Generating synthetic contrast enhancement from non-contrast chest computed tomography using a generative adversarial network.
Researchers
Journal
Modalities
Models
Abstract
This study aimed to evaluate a deep learning model for generating synthetic contrast-enhanced CT (sCECT) from non-contrast chest CT (NCCT). A deep learning model was applied to generate sCECT from NCCT. We collected three separate data sets, the development set (nā=ā25) for model training and tuning, test set 1 (nā=ā25) for technical evaluation, and test set 2 (nā=ā12) for clinical utility evaluation. In test set 1, image similarity metrics were calculated. In test set 2, the lesion contrast-to-noise ratio of the mediastinal lymph nodes was measured, and an observer study was conducted to compare lesion conspicuity. Comparisons were performed using the paired t-test or Wilcoxon signed-rank test. In test set 1, sCECT showed a lower mean absolute error (41.72 vs 48.74; Pā<ā.001), higher peak signal-to-noise ratio (17.44 vs 15.97; Pā<ā.001), higher multiscale structural similarity index measurement (0.84 vs 0.81; Pā<ā.001), and lower learned perceptual image patch similarity metric (0.14 vs 0.15; Pā<ā.001) than NCCT. In test set 2, the contrast-to-noise ratio of the mediastinal lymph nodes was higher in the sCECT group than in the NCCT group (6.15āĀ±ā5.18 vs 0.74āĀ±ā0.69; Pā<ā.001). The observer study showed for all reviewers higher lesion conspicuity in NCCT with sCECT than in NCCT alone (Pāā¤ā.001). Synthetic CECT generated from NCCT improves the depiction of mediastinal lymph nodes.Ā© 2021. The Author(s).