, MAE decreasing from 859.7 to 102.6 HU, and PSNR increased from 13.6 to 27.9 dB. Crucially, the generated sCTs maintained high anatomical consistency with reference CTs. In clinical validation, automated screw planning based on sCTs achieved a 100% Grade A standard, with 94.7% of screws placed without cortical breach and 5.3% exhibiting only minor (<2 mm) erosion. The proposed method effectively synthesizes high-quality CT images, preserving vertebral anatomy and significantly improving the accuracy and safety of intraoperative pedicle screw planning.
BalakrishnanGZhaoASabuncuMR, et al.VoxelMorph: a learning framework for deformable medical image registration. IEEE Trans Med Imaging2019; 38: 1788–1800.
2.
GuoCK. Multi-modal image registration with unsupervised deep learning. PhD Thesis, Massachusetts Institute of Technology, 2019.
3.
MasonAPaulsenRBabuskaJM, et al.The accuracy of pedicle screw placement using intraoperative image guidance systems: a systematic review. J Neurosurg Spine2014; 20: 196–203.
4.
LeeJCarassAJogA, et al.Multi-atlas-based CT synthesis from conventional MRI with patch-based refinement for MRI-based radiotherapy planning. In Medical imaging 2017: image orocessing. Vol. 10133. SPIE, pp. 434–439.
5.
SorciniBTilikidisA. Clinical application of image-guided radiotherapy, IGRT (on the Varian OBI platform). Cancer/Radiothérapie2006; 10: 252–257.
6.
LeeYCLeeR. Image-guided pedicle screws using intraoperative cone-beam CT and navigation. A cost-effectiveness study. J Clin Neurosci2020; 72: 68–71.
7.
DeaNFisherCGBatkeJ, et al.Economic evaluation comparing intraoperative cone beam CT-based navigation and conventional fluoroscopy for the placement of spinal pedicle screws: a patient-level data cost-effectiveness analysis. Spine J2016; 16: 23–31.
8.
RivkinMAYocomSS. Thoracolumbar instrumentation with CT-guided navigation (O-arm) in 270 consecutive patients: accuracy rates and lessons learned. Neurosurg Focus2014; 36: E7.
9.
CaiDWangZLiuY, et al.Automatic path planning for navigated pedicle screw surgery based on deep neural network. In 2019 WRC symposium on advanced robotics and automation (WRC SARA). IEEE, pp. 62–67.
10.
HarmsJLeiYWangT, et al.Paired cycle-GAN-based image correction for quantitative cone-beam computed tomography. Med Phys2019; 46: 3998–4009.
11.
JajuPPJainMSinghA, et al.Artefacts in cone beam CT. Open J Stomatol2013; 3: 292.
12.
SchulzeRHeilUGroβD, et al.Artefacts in CBCT: a review. Dentomaxillofac Radiol2011; 40: 265–273.
13.
SilbermannJRieseFAllamY, et al.Computer tomography assessment of pedicle screw placement in lumbar and sacral spine: comparison between free-hand and O-arm based navigation techniques. Eur Spine J2011; 20: 875–881.
14.
ZhangQHanXGXuYF, et al.Robotic navigation during spine surgery. Expert Rev Med Devices2020; 17: 27–32.
15.
ZhuLXieYWangJ, et al.Scatter correction for cone-beam CT in radiation therapy. Med Phys2009; 36: 2258–2268.
16.
XuYBaiTYanH, et al.A practical cone-beam CT scatter correction method with optimized monte carlo simulations for image-guided radiation therapy. Phys Med Biol2015; 60: 3567.
17.
WuMKeilAConstantinD, et al.Metal artifact correction for x-ray computed tomography using KV and selective MV imaging. Med Phys2014; 41: 121910.
18.
BecharaBMooreWMcMahanC, et al.Metal artefact reduction with cone beam CT: an in vitro study. Dentomaxillofac Radiol2012; 41: 248–253.
19.
LiYGarrettJChenGH. Reduction of beam hardening artifacts in cone-beam CT imaging via SMART-RECON algorithm. In Proceedings of SPIE–the international society for optical engineering. Vol. 9783. p. 97830W.
20.
KidaSNakamotoTNakanoM, et al.Cone beam computed tomography image quality improvement using a deep convolutional neural network. Cureus2018; 10: e2548.
21.
ThummererADe JongBAZaffinoP, et al.Comparison of the suitability of CBCT-and MR-based synthetic CTs for daily adaptive proton therapy in head and neck patients. Phys Med Biol2020; 65: 235036.
22.
YuanNDyerBRaoS, et al.Convolutional neural network enhancement of fast-scan low-dose cone-beam CT images for head and neck radiotherapy. Phys Med Biol2020; 65: 035003.
23.
DarSUYurtMKaracanL, et al.Image synthesis in multi-contrast MRI with conditional generative adversarial networks. IEEE Trans Med Imaging2019; 38: 2375–2388.
24.
