Image quality and metal artifact reduction in total hip arthroplasty CT: deep learning-based algorithm versus virtual monoenergetic imaging and orthopedic metal artifact reduction

European Radiology Experimental

Table 2 Median and interquartile range (IQR) for conventional images, 130-keV monoE, conventional images with O-MAR, 130-keV monoE with O-MAR, and DL-MAR images

	Conventional (median, IQR)	130 keV	Conventional + O-MAR	130 keV + O-MAR	DL-MAR
Image quality	1 (1–2)	1 (1–2)	2 (2–3)^a	2 (2–3)^a	3 (3–4)^b
Diagnostic confidence
Bone	1 (1–1)	1 (1–2)	2 (2–3)^a	2 (2–3)^a	4 (3–4)^b
Pelvic organs	1 (1–2)	1 (1–1)	2 (2–3)^a	2 (1–3)^a	4 (2–4)^a
Soft tissue adjacent to the prosthesis	1 (1–2)	1 (1–2)	2 (2–3)^a	2 (2–3)^a	3 (3–4)^b
Metal artifacts	1 (1–1)	1 (1–1)	2 (2–3)^a	2 (2–3)^a	3 (3–4)^b

IQR Interquartile range, O-MAR Orthopedic metal artifact reduction, DL-MAR Deep learning-based metal artifact reduction
^aSignificant reduction in comparison to conventional images and 130-keV monoE
^bSignificant reduction in comparison to conventional images, 130-keV monoE, conventional images with O-MAR, and 130-keV monoE with O-MAR