Deep neural network for beam hardening artifacts removal in image reconstruction

Kalare, Kailash; Bajpai, Manish Kumar; Sarkar, Shubhabrata; Munshi, P.

doi:10.1007/s10489-021-02604-y

Cited by 10 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, deep learning has been applied to the problem of metal artifacts in CT images. [33][34][35][36] While these methods demonstrate good results, the drawback is that they are supervised learning methods, and require labeled datasets of images with metal artifacts and the same images with corrected or no metal artifacts as a target. One solution to this is unsupervised learning, which has been implemented for MAR more recently.…”

Section: Introductionmentioning

confidence: 99%

“…However, iterative methods usually require extensive computation time due to their iterative nature. More recently, deep learning has been applied to the problem of metal artifacts in CT images 33–36 . While these methods demonstrate good results, the drawback is that they are supervised learning methods, and require labeled datasets of images with metal artifacts and the same images with corrected or no metal artifacts as a target.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Metal artifact correction in photon‐counting detector computed tomography: metal trace replacement using high‐energy data

et al. 2022

View full text Add to dashboard Cite

Background: Metal artifacts have been an outstanding issue in computed tomography (CT) since its first uses in the clinic and continue to interfere. Metal artifact reduction (MAR) methods continue to be proposed and photon-counting detectors (PCDs) have recently been the subject of research toward this purpose. PCDs offer the ability to distinguish the energy of incident x-rays and sort them in a set number of energy bins. High-energy data captured using PCDs have been shown to reduce metal artifacts in reconstructions due to reduced beam hardening. Purpose: High-energy reconstructions using PCD-CT have their drawbacks, such as reduced image contrast and increased noise. Here, we demonstrate a MAR algorithm, trace replacement MAR (TRMAR), in which the data corrupted by metal artifacts in full energy spectrum projections are corrected using the high-energy data captured during the same scan. The resulting reconstructions offer similar MAR to that seen in high-energy reconstructions, but with improved image quality. Methods: Experimental data were collected using a bench-top PCD-CT system with a cadmium zinc telluride PCD. Simulations were performed to determine the optimal high-energy threshold and to test TRMAR in simulations using the XCAT phantom and a biological sample. For experiments a 100-mm diameter cylindrical phantom containing vials of water, two screws, various densities of Ca(ClO 4 ) 2 , and a spatial resolution phantom was imaged with and without the screws. The screws were segmented in the initial reconstruction and forward projected to identify them in the sinogram space in order to perform TRMAR.The resulting reconstructions were compared to the control and to reconstructions corrected using normalized metal artifact reduction (NMAR). Additionally, a beef short rib was imaged with and without metal to provide a more realistic phantom. Results: XCAT simulations showed a reduction in the streak artifact from −978 HU in uncorrected images to −10 HU with TRMAR. The magnitude of the metal artifact in uncorrected images of the 100-mm phantom was −442 HU, compared to the desired −81 HU with no metal. TRMAR reduced the magnitude of the artifact to −142 HU, with NMAR reducing the magnitude to −96 HU. Relative image noise was reduced from 176% in the high-energy image to 56% using TRMAR. Density quantification was better with NMAR, with the Ca(ClO 4 ) 2 vial affected most by metal artifacts showing 0.8% error compared to 2.1% with TRMAR. Small features were preserved to a greater extent with TRMAR, with the limiting spatial frequency at 20% of the MTF fully maintained at 1.31 lp/mm, 380

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%