Noise power spectrum properties of deep learning–based reconstruction and iterative reconstruction algorithms: Phantom and clinical study

• Published in: European journal of radiology 2023-08, Vol.165, p.110914-110914, Article 110914
• Main Authors: Funama, Yoshinori, Nakaura, Takeshi, Hasegawa, Akira, Sakabe, Daisuke, Oda, Seitaro, Kidoh, Masafumi, Nagayama, Yasunori, Hirai, Toshinori
• Format: Article
• Language: English
• Subjects: Computed tomography; Deep learning reconstruction; Image texture; Noise reduction; Visual evaluation
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2023.110914

•DLR images achieve substantial noise reduction compared with other reconstruction algorithms.•DLR images maintain noise texture better than other reconstruction algorithms.•Sole phantom studies are insufficient for future evaluation of DLR techniques. To compare the noise power spectrum (NPS) properties and perform a qualitative analysis of hybrid iterative reconstruction (IR), model-based IR (MBIR), and deep learning–based reconstruction (DLR) at a similar noise level in clinical study and compare these outcomes with those in phantom study. A Catphan phantom with an external body ring was used in the phantom study. In the clinical study, computed tomography (CT) examination data of 34 patients were reviewed. NPS was calculated from DLR, hybrid IR, and MBIR images. The noise magnitude ratio (NMR) and the central frequency ratio (CFR) were calculated from DLR, hybrid IR, and MBIR images relative to filtered back-projection images using NPS. Clinical images were independently reviewed by two radiologists. In the phantom study, DLR with a mild level had a similar noise level as hybrid IR and MBIR with strong levels. In the clinical study, DLR with a mild level had a similar noise level as hybrid IR with standard and MBIR with strong levels. The NMR and CFR were 0.40 and 0.76 for DLR, 0.42 and 0.55 for hybrid IR, and 0.48 and 0.62 for MBIR. The visual inspection of the clinical DLR image was superior to that of the hybrid IR and MBIR images. Deep learning–based reconstruction improves overall image quality with substantial noise reduction while maintaining image noise texture compared with the CT reconstruction techniques.