NieDTrulloRLianJ, et al.Medical image synthesis with deep convolutional adversarial networks. IEEE Trans Biomed Eng2018; 65: 2720–2730.
25.
ArmaniousKJiangCFischerM, et al.MedGAN: medical image translation using GANs. Comput Med Imaging Graph2020; 79: 101684.
26.
BarateauADe CrevoisierRLargentA, et al.Comparison of CBCT-based dose calculation methods in head and neck cancer radiotherapy: from hounsfield unit to density calibration curve to deep learning. Med Phys2020; 47: 4683–4693.
27.
ZhangYYueNSuMY, et al.Improving CBCT quality to CT level using deep learning with generative adversarial network. Med Phys2021; 48: 2816–2826.
28.
DahiyaNAlamSRZhangP, et al.Multitask 3D CBCT-to-CT translation and organs-at-risk segmentation using physics-based data augmentation. Med Phys2021; 48: 5130–5141.
29.
KidaSKajiSNawaK, et al.Visual enhancement of cone-beam CT by use of cyclegan. Med Phys2020; 47: 998–1010.
30.
KurzCMasperoMSavenijeMH, et al.CBCT correction using a cycle-consistent generative adversarial network and unpaired training to enable photon and proton dose calculation. Phys Med Biol2019; 64: 225004.
31.
LiangXChenLNguyenD, et al.Generating synthesized computed tomography (CT) from cone-beam computed tomography (CBCT) using cyclegan for adaptive radiation therapy. Phys Med Biol2019; 64: 125002.
32.
LiuYLeiYWangT, et al.CBCT-based synthetic CT generation using deep-attention cyclegan for pancreatic adaptive radiotherapy. Med Phys2020; 47: 2472–2483.
33.
GaoLXieKWuX, et al.Generating synthetic CT from low-dose cone-beam CT by using generative adversarial networks for adaptive radiotherapy. Radiat Oncol2021; 16: 1–16.
34.
XueXDingYShiJ, et al.Cone beam CT (CBCT) based synthetic CT generation using deep learning methods for dose calculation of nasopharyngeal carcinoma radiotherapy. Technol Cancer Res Treat2021; 20: 15330338211062415.
35.
LemusOMDWangYFLiF, et al.Dosimetric assessment of patient dose calculation on a deep learning-based synthesized computed tomography image for adaptive radiotherapy. J Appl Clin Med Phys2022; 23: e13595.
36.
DhariwalPNicholA. Diffusion models beat GANs on image synthesis. Adv Neural Inf Process Syst2021; 34: 8780–8794.
JalalAArvinteMDarasG, et al.Robust compressed sensing MRI with deep generative priors. Adv Neural Inf Process Syst2021; 34: 14938–14954.
39.
ChungHYeJC. Score-based diffusion models for accelerated MRI. Med Image Anal2022; 80: 102479.
40.
SongYShenLXingL, et al.Solving inverse problems in medical imaging with score-based generative models. arXiv preprint arXiv:211108005 (2021).
41.
GüngörADarSUÖztürkŞ, et al.Adaptive diffusion priors for accelerated MRI reconstruction. Med Image Anal2023; 88: 102872.
42.
ChungHLeeESYeJC. Mr image denoising and super-resolution using regularized reverse diffusion. IEEE Trans Med Imaging2022; 42: 922–934.
43.
PinayaWHLTudosiuPDDafflonJ, et al.Brain imaging generation with latent diffusion models. in MICCAI workshop on deep generative models, 2022, pp. 117–126.
44.
LugmayrADanelljanMRomeroA, et al.Repaint: Inpainting using denoising diffusion probabilistic models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 11461–11471.
RonnebergerOFischerPBroxT. U-Net: convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, 5–9 October 2015, proceedings, part III 18. Springer, pp. 234–241.
47.
VaswaniAShazeerNParmarN, et al.Attention is all you need. Adv Neural Inf Process Syst2017; 30: 5998–6008.
48.
HuangLYuanYGuoJ, et al.Interlaced sparse self-attention for semantic segmentation. arXiv preprint arXiv:190712273 (2019).
49.
HoJKalchbrennerNWeissenbornD, et al.Axial attention in multidimensional transformers. arXiv preprint arXiv:191212180 (2019).
50.
DongGZhangCLiangX, et al.A deep unsupervised learning model for artifact correction of pelvis cone-beam CT. Front Oncol2021; 11: 686875.
51.
PengJQiuRLWynneJF, et al.CBCT-based synthetic CT image generation using conditional denoising diffusion probabilistic model. Med Phys2024; 51: 1847–1859.
52.
FuLLiXCaiX, et al.Energy-guided diffusion model for CBCT-to-CT synthesis. Comput Med Imaging Graph2024; 113: 102344.
53.
HuijbenETerpstraMGalaponA, et al.Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report. Med Image Anal2024; 97: 103276.
54.
ZhangYLiuWZhaoJ, et al.Improving pedicle screw path planning by vertebral posture estimation. Phys Med Biol2023; 68: 185011.
