TY - JOUR
T1 - Is AI the way forward for reducing metal artifacts in CT? development of a generic deep learning-based method and initial evaluation in patients with sacroiliac joint implants
AU - Selles, Mark
AU - Maas, Mario
AU - Wellenberg, Ruud H. H.
AU - Slotman, Derk J.
AU - van Osch, Jochen A. C.
AU - Nijholt, Ingrid M.
AU - Boomsma, Martijn. F.
N1 - Funding Information: The Department of Radiology, Isala, Zwolle, the Netherlands, has established a research collaboration with Philips Healthcare regarding metal artefact reduction. This work was supported by a research exhibit with Philips Healthcare (Exhibit B-12: Photon Counting in Metal Artifact Reduction). However, the subsiding party had no decisive role in deep learning model development, data collection, data analysis nor data interpretation. The authors would like to thank Bas Buijtenhuis and Robin van Riel for their contribution to this research. Ethical approval was issued by the institutional medical ethical committee of Isala, Zwolle with a waiver for the need for informed consent. Informed consent was not necessary due to the retrospective nature of the study. Publisher Copyright: © 2023 Elsevier B.V.
PY - 2023/6/1
Y1 - 2023/6/1
N2 - Purpose: To develop a deep learning-based metal artifact reduction technique (DL-MAR) and quantitatively compare metal artifacts on DL-MAR-corrected CT-images, orthopedic metal artifact reduction (O-MAR)-corrected CT-images and uncorrected CT-images after sacroiliac (SI) joint fusion. Methods: DL-MAR was trained on CT-images with simulated metal artifacts. Pre-surgery CT-images and uncorrected, O-MAR-corrected and DL-MAR-corrected post-surgery CT-images of twenty-five patients undergoing SI joint fusion were retrospectively obtained. Image registration was applied to align pre-surgery with post-surgery CT-images within each patient, allowing placement of regions of interest (ROIs) on the same anatomical locations. Six ROIs were placed on the metal implant and the contralateral side in bone lateral of the SI joint, the gluteus medius muscle and the iliacus muscle. Metal artifacts were quantified as the difference in Hounsfield units (HU) between pre- and post-surgery CT-values within the ROIs on the uncorrected, O-MAR-corrected and DL-MAR-corrected images. Noise was quantified as standard deviation in HU within the ROIs. Metal artifacts and noise in the post-surgery CT-images were compared using linear multilevel regression models. Results: Metal artifacts were significantly reduced by O-MAR and DL-MAR in bone (p < 0.001), contralateral bone (O-MAR: p = 0.009; DL-MAR: p < 0.001), gluteus medius (p < 0.001), contralateral gluteus medius (p < 0.001), iliacus (p < 0.001) and contralateral iliacus (O-MAR: p = 0.024; DL-MAR: p < 0.001) compared to uncorrected images. Images corrected with DL-MAR resulted in stronger artifact reduction than images corrected with O-MAR in contralateral bone (p < 0.001), gluteus medius (p = 0.006), contralateral gluteus medius (p < 0.001), iliacus (p = 0.017), and contralateral iliacus (p < 0.001). Noise was reduced by O-MAR in bone (p = 0.009) and gluteus medius (p < 0.001) while noise was reduced by DL-MAR in all ROIs (p < 0.001) in comparison to uncorrected images. Conclusion: DL-MAR showed superior metal artifact reduction compared to O-MAR in CT-images with SI joint fusion implants.
AB - Purpose: To develop a deep learning-based metal artifact reduction technique (DL-MAR) and quantitatively compare metal artifacts on DL-MAR-corrected CT-images, orthopedic metal artifact reduction (O-MAR)-corrected CT-images and uncorrected CT-images after sacroiliac (SI) joint fusion. Methods: DL-MAR was trained on CT-images with simulated metal artifacts. Pre-surgery CT-images and uncorrected, O-MAR-corrected and DL-MAR-corrected post-surgery CT-images of twenty-five patients undergoing SI joint fusion were retrospectively obtained. Image registration was applied to align pre-surgery with post-surgery CT-images within each patient, allowing placement of regions of interest (ROIs) on the same anatomical locations. Six ROIs were placed on the metal implant and the contralateral side in bone lateral of the SI joint, the gluteus medius muscle and the iliacus muscle. Metal artifacts were quantified as the difference in Hounsfield units (HU) between pre- and post-surgery CT-values within the ROIs on the uncorrected, O-MAR-corrected and DL-MAR-corrected images. Noise was quantified as standard deviation in HU within the ROIs. Metal artifacts and noise in the post-surgery CT-images were compared using linear multilevel regression models. Results: Metal artifacts were significantly reduced by O-MAR and DL-MAR in bone (p < 0.001), contralateral bone (O-MAR: p = 0.009; DL-MAR: p < 0.001), gluteus medius (p < 0.001), contralateral gluteus medius (p < 0.001), iliacus (p < 0.001) and contralateral iliacus (O-MAR: p = 0.024; DL-MAR: p < 0.001) compared to uncorrected images. Images corrected with DL-MAR resulted in stronger artifact reduction than images corrected with O-MAR in contralateral bone (p < 0.001), gluteus medius (p = 0.006), contralateral gluteus medius (p < 0.001), iliacus (p = 0.017), and contralateral iliacus (p < 0.001). Noise was reduced by O-MAR in bone (p = 0.009) and gluteus medius (p < 0.001) while noise was reduced by DL-MAR in all ROIs (p < 0.001) in comparison to uncorrected images. Conclusion: DL-MAR showed superior metal artifact reduction compared to O-MAR in CT-images with SI joint fusion implants.
KW - CT
KW - Deep learning
KW - Metal artifacts
KW - Orthopedic implants
KW - Sacroiliac joint fusion
UR - http://www.scopus.com/inward/record.url?scp=85153590177&partnerID=8YFLogxK
U2 - https://doi.org/10.1016/j.ejrad.2023.110844
DO - https://doi.org/10.1016/j.ejrad.2023.110844
M3 - Article
C2 - 37119708
SN - 0720-048X
VL - 163
JO - European Journal of Radiology
JF - European Journal of Radiology
M1 - 110844
ER -