Journal: Diagnostic and Interventional Imaging

Abbreviation

Publisher

Elsevier

Journal Volumes

ISSN

Description

Filters

2021 - 20222
Reset filters

Search Results

Publications 1 - 2 of 2
  • Impact of dose reduction and iterative reconstruction algorithm on the detectability of pulmonary nodules by artificial intelligence
    Item type: Journal Article
    Schwyzer, Moritz; Messerli, Michael; Eberhard, Matthias; et al. (2022)
    Diagnostic and Interventional Imaging
    Purpose: The purpose of this study was to assess whether the performances of an automated software for lung nodule detection with computed tomography (CT) are affected by radiation dose and the use of iterative reconstruction algorithm. Materials and methods: A chest phantom (Multipurpose Chest Phantom N1; Kyoto Kagaku Co. Ltd, Kyoto, Japan) with 15 pulmonary nodules was scanned with a total of five CT protocol settings with up to 20-fold dose reduction. All CT examinations were reconstructed with iterative reconstruction algorithms ADMIRE 3 and ADMIRE 5 and were then analyzed for the presence of pulmonary nodules with a fully automated computer aided detection software system (InferReadTM CT Lung, Infervision), which is based on deep neural networks. Results: The sensitivity of fully automated pulmonary nodule detection for ground-glass nodules at standard dose CT was greater (70.0%; 14/20; 95% CI: 51.6-88.4%) than at 10-fold and 20-fold dose reduction (30.0%; 6/20; 95% CI: 0.0%-62.5%). There were less false positive findings when ADMIRE 5 reconstruction was used (4.0 ± 2.8 [SD]; range: 2–6) instead of ADMIRE 3 reconstruction (25.0 ± 15.6 [SD]; range: 14–36). There was no difference in the sensitivity of detection of solid and subsolid nodules between standard dose (100%; 95% CI: 100–100%) and 10- and 20-fold reduced dose CT (92.5%; 95% CI: 83.8–100.0%). Image noise was significantly greater with ADMIRE 3 (81 ± 2 [SD] [range: 79–84]; 104 ± 3 [SD] [range: 101–107]; 114 ± 5 [SD] [range: 110–119]; 193 ± 10 [SD] [range: 183-203]; 220 ± 16 [SD] [range: 210–238]) compared to ADMIRE 5 (44 ± 2 [SD] [range: 42–46]; 60 ± 2 [SD] [range: 57–61]; 66 ± 1 [SD] [range: 65–67]; 103 ± 4 [SD] [range: 98–106]; 110 ± 1 [SD] [range: 109–111]), respectively in each of the five CT protocols. Conclusion: This phantom study suggests that dose reduction and iterative reconstruction settings have an impact on detectability of pulmonary nodules by artificial intelligence software and we therefore encourage adaption of dose levels and reconstruction methods prior to widespread implementation of fully automatic nodule detection software for lung cancer screening purposes.
  • T2-weighted Dixon MRI of the spine: A feasibility study of quantitative vertebral bone marrow analysis
    Item type: Journal Article
    Donners, Ricardo; Hirschmann, Anna; Gutzeit, Andreas; et al. (2021)
    Diagnostic and Interventional Imaging
    Purpose To compare the measurements of fat fraction (FF) and in-phase vs. opposed-phase ratio between two-dimensional T2-weighted (T2W) spin-echo (SE) Dixon and three-dimensional (3D) T1-weighted (T1W) volume interpolated breath-hold examination (VIBE) Dixon sequences in malignant vertebral lesions and normal vertebral bone marrow. Materials and methods Thirty patients with focal vertebral malignancies (20 men, mean age, 67.3 ± 9.4 [SD] years; age range: 41–84 years) and 30 patients without malignant spinal disease (11 men, mean age, 70.1 ± 12.9 [SD]; age range: 53–93 years) were retrospectively included. Each patient underwent spine MRI at 1.5 Tesla including T2W SE and T1W VIBE 2-point Dixon sequences. Two readers independently performed 3D-volume of interest (VOI) and region of interest (ROI)-based FF and IO-ratio measurements of malignant lesions and normal vertebrae. Student t-test, Pearson correlation (r) test and two-way mixed model intraclass correlation coefficients (ICC) were used to compare measurements. Results T2W SE and T1W VIBE mean FF and IO-ratio were significantly smaller in malignancy compared to normal marrow, but there were significant differences of paired measurement mean values between T2W SE and T1W VIBE Dixon parameters in malignant lesions T2W SE VOI FF = 9%, T2W SE ROI FF = 7%, T2W SE IO-ratio = 4% vs. T1W VIBE VOI FF = 11%, T1W VIBE ROI FF = 9%, T1W VIBE IO-ratio = −2%, and in normal vertebrae T2W SE VOI FF = 74%, T2W SE ROI FF = 77%, T2W SE IO-ratio = 51% vs. T1W VIBE VOI FF = 67%, T1W VIBE ROI FF = 73%, T1W VIBE IO-ratio = 58% (each P comparing the paired T2W TSE and T1W VIBE parameter, respectively < 0.001). There was excellent positive correlation between T2 W SE and T1 W VIBE-FF (r ≥ 0.99) and VOI and ROI FF measurements for each sequence (r ≥ 0.99). Inter-reader agreement was excellent for all measurements (ICC ≥ 0.94 for all). Conclusion Calculation of T2W SE Dixon derived FF is feasible and gave valid results that help discriminate between malignant vertebral lesions and normal vertebral bone marrow.
Publications 1 - 2 of 2