Huber, Nathan Robert

Objective: The purpose of this study was to evaluate the potential clinical value of spectral CT for image guidance during percutaneous thermal ablation, particularly investigating high monoenergetic (MonoE) for metal artifact reduction. Materials and Methods: A phantom experiment was performed in which an ablation probe was scanned in “continuous CT” (CCT) mode on a spectral CT scanner. ROI measurements quantified metal artifacts for conventional and MonoE CCT images. Subsequently, a retrospective reader study was conducted with 10 patient cases. Three radiologists reviewed cases to select the optimal MonoE setting and perform a Likert score rating (+2: MonoE preferred, −2: conventional preferred). Results: Phantom measurements indicated a reduction in metal artifact for high MonoE (150 keV: −46 HU) relative to conventional CCT (−122 HU). The MonoE setting preference was 151±21 keV. The mean Likert score was 1.2±0.7. Radiologists indicated a perceived benefit of high MonoE CCT when probe placement was near a critical structure. Conclusions: This study indicates a clinical preference for high MonoE CCT compared with conventional CCT. Insofar as spectral CCT can be offered at a clinically feasible time frame, our results support the assessment of 150 keV image to reduce metal artifact while maintaining satisfactory soft tissue contrast.

Abstract Objective. To develop a convolutional neural network (CNN) noise reduction technique for ultra-high-resolution photon-counting detector computed tomography (UHR-PCD-CT) that can be efficiently implemented using only clinically available reconstructed images. The developed technique was demonstrated for skeletal survey, lung screening, and head angiography (CTA). Approach . There were 39 participants enrolled in this study, each received a UHR-PCD and an energy integrating detector (EID) CT scan. The developed CNN noise reduction technique uses image-based noise insertion and UHR-PCD-CT images to train a U-Net via supervised learning. For each application, 13 patient scans were reconstructed using filtered back projection (FBP) and iterative reconstruction (IR) and allocated into training, validation, and testing datasets (9:1:3). The subtraction of FBP and IR images resulted in approximately noise-only images. The 5-slice average of IR produced a thick reference image. The CNN training input consisted of thick reference images with reinsertion of spatially decoupled noise-only images. The training target consisted of the corresponding thick reference images without noise insertion. Performance was evaluated based on difference images, line profiles, noise measurements, nonlinear perturbation assessment, and radiologist visual assessment. UHR-PCD-CT images were compared with EID images (clinical standard). Main results. Up to 89% noise reduction was achieved using the proposed CNN. Nonlinear perturbation assessment indicated reasonable retention of 1 mm radius and 1000 HU contrast signals (>80% for skeletal survey and head CTA, >50% for lung screening). A contour plot indicated reduced retention for small-radius and low contrast perturbations. Radiologists preferred CNN over IR for UHR-PCD-CT noise reduction. Additionally, UHR-PCD-CT with CNN was preferred over standard resolution EID-CT images. Significance. CT images reconstructed with very sharp kernels and/or thin sections suffer from increased image noise. Deep learning noise reduction can be used to offset noise level and increase utility of UHR-PCD-CT images.