Photon Counting CT For Ultra Low-Dose Lung Cancer Screening

Abstract

Objective: The two-fold aim of this phantom study was first to evaluate the accuracy of pulmonary nodule detection for lung cancer screening at progressively lower dose levels of photon-counting computed tomography (PC-CT) and, second, to objectively compare the image quality across different acquisition and reconstruction settings, through a comparison of PC-CT and conventional energy-integrating detector (EID) CT.
Methods: Thirty-six artificial lung nodules with 6 diameters (2.5, 3, 4, 5, 6 and 10mm), 3 shapes (spherical, lobulated, spiculated) and two densities (-300 HU and +100 HU) were placed in an anthropomorphic chest phantom. The phantom was scanned using a standard lung cancer screening protocol (Sn 100 kV) with dose-matched EID-CT and PC-CT (CTDIvol of 0.8 mGy), in addition to 75%, 50%, 25% and 10% doses on the PC-CT (CTDIvol 0.6-0.07mGy). Nodule detection
was performed by one experienced reader, and denoted as the sensitivity, specificity, precision and false positive (FP) nodules. The acquisitions for assessing image quality were performed on a Quality Assurance (QA) phantom at full dose, with varying levels of iterative reconstruction (IR), virtual monoenergetic image (VMI) keV levels, slice thicknesses and increments, kernel strengths and scan modes. The noise power spectrum (NPS) and the task-based transfer function (TTF) were computed. The detectability index (d’) was computed to model the detection of a 4 mm solid and 5 mm subsolid pulmonary nodule.
Results: Sensitivity of 51-62% and specificity of 50-95% were obtained at 100%, 75%, 50%, 25% and 10% doses on the PC-CT, respectively, compared to the 59% sensitivity and 100% specificity on the EID-CT. The precision was 100% on the EID-CT and 94-99% on the PC-CT down to 25% dose, whereas at 10% dose the precision dropped to 88% and the FP nodules tripled from 5 to 15. Increasing the IR level, VMI keV and slice thickness decreased noise magnitude, with only minimal changes in noise texture. In contrast, higher kernel strength increased the noise magnitude, but created a finer noise texture. All settings showed a minimal impact on the spatial resolution. Noise magnitude was 40-60% higher on the EID-CT compared to PC-CT for all scan modes, although no difference in spatial resolution was found. Furthermore, the PC-CT attained 30-50% higher d’ values independent of scanmode or tin filter, in comparison to the EID-CT at a similar dose.
Conclusion: PC-CT with similar acquisition and reconstruction settings demonstrated comparable sensitivity for lung nodule detection despite lower radiation dose, when compared with EID-CT for low-dose lung cancer CT screening. However, attention has to be paid to FP findings at ultra-low dose levels, since the specificity decreased with every dose reduction. Furthermore, PC-CT achieved higher d’ values compared to EID-CT at an equivalent dose, through enhanced image quality and less noise. Additionally, the study shows that optimizing the image acquisition and reconstruction parameters can further enhance the image quality of PC-CT. These findings show that PC-CT holds significant promise as an alternative method for low-dose lung cancer screening. Consequently, future research should focus on evaluating the performance of PC-CT further on a more representative anthropomorphic phantom and in a clinical setting.