First Results of a New Deep Learning Reconstruction Algorithm on Image Quality and Liver Metastasis Conspicuity for Abdominal Low-Dose CT.

Publisher: MDPI AG Country of Publication: Switzerland NLM ID: 101658402 Publication Model: Electronic Cited Medium: Print ISSN: 2075-4418 (Print) Linking ISSN: 20754418 NLM ISO Abbreviation: Diagnostics (Basel) Subsets: PubMed not MEDLINE

Original Publication: Basel, Switzerland : MDPI AG, [2011]-

The study's aim was to assess the impact of a deep learning image reconstruction algorithm (Precise Image; DLR) on image quality and liver metastasis conspicuity compared with an iterative reconstruction algorithm (IR). This retrospective study included all consecutive patients with at least one liver metastasis having been diagnosed between December 2021 and February 2022. Images were reconstructed using level 4 of the IR algorithm (i4) and the Standard/Smooth/Smoother levels of the DLR algorithm. Mean attenuation and standard deviation were measured by placing the ROIs in the fat, muscle, healthy liver, and liver tumor. Two radiologists assessed the image noise and image smoothing, overall image quality, and lesion conspicuity using Likert scales. The study included 30 patients (mean age 70.4 ± 9.8 years, 17 men). The mean CTDI vol was 6.3 ± 2.1 mGy, and the mean dose-length product 314.7 ± 105.7 mGy.cm. Compared with i4, the HU values were similar in the DLR algorithm at all levels for all tissues studied. For each tissue, the image noise significantly decreased with DLR compared with i4 ( p < 0.01) and significantly decreased from Standard to Smooth (-26 ± 10%; p < 0.01) and from Smooth to Smoother (-37 ± 8%; p < 0.01). The subjective image assessment confirmed that the image noise significantly decreased between i4 and DLR ( p < 0.01) and from the Standard to Smoother levels ( p < 0.01), but the opposite occurred for the image smoothing. The highest scores for overall image quality and conspicuity were found for the Smooth and Smoother levels.

Eur Radiol. 2019 Nov;29(11):6163-6171. (PMID: 30976831)
Radiol Artif Intell. 2019 Oct 09;1(6):e180011. (PMID: 33937803)
Eur Radiol. 2020 Jul;30(7):3951-3959. (PMID: 32100091)
BMC Med Res Methodol. 2013 Apr 29;13:61. (PMID: 23627889)
Eur J Radiol. 2020 Dec;133:109349. (PMID: 33152626)
Radiology. 2021 Jan;298(1):180-188. (PMID: 33201790)
Clin Radiol. 2021 Sep;76(9):710.e15-710.e24. (PMID: 33879322)
Med Phys. 2020 Sep;47(9):3961-3971. (PMID: 32506661)
Br J Radiol. 2021 Feb 01;94(1118):20201086. (PMID: 33242256)
Ann Oncol. 2014 Sep;25 Suppl 3:iii1-9. (PMID: 25190710)
Diagn Interv Imaging. 2023 Feb;104(2):76-83. (PMID: 36100524)
AJR Am J Roentgenol. 2020 Mar;214(3):566-573. (PMID: 31967501)
Jpn J Radiol. 2021 Jun;39(6):598-604. (PMID: 33449305)
J Xray Sci Technol. 2021;29(2):361-372. (PMID: 33612538)
Med Phys. 2021 Oct;48(10):5743-5755. (PMID: 34418110)
AJR Am J Roentgenol. 2020 Jul;215(1):50-57. (PMID: 32286872)
Eur Radiol. 2021 May;31(5):3156-3164. (PMID: 33057781)
Eur Radiol. 2021 Jul;31(7):4700-4709. (PMID: 33389036)
Br J Math Stat Psychol. 2008 May;61(Pt 1):29-48. (PMID: 18482474)
Abdom Radiol (NY). 2021 Sep;46(9):4238-4244. (PMID: 33973060)
Diagn Interv Imaging. 2022 Jan;103(1):21-30. (PMID: 34493475)
Eur Radiol. 2020 May;30(5):2493-2501. (PMID: 31792583)
Eur Radiol. 2015 Dec;25(12):3438-54. (PMID: 25994193)
Diagn Interv Imaging. 2018 May;99(5):311-320. (PMID: 29396085)
Med Phys. 2022 Aug;49(8):5052-5063. (PMID: 35696272)
Diagn Interv Imaging. 2021 Jun;102(6):379-387. (PMID: 33714689)
Eur Radiol. 2023 Jan;33(1):699-710. (PMID: 35864348)
Diagn Interv Imaging. 2022 Dec;103(12):571-573. (PMID: 36280585)

Keywords: artificial intelligence; deep learning; image enhancement; liver neoplasms; multidetector computed tomography

Date Created: 20230329 Latest Revision: 20230331

20230331

PMC10047497

10.3390/diagnostics13061182

36980490