Learning metal artifact reduction in cardiac CT images with moving pacemakers

Lossau, Tanja; Nickisch, Hannes; Wissel, Tobias; Morlock, Michael M.; Graß, Michael

doi:10.1016/j.media.2020.101655

Cited by 15 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different strategies for deep learning-based metal artefact reduction (MAR) of CT images were explored either in the image or projection domains [18][19][20][21][22]. The evaluation of CT images after MAR demonstrated the superior performance of the deep learning-based MAR in the image domain (DLI-MAR) when additional information (prior knowledge) in the form of CT images corrected by the normalized MAR approach was also fed to the network (Fig.…”

Section: Discussionmentioning

confidence: 99%

“…Deep learning-based algorithms emerged as promising approaches for solving a variety of image analysis and pattern recognition problems and have been successfully implemented in the context of metal artefact reduction in CT imaging [18][19][20][21][22][23]. Deep learning-based MAR techniques could be categorized as the 4th type of MAR approaches, wherein the correction for metal-induced beam hardening is applied in either the projection [22] or image domain [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning–based metal artefact reduction in PET/CT imaging

Arabi

Zaidi

2021

Eur Radiol

View full text Add to dashboard Cite

Objectives The susceptibility of CT imaging to metallic objects gives rise to strong streak artefacts and skewed information about the attenuation medium around the metallic implants. This metal-induced artefact in CT images leads to inaccurate attenuation correction in PET/CT imaging. This study investigates the potential of deep learning–based metal artefact reduction (MAR) in quantitative PET/CT imaging. Methods Deep learning–based metal artefact reduction approaches were implemented in the image (DLI-MAR) and projection (DLP-MAR) domains. The proposed algorithms were quantitatively compared to the normalized MAR (NMAR) method using simulated and clinical studies. Eighty metal-free CT images were employed for simulation of metal artefact as well as training and evaluation of the aforementioned MAR approaches. Thirty 18F-FDG PET/CT images affected by the presence of metallic implants were retrospectively employed for clinical assessment of the MAR techniques. Results The evaluation of MAR techniques on the simulation dataset demonstrated the superior performance of the DLI-MAR approach (structural similarity (SSIM) = 0.95 ± 0.2 compared to 0.94 ± 0.2 and 0.93 ± 0.3 obtained using DLP-MAR and NMAR, respectively) in minimizing metal artefacts in CT images. The presence of metallic artefacts in CT images or PET attenuation correction maps led to quantitative bias, image artefacts and under- and overestimation of scatter correction of PET images. The DLI-MAR technique led to a quantitative PET bias of 1.3 ± 3% compared to 10.5 ± 6% without MAR and 3.2 ± 0.5% achieved by NMAR. Conclusion The DLI-MAR technique was able to reduce the adverse effects of metal artefacts on PET images through the generation of accurate attenuation maps from corrupted CT images. Key Points • The presence of metallic objects, such as dental implants, gives rise to severe photon starvation, beam hardening and scattering, thus leading to adverse artefacts in reconstructed CT images. • The aim of this work is to develop and evaluate a deep learning–based MAR to improve CT-based attenuation and scatter correction in PET/CT imaging. • Deep learning–based MAR in the image (DLI-MAR) domain outperformed its counterpart implemented in the projection (DLP-MAR) domain. The DLI-MAR approach minimized the adverse impact of metal artefacts on whole-body PET images through generating accurate attenuation maps from corrupted CT images.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep learning–based metal artefact reduction in PET/CT imaging

Arabi

Zaidi

2021

Eur Radiol

View full text Add to dashboard Cite

show abstract

“…VMI at higher keV levels provided significant reduction of artifacts at CIED generator and leads (with exception of VMI for hypodense artifacts at the leads) in the subjective assessment, whereas a significant decrease of artifacts in the objective analysis was only observed for Prior studies have investigated the use of VMI, MAR, and their combination (VMI MAR ) from dual-energy CT for reduction of artifacts arising from high density materials, such as orthopedic hardware [24], dental implants [13], deep brain stimulation leads [25], iodinated contrast agent [26], and coils and clips for intracranial aneurysm treatment [21,27,28]. More recent studies focusing on the reduction of artifacts impairing the assessment of the heart and surrounding structures (e.g., from pacemaker devices or other cardiac hardware) showed promising results for the application of artifact reduction algorithms and reconstruction techniques to improve image quality [12,[14][15][16][17]. For instance, Tatsugami et al demonstrated that artifact reduction algorithms allow for a superior Fig.…”

