Patient‐specific pixel‐based weighting factor dual‐energy x‐ray imaging system using a priori CT data
Journal Articles
Overview
Research
Identity
Additional Document Info
View All
Overview
abstract
PurposeThe purpose of this study was to develop a novel patient‐specific pixel‐based weighting factor dual‐energy (PP‐DE) algorithm to effectively suppress bone throughout the image and overcome the limitation of the conventional DE algorithm with constant weighting factor which is restricted to regions with uniform patient thickness. Additionally, to derive theoretical expressions to describe the dependence of the weighting factors on several imaging parameters and validate them with measurement.MethodsA step phantom was constructed consisting of slabs of solid water and bone materials. Thicknesses of bone ranged [0–6] cm in one direction and solid water [5–30] cm in the other direction. Projection images at 60 and 140 kVp were acquired using a clinical imaging system. Optimal weighting factors were found by iteratively varying it in the range [0–1.4], where bone and soft‐tissue contrast‐to‐noise ratio (CNR) reached zero. Bone and soft‐tissue digitally reconstructed thicknesses were created using computed tomography (CT) images of a Rando phantom and ray tracing techniques. A weighting factor image (ω) was calculated using digitally reconstructed thicknesses (DRTs) and precalculated weighting factors from the step phantom. This ω image was then used to generate a PP‐DE image. The PP‐DE image was compared to the conventional DE image which uses a constant weighting factor throughout the image. The effect of the misaligned ω image on PP‐DE images was investigated by acquiring LE and HE images at various shifts of Rando phantom. A rigid registration was used based on mutual information algorithm in Matlab. The signal‐to‐noise ratios (SNR) were calculated in the step phantom for the PP‐DE image and compared to that of conventional DE technique. Analytical expressions for theoretical weighting factors were derived which included various effects such as beam hardening, scatter, and detector response. The analytical expressions were simulated in Spektr3.0 for different bone and solid water thicknesses as per the step phantom. A tray of steel pins was constructed and used with the step phantom to remove the scattered radiation. The simulated theoretical weighting factors were validated by comparing to those from the step phantom measurement.ResultsOptimal weighting factor values for the step phantom varied from 0.633 to 1.372 depending on region thickness. Thicker regions required larger weighting factors for bone cancellation. The PP‐DE image of the Rando phantom favorably cancelled both ribs and spine, whereas in the conventional DE image, only one could be cancelled at a time. The misaligned ω image was less effective in removing all bones indicating the importance of alignment as part of the PP‐DE algorithm implementation. The SNRs for the PP‐DE image was larger than those of the conventional DE images for regions which required smaller weighting factors for bone suppression. Comparisons of measured and simulated weighting factors demonstrated a 3% agreement for all bone overlapped regions except for the thickest region with 30 cm of solid water overlapped with 6 cm bone where the signal was lost due to excess attenuation.ConclusionsA novel PP‐DE algorithm was developed which can create higher quality DE images with enhanced bone cancellation and improved noise characteristics compared to conventional DE technique. In addition, theoretical weighting factor expressions were derived and validated against measurement.
