Assessment of low-dose paranasal sinus CT imaging using a new deep learning image reconstruction technique in children compared to adaptive statistical iterative reconstruction V (ASiR-V)

Table 2 Comparison of noise and CNR in different reconstruction methods (DLIR-high) and (AsirV-50%)

Reconstruction algorithm	Inferior meatus level						Temporal bone level
Reconstruction algorithm	Inferior turbinate mucosa Noise	Infratemporal fossa Noise	Image Noise	Inferior turbinate mucosa SNR	Infratemporal fossa SNR	CNR	Petrosal bone Noise	Pterygoid process Noise	Image Noise	Petrosal bone SNR	Pterygoid process SNR	CNR
DLIR-high	10.14 ± 2.45	11.56 ± 3.42	8.12 ± 2.45	4.26 ± 1.91	9.73 ± 3.80	18.68 ± 5.28	140.98 ± 40.21	76.44 ± 20.66	9.94 ± 1.29	14.05 ± 4.33	0.52 ± 0.24	189.66 ± 23.15
AsirV-50%	13.79 ± 2.59	15.86 ± 3.59	14.35 ± 3.08	2.86 ± 0.90	6.74 ± 2.16	10.18 ± 2.65	150.32 ± 37.54	81.24 ± 20.01	21.35 ± 2.30	13.09 ± 4.04	0.51 ± 0.30	88.49 ± 10.62
P	P < 0.05	P < 0.05	P < 0.05	P < 0.05	P < 0.05	P < 0.05	P > 0.05	P > 0.05	P < 0.05	P > 0.05	P > 0.05	P < 0.05

ISSN: 1471-2342