A Deep Learning Image Reconstruction Algorithm for Improving Image Quality and Hepatic Lesion Detectability in Abdominal Dual-Energy Computed Tomography: Preliminary Results

Abstract

This study aimed to compare the performance of deep learning image reconstruction (DLIR) and adaptive statistical iterative reconstruction-Veo (ASIR-V) in improving image quality and diagnostic performance using virtual monochromatic spectral images in abdominal dual-energy computed tomography (DECT). Sixty-two patients [mean age ± standard deviation (SD): 56 years ± 13; 30 men] who underwent abdominal DECT were prospectively included in this study. The 70-keV DECT images in the portal phase were reconstructed at 5-mm and 1.25-mm slice thicknesses with 40% ASIR-V (ASIR-V40%) and at 1.25-mm slice with deep learning image reconstruction at medium (DLIR-M) and high (DLIR-H) levels and then compared. Computed tomography (CT) attenuation, SD values, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured in the liver, spleen, erector spinae, and intramuscular fat. The lesions in each reconstruction group at 1.25-mm slice thickness were counted. The image quality and diagnostic confidence were subjectively evaluated by two radiologists using a 5-point scale. For the 1.25-mm images, DLIR-M and DLIR-H had lower SD, higher SNR and CNR, and better subjective image quality compared with ASIR-V40%; DLIR-H performed the best (all P values < 0.001). Furthermore, the 1.25-mm DLIR-H images had similar SD, SNR, and CNR values as the 5-mm ASIR-V40% images (all P > 0.05). Three image groups had similar lesion detection rates, but DLIR groups exhibited higher confidence in diagnosing lesions. Compared with ASIR-V40% at 70 keV, 70-keV DECT with DLIR-H further reduced image noise and improved image quality. Additionally, it improved diagnostic confidence while ensuring a consistent lesion detection rate of liver lesions.

What to Expect (and What Not) from Dual-Energy CT Imaging Now and in the Future?

“…DL may extrapolate information outside the field of measurement of the second source-detector pair [66,67]. AI reduces image noise and improves DECT imaging quality [68][69][70][71]. Moreover, current material decomposition techniques suffer from excessive image noise and artifacts due to the dose limit in CT scanning and the noise magnification of the material decomposition process.…”

“…DLR provides better noise containment for low keV images and AI techniques have been demonstrated that may improve material decomposition performance and detectability of low iodine concentrations [69,71,72]. Additionally, in clinical practice, AI has also shown to be useful in tumor detection, characterization, staging, and prognosis [70,[73][74][75][76].…”