Impact of a Deep Learning-based Super-resolution Image Reconstruction Technique on High-contrast Computed Tomography: A Phantom Study

Hideyuki Sato; Shinichiro Fujimoto; Nobuo Tomizawa; Hidekazu Inage; Takuya Yokota; Hikaru Kudo; Ruiheng Fan; Keiichi Kawamoto; Yuri Honda; Takayuki Kobayashi; Tohru Minamino; Yosuke Kogure

doi:10.1016/j.acra.2022.12.040

Impact of a Deep Learning-based Super-resolution Image Reconstruction Technique on High-contrast Computed Tomography: A Phantom Study

Acad Radiol. 2023 Nov;30(11):2657-2665. doi: 10.1016/j.acra.2022.12.040. Epub 2023 Jan 22.

Authors

Affiliations

¹ Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan.
² Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Tokyo, Japan. Electronic address: blanks-fujimo@tj8.so-net.ne.jp.
³ Department of Radiology, Juntendo University Graduate School of Medicine, Tokyo, Japan.
⁴ Department of Radiological Technology, Kitasato University Kitasato Institute Hospital, Tokyo, Japan.
⁵ Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Tokyo, Japan.

PMID: 36690564
DOI: 10.1016/j.acra.2022.12.040

Abstract

Rationale and objectives: Deep-learning-based super-resolution image reconstruction (DLSRR) is a novel image reconstruction technique that is expected to contribute to improvement in spatial resolution as well as noise reduction through learning from high-resolution computed tomography (CT). This study aims to evaluate image quality obtained with DLSRR and assess its clinical potential.

Materials and methods: CT images of a Mercury CT 4.0 phantom were obtained using a 320-row multi-detector scanner at tube currents of 100, 200, and 300 mA. Image data were reconstructed by filtered back projection (FBP), hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), deep-learning-based image reconstruction (DLR), and DLSRR at image reconstruction strength levels of mild, standard, and strong. Noise power spectrum (NPS), task transfer function (TTF), and detectability index were calculated.

Results: The magnitude of the noise-reducing effect in comparison with FBP was in the order MBIR <HIR <DLR <DLSRR. The resolution property was in the order HIR <FBP <DLR <MBIR <DLSRR. The detectability index was highest for DLSRR. The maximum and mean of the NPS shifted towards lower frequencies for HIR and MBIR compared with FBP, and similar shifts were observed for DLR and DLSRR. For each image reconstruction technique, NPS decreased with increasing reconstruction strength level, but no change was observed in TTF.

Conclusion: The present results suggest that DLSRR can achieve greater noise reduction and improved spatial resolution in the high-contrast region compared with conventional DLR and iterative reconstruction techniques.

Keywords: deep-learning-based super-resolution image reconstruction; detectability index; iterative reconstruction; noise power spectrum; task transfer function.