Objective We propose a motion artifact correction algorithm (DMBL) for reducing motion artifacts in reconstructed dental cone-beam computed tomography (CBCT) images based on deep blur learning. Methods A blur encoder was used to extract motion-related degradation features to model the degradation process caused by motion, and the obtained motion degradation features were imported in the artifact correction module for artifact removal. The artifact correction module adopts a joint learning framework for image blur removal and image blur simulation for treatment of spatially varying and random motion patterns. Comparative experiments were conducted to verify the effectiveness of the proposed method using both simulated motion data sets and clinical data sets. Results The experimental results with the simulated dataset showed that compared with the existing methods, the PSNR of the proposed method increased by 2.88%, the SSIM increased by 0.89%, and the RMSE decreased by 10.58%. The results with the clinical dataset showed that the proposed method achieved the highest expert level with a subjective image quality score of 4.417 (in a 5-point scale), significantly higher than those of the comparison methods. Conclusion The proposed DMBL algorithm with a deep blur joint learning network structure can effectively reduce motion artifacts in dental CBCT images and achieve high-quality image restoration.
KaasalainenT, EkholmM, SiiskonenT, et al. Dental cone beam CT: an updated review[J]. Phys Med, 2021, 88: 193-217.
[2]
NemtoiA, CzinkC, HabaD, et al. Cone beam CT: a current overview of devices[J]. Dentomaxillofac Radiol, 2013, 42(8): 20120443.
[3]
Spin-NetoR, WenzelA. Patient movement and motion artefacts in cone beam computed tomography of the dentomaxillofacial region: a systematic literature review[J]. Oral Surg Oral Med Oral Pathol Oral Radiol, 2016, 121(4): 425-33.
[4]
HanzelkaT, DusekJ, OcasekF, et al. Movement of the patient and the cone beam computed tomography scanner: objectives and possible solutions[J]. Oral Surg Oral Med Oral Pathol Oral Radiol, 2013, 116(6): 769-73.
[5]
Spin-NetoR, CostaC, SalgadoDM, et al. Patient movement characteristics and the impact on CBCT image quality and interpretability[J]. Dentomaxillofac Radiol, 2018, 47(1): 20170216.
[6]
WeisenbergerAG, GleasonSS, GoddardJ, et al. A restraint-free small animal SPECT imaging system with motion tracking[J]. IEEE Trans Nucl Sci, 2005, 52(3): 638-44.
[7]
HerzogH, TellmannL, FultonR, et al. Motion artifact reduction on parametric PET images of neuroreceptor binding[J]. J Nucl Med, 2005, 46(6): 1059-65.
[8]
KimJH, NuytsJ, KymeA, et al. A rigid motion correction method for helical computed tomography (CT)[J]. Phys Med Biol, 2015, 60(5): 2047-73.
[9]
KymeAZ, SeS, MeikleSR, et al. Markerless motion estimation for motion-compensated clinical brain imaging[J]. Phys Med Biol, 2018, 63(10): 105018.
[10]
SisniegaA, StaymanJW, YorkstonJ, et al. Motion compensation in extremity cone-beam CT using a penalized image sharpness criterion[J]. Phys Med Biol, 2017, 62(9): 3712-34.
[11]
MaurS, StsepankouD, HesserJ. Auto-calibration by locally consistent contours for dental CBCT[J]. Phys Med Biol, 2018, 63(21): 215018.
[12]
HuangH, SiewerdsenJH, ZbijewskiW, et al. Reference-free learning-based similarity metric for motion compensation in cone-beam CT[J]. Phys Med Biol, 2022, 67(12): 10.1088/1361-6560/ac749a.
[13]
HahnJ, BruderH, RohkohlC, et al. Motion compensation in the region of the coronary arteries based on partial angle reconstructions from short-scan CT data[J]. Med Phys, 2017, 44(11): 5795-813.
[14]
BergerM, XiaY, AichingerW, et al. Motion compensation for cone-beam CT using Fourier consistency conditions[J]. Phys Med Biol, 2017, 62(17): 7181-215.
[15]
PreuhsA, MaierA, ManhartM, et al. Symmetry prior for epipolar consistency[J]. Int J Comput Assist Radiol Surg, 2019, 14(9): 1541-51.
[16]
OuadahS, JacobsonM, StaymanJW, et al. Correction of patient motion in cone-beam CT using 3D-2D registration[J]. Phys Med Biol, 2017, 62(23): 8813-31.
[17]
NieblerS, SchömerE, TjadenH, et al. Projection-based improvement of 3D reconstructions from motion-impaired dental cone beam CT data[J]. Med Phys, 2019, 46(10): 4470-80.
[18]
HuZL, JiangCH, ZhangQY, et al. Wasserstein generative adversarial networks for motion artifact removal in dental CT imaging[C]//Medical Imaging 2019: Physics of Medical Imaging. February 16-21, 2019. San Diego, USA. SPIE, 2019: 1094836.
[19]
SuB, WenYT, LiuYY, et al. A deep learning method for eliminating head motion artifacts in computed tomography[J]. Med Phys, 2022, 49(1): 411-9.
[20]
KoY, MoonS, BaekJ, et al. Rigid and non-rigid motion artifact reduction in X-ray CT using attention module[J]. Med Image Anal, 2021, 67: 101883.
[21]
Spin-NetoR, MatzenLH, SchroppLW, et al. An ex vivo study of automated motion artefact correction and the impact on cone beam CT image quality and interpretability[J]. Dentomaxillofacial Radiol, 2018: 20180013.
[22]
KimJH, SunT, AlcheikhAR, et al. Correction for human head motion in helical X-ray CT[J]. Phys Med Biol, 2016, 61(4): 1416-38.
[23]
LiXH, DaZ, LiuB. A generic geometric calibration method for tomographic imaging systems with flat-panel detectors: a detailed implementation guide[J]. Med Phys, 2010, 37(7): 3844-54.
[24]
LiDS, ZhangY, CheungKC, et al. Learning degradation representations for image deblurring[C]//European Conference on Computer Vision. Cham: Springer, 2022: 736-753.
[25]
ParkT, LiuMY, WangTC, et al. Semantic image synthesis with spatially-adaptive normalization[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA. IEEE, 2019: 2332-41.
[26]
MechrezR, TalmiI, ShamaF, et al. Maintaining natural image statistics with the contextual loss[C]//Asian Conference on Computer Vision. Cham: Springer, 2019: 427-443.
[27]
RonnebergerO, FischerP, BroxT. U-net: convolutional networks for biomedical image segmentation[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015: 234-41.
[28]
GulrajaniI, AhmedF, ArjovskyM, et al. Improved training of Wasserstein GANs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. December 4 ‑9, 2017, Long Beach, California, USA. ACM, 2017: 5769-79.
[29]
ChenLY, LuX, ZhangJ, et al. HINet: half instance normalization network for image restoration[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Nashville, TN, USA. IEEE, 2021: 182-92.
[30]
ZamirSW, AroraA, KhanS, et al. Restormer: efficient transformer for high-resolution image restoration[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, LA, USA. IEEE, 2022: 5718-29.
[31]
SunT, JacobsR, PauwelsR, et al. A motion correction approach for oral and maxillofacial cone-beam CT imaging[J]. Phys Med Biol, 2021, 66(12): 125008.
[32]
WangZH, ChenJ, HoiSCH. Deep learning for image super-resolution: a survey[J]. IEEE Trans Pattern Anal Mach Intell, 2021, 43(10): 3365-87.