Section: Discussionmentioning

confidence: 99%

“…For the CIED leads, VMI alone (third row) provide only minimal benefit in artifact reduction, whereas performance by VMI MAR (bottom row) is a lot stronger assessment of coronary arteries in patients with CIEDs [12]. Also, the application of a convolutional network has been successfully tested for the reduction of artifacts from pacemaker leads [16]. Van Hedent et al investigated the application of VMI for the reduction of artifacts in chest and abdominal imaging of patients including artifacts from pacemakers [17].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Reduction of CT artifacts from cardiac implantable electronic devices using a combination of virtual monoenergetic images and post-processing algorithms

et al. 2021

View full text Add to dashboard Cite

Objectives To evaluate the reduction of artifacts from cardiac implantable electronic devices (CIEDs) by virtual monoenergetic images (VMI), metal artifact reduction (MAR) algorithms, and their combination (VMIMAR) derived from spectral detector CT (SDCT) of the chest compared to conventional CT images (CI). Methods In this retrospective study, we included 34 patients (mean age 74.6 ± 8.6 years), who underwent a SDCT of the chest and had a CIED in place. CI, MAR, VMI, and VMIMAR (10 keV increment, range: 100–200 keV) were reconstructed. Mean and standard deviation of attenuation (HU) among hypo- and hyperdense artifacts adjacent to CIED generator and leads were determined using ROIs. Two radiologists qualitatively evaluated artifact reduction and diagnostic assessment of adjacent tissue. Results Compared to CI, MAR and VMIMAR ≥ 100 keV significantly increased attenuation in hypodense and significantly decreased attenuation in hyperdense artifacts at CIED generator and leads (p < 0.05). VMI ≥ 100 keV alone only significantly decreased hyperdense artifacts at the generator (p < 0.05). Qualitatively, VMI ≥ 100 keV, MAR, and VMIMAR ≥ 100 keV provided significant reduction of hyper- and hypodense artifacts resulting from the generator and improved diagnostic assessment of surrounding structures (p < 0.05). Diagnostic assessment of structures adjoining to the leads was only improved by MAR and VMIMAR 100 keV (p < 0.05), whereas keV values ≥ 140 with and without MAR significantly worsened diagnostic assessment (p < 0.05). Conclusions The combination of VMI and MAR as well as MAR as a standalone approach provides effective reduction of artifacts from CIEDs. Still, higher keV values should be applied with caution due to a loss of soft tissue and vessel contrast along the leads. Key Points • The combination of VMI and MAR as well as MAR as a standalone approach enables effective reduction of artifacts from CIEDs. • Higher keV values of both VMI and VMIMARat CIED leads should be applied with caution since diagnostic assessment can be hampered by a loss of soft tissue and vessel contrast. • Recommended keV values for CIED generators are between 140 and 200 keV and for leads around 100 keV.

show abstract

Single‐pass metal artifact reduction using a dual‐layer flat panel detector

et al. 2021

View full text Add to dashboard Cite

Metal artifact remains a challenge in cone-beam CT images. Many image domain-based segmentation methods have been proposed for metal artifact reduction (MAR), which require two-pass reconstruction. Such methods first segment metal from a first-pass reconstruction and then forward-project the metal mask to identify them in projections. These methods work well in general but are limited when the metal is outside the scan field-of-view (FOV) or when the metal is moving during the scan. In the former, even reconstructing with a larger FOV does not guarantee a good estimate of metal location in the projections; and in the latter, the metal location in each projection is difficult to identify due to motion. Single-pass methods that detect metal in single-energy projections have also been developed, but often have imperfect metal detection that leads to residual artifacts. In this work, we develop a MAR method using a dual-layer (DL) flat panel detector, which improves performance for single-pass reconstruction. Methods:In this work, we directly detect metal objects in projections using dualenergy (DE) imaging that generates material-specific images (e.g., soft tissue and bone), where the metal stands out in bone images when nonuniform soft tissue background is removed. Metal is detected via simple thresholding, and entropy filtration is further applied to remove false-positive detections. A DL detector provides DE images with superior temporal and spatial registration and was used to perform the task. Scatter correction was first performed on DE raw projections to improve the accuracy of material decomposition. One phantom mimicking a liver biopsy setup and a cadaver head were used to evaluate the metal reduction performance of the proposed method and compared with that of a standard two-pass reconstruction, a previously published sinogram-based method using a Markov random field (MRF) model, and a single-pass projectiondomain method using single-energy imaging. The phantom has a liver steering setup placed in a hollow chest phantom, with embedded metal and a biopsy needle crossing the phantom boundary. The cadaver head has dental fillings and a metal tag attached to its surface. The identified metal regions in each projection SINGLE-PASS METAL ARTIFACT REDUCTION USING A DUAL-LAYER FLAT PANEL DETECTOR 6483 2 |

show abstract

Learning metal artifact reduction in cardiac CT images with moving pacemakers

Cited by 15 publications

References 22 publications

Deep learning–based metal artefact reduction in PET/CT imaging

Deep learning–based metal artefact reduction in PET/CT imaging

Reduction of CT artifacts from cardiac implantable electronic devices using a combination of virtual monoenergetic images and post-processing algorithms

Single‐pass metal artifact reduction using a dual‐layer flat panel detector

Contact Info

Product

Resources

About