Deep learning trained algorithm maintains the quality of half-dose contrast-enhanced liver computed tomography images: Comparison with hybrid iterative reconstruction

Purpose This study compares the image and diagnostic qualities of a DEep Learning Trained Algorithm (DELTA) for half-dose contrast-enhanced liver computed tomography (CT) with those of a commercial hybrid iterative reconstruction (HIR) method used for standard-dose CT (SDCT). Methods This study enrolled 207 adults, and they were divided into two groups: SDCT and low-dose CT (LDCT). SDCT was reconstructed using the HIR method (SDCTHIR), and LDCT was reconstructed using both the HIR method (LDCTHIR) and DELTA (LDCTDL). Noise, Hounsfield unit (HU) values, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were compared between three image series. Two radiologists assessed the noise, artefacts, overall image quality, visualisation of critical anatomical structures and lesion detection, characterisation and visualisation. Results The mean effective doses were 5.64 ± 1.96 mSv for SDCT and 2.87 ± 0.87 mSv for LDCT. The noise of LDCTDL was significantly lower than that of SDCTHIR and LDCTHIR. The SNR and CNR of LDCTDL were significantly higher than those of the other two groups. The overall image quality, visualisation of anatomical structures and lesion visualisation between LDCTDL and SDCTHIR were not significantly different. For lesion detection, the sensitivities and specificities of SDCTHIR vs. LDCTDL were 81.9 % vs. 83.7 % and 89.1 % vs. 86.3 %, respectively, on a per-patient basis. SDCTHIR showed 75.4 % sensitivity and 82.6 % specificity for lesion characterisation on a per-patient basis, whereas LDCTDL showed 73.5 % sensitivity and 82.4 % specificity. Conclusions LDCT with DELTA had approximately 49 % dose reduction compared with SDCT with HIR while maintaining image quality on contrast-enhanced liver CT.