Improved virtual non-contrast images in liver dual-energy CT with deep learning algorithm for image reconstruction.

BACKGROUND

We aimed to explore the use of deep learning image reconstruction (DLIR) to improve virtual non-contrast (VNC) images from enhanced dual-energy computed tomography (DECT).

MATERIALS AND

METHODS

A total of 91 patients undergoing treatment for liver lesions from September to December 2024 were analyzed. All patients underwent true non-contrast (TNC) and dual-phase enhanced DECT with medium-level DLIR (DLIR-M). The VNC images were generated from arterial phase (VNCA) and venous phase (VNCV) scans. The CT values and standard deviations of liver, spleen, bilateral erector spinae, and liver lesions were measured across the three image groups, and the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. Two radiologists subjectively scored the image quality. Measurements and quality scores were statistically compared among the groups.

RESULTS

There was no difference in CT values among the three groups (P > 0.05); VNCA and VNCV images did not alter the primary imaging characteristics of hypervascular liver lesions. The VNCA and VNCV images had lower image noise than the TNC images, with VNCV images having the lowest noise. Except for the spleen, VNCA and VNCV images had higher SNR than TNC images, with VNCV images having the best SNR. The subjective scores of the TNC, VNCA, and VNCV images were all greater than 3, showing good consistency between the two observers (kappa = 0.78, 0.76, and 0.83, respectively).There was no difference between the subjective evaluation of VNCA and TNC (P > 0.05), while VNCV had better image quality than TNC (P < 0.05). The total effective radiation dose was 8.55 ± 0.38 mSv; thus, replacing TNC with VNC would reduce the dose by 33.4%.

CONCLUSION

Virtual non-contrast images generated in liver DECT with DLIR provide similar CT values to TNC images. The VNCV images provide lower image noise as well as higher SNR and subjective scores than TNC and are recommended for clinical use.

ADVANCES IN KNOWLEDGE: Virtual non-contrast images with DLIR generated from DECT can improve image quality and reduce radiation dose.