Deep learning-based reconstruction of virtual monoenergetic images of kVp-switching dual energy CT for evaluation of hypervascular liver lesions: Comparison with standard reconstruction technique

• Published in: European journal of radiology 2022-09, Vol.154, p.110390-110390, Article 110390
• Main Authors: Seo, June Young, Joo, Ijin, Yoon, Jeong Hee, Kang, Hyo Jin, Kim, Sewoo, Kim, Jong Hyo, Ahn, Chulkyun, Lee, Jeong Min
• Format: Article
• Language: English
• Subjects: Deep learning; Dual-energy computed tomography; Image reconstruction; Liver; Noise reduction
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2022.110390

To investigate clinical applicability of deep learning(DL)-based reconstruction of virtual monoenergetic images(VMIs) of arterial phase liver CT obtained by rapid kVp-switching dual-energy CT for evaluation of hypervascular liver lesions. We retrospectively included 109 patients who had available late arterial phase liver CT images of the liver obtained with a rapid switching kVp DECT scanner for suspicious intra-abdominal malignancies. Two VMIs of 70 keV and 40 keV were reconstructed using adaptive statistical iterative reconstruction (ASiR-V) for arterial phase scans. VMIs at 40 keV were additionally reconstructed with a vendor-agnostic DL-based reconstruction technique (ClariCT.AI, ClariPi, DL 40 keV). Qualitative, quantitative image quality and subjective diagnostic acceptability were compared according to reconstruction techniques. In qualitative analysis, DL 40 keV images showed less image noise (4.55 vs 3.11 vs 3.95, p