Evaluation of thin-slice abdominal DECT using deep-learning image reconstruction in 74keV virtual monoenergetic images: an image quality comparison.

Abstract

To compare noise, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR) and image quality using deep-learning image reconstruction (DLIR) vs. adaptive statistical iterative reconstruction (ASIR-V) in 0.625 and 2.5mm slice thickness gray scale 74keV virtual monoenergetic (VM) abdominal dual-energy CT (DECT). This retrospective study was approved by the institutional review board and regional ethics committee. We analysed 30 portal-venous phase abdominal fast kV-switching DECT (80/140kVp) scans. Data were reconstructed to ASIR-V 60% and DLIR-High at 74keV in 0.625 and 2.5mm slice thickness. Quantitative HU and noise assessment were measured within liver, aorta, adipose tissue and muscle. Two board-certified radiologists evaluated image noise, sharpness, texture and overall quality based on a five-point Likert scale. DLIR significantly reduced image noise and increased CNR as well as SNR compared to ASIR-V, when slice thickness was maintained (p < 0.001). Slightly higher noise of 5.5-16.2% was measured (p < 0.01) in liver, aorta and muscle tissue at 0.625mm DLIR compared to 2.5mm ASIR-V, while noise in adipose tissue was 4.3% lower with 0.625mm DLIR compared to 2.5mm ASIR-V (p = 0.08). Qualitative assessments demonstrated significantly improved image quality for DLIR particularly in 0.625mm images. DLIR significantly reduced image noise, increased CNR and SNR and improved image quality in 0.625mm slice images, when compared to ASIR-V. DLIR may facilitate thinner image slice reconstructions for routine contrast-enhanced abdominal DECT.