PMID- 35195431 OWN - NLM STAT- MEDLINE DCOM- 20220726 LR - 20220912 IS - 1546-3141 (Electronic) IS - 0361-803X (Linking) VI - 219 IP - 2 DP - 2022 Aug TI - Radiation Dose Reduction for 80-kVp Pediatric CT Using Deep Learning-Based Reconstruction: A Clinical and Phantom Study. PG - 315-324 LID - 10.2214/AJR.21.27255 [doi] AB - BACKGROUND. Deep learning-based reconstruction (DLR) may facilitate CT radiation dose reduction, but a paucity of literature has compared lower-dose DLR images with standard-dose iterative reconstruction (IR) images or explored application of DLR to low-tube-voltage scanning in children. OBJECTIVE. The purpose of this study was to assess whether DLR can be used to reduce radiation dose while maintaining diagnostic image quality in comparison with hybrid IR (HIR) and model-based IR (MBIR) for low-tube-voltage pediatric CT. METHODS. This retrospective study included children 6 years old or younger who underwent contrast-enhanced 80-kVp CT with a standard-dose or lower-dose protocol. Standard images were reconstructed with HIR, and lower-dose images were reconstructed with HIR, MBIR, and DLR. Size-specific dose estimate (SSDE) was calculated for both protocols. Image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were quantified. Two radiologists independently evaluated noise magnitude, noise texture, streak artifact, edge sharpness, and overall quality. Interreader agreement was assessed, and mean values were calculated. To evaluate task-based object detection performance, a phantom was imaged with 80-kVp CT at six doses (SSDE, 0.6-5.3 mGy). Detectability index (d') was calculated from the noise power spectrum and task-based transfer function. Reconstruction methods were compared. RESULTS. Sixty-five children (mean age, 25.0 +/- 25.2 months) who underwent CT with standard- (n = 31) or lower-dose (n = 34) protocol were included. SSDE was 54% lower for the lower-dose than for the standard-dose group (1.9 +/- 0.4 vs 4.1 +/- 0.8 mGy). Lower-dose DLR and MBIR yielded lower image noise and higher SNR and CNR than standard-dose HIR (p < .05). Interobserver agreement on subjective features ranged from a kappa coefficient of 0.68 to 0.78. The readers subjectively scored noise texture, edge sharpness, and overall quality lower for lower-dose MBIR than for standard-dose HIR (p < .001), though higher for lower-dose DLR than for standard-dose HIR (p < .001). In the phantom, DLR provided higher d' than HIR and MBIR at each dose. Object detectability was greater for 2.0-mGy DLR than for 4.0-mGy HIR for low-contrast (3.67 vs 3.57) and high-contrast (1.20 vs 1.04) objects. CONCLUSION. Compared with IR algorithms, DLR results in substantial dose reduction with preserved or even improved image quality for low-tube-voltage pediatric CT. CLINICAL IMPACT. Use of DLR at 80 kVp allows greater dose reduction for pediatric CT than do current IR techniques. FAU - Nagayama, Yasunori AU - Nagayama Y AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. FAU - Goto, Makoto AU - Goto M AD - Department of Central Radiology, Kumamoto University Hospital, Kumamoto, Japan. FAU - Sakabe, Daisuke AU - Sakabe D AD - Department of Central Radiology, Kumamoto University Hospital, Kumamoto, Japan. FAU - Emoto, Takafumi AU - Emoto T AD - Department of Central Radiology, Kumamoto University Hospital, Kumamoto, Japan. FAU - Shigematsu, Shinsuke AU - Shigematsu S AD - Department of Central Radiology, Kumamoto University Hospital, Kumamoto, Japan. FAU - Oda, Seitaro AU - Oda S AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. FAU - Tanoue, Shota AU - Tanoue S AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. FAU - Kidoh, Masafumi AU - Kidoh M AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. FAU - Nakaura, Takeshi AU - Nakaura T AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. FAU - Funama, Yoshinori AU - Funama Y AD - Department of Medical Radiation Sciences, Faculty of Life Sciences, Kumamoto University, Kumamoto, Japan. FAU - Uchimura, Ryutaro AU - Uchimura R AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. FAU - Takada, Sentaro AU - Takada S AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. FAU - Hayashi, Hidetaka AU - Hayashi H AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. FAU - Hatemura, Masahiro AU - Hatemura M AD - Department of Central Radiology, Kumamoto University Hospital, Kumamoto, Japan. FAU - Hirai, Toshinori AU - Hirai T AD - Department of Diagnostic Radiology, Graduate School of Medical Sciences, Kumamoto University, 1-1-1, Honjo, Chuo-ku, Kumamoto 860-8556, Japan. LA - eng PT - Journal Article DEP - 20220223 PL - United States TA - AJR Am J Roentgenol JT - AJR. American journal of roentgenology JID - 7708173 SB - IM CIN - AJR Am J Roentgenol. 2022 Mar 9;:. PMID: 35261283 MH - Algorithms MH - Child MH - Child, Preschool MH - *Deep Learning MH - Drug Tapering MH - Humans MH - Radiation Dosage MH - *Radiographic Image Interpretation, Computer-Assisted/methods MH - Retrospective Studies MH - Tomography, X-Ray Computed/methods OTO - NOTNLM OT - CT OT - deep learning OT - image reconstruction OT - low peak kilovoltage OT - pediatric EDAT- 2022/02/24 06:00 MHDA- 2022/07/27 06:00 CRDT- 2022/02/23 12:19 PHST- 2022/02/24 06:00 [pubmed] PHST- 2022/07/27 06:00 [medline] PHST- 2022/02/23 12:19 [entrez] AID - 10.2214/AJR.21.27255 [doi] PST - ppublish SO - AJR Am J Roentgenol. 2022 Aug;219(2):315-324. doi: 10.2214/AJR.21.27255. Epub 2022 Feb 23.