Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 12, 2025Journal of Computer Assisted Tomography

Image Quality Assessment of Deep Learning-Based Virtual Monoenergetic Images From Single-Energy CT Pulmonary Angiography

View Full Paper
Ask AI
Bookmark
Share

Authors

KLKe LiPNPrashant NagpalBMBrian F. Mullan

Discussion

Loading...

Member takes

Overview

Retrospective assessment demonstrates improved image quality and vessel opacification in DL-generated images from single-energy CT, suggesting effective clinical use.

Key Points

  • This research aims to evaluate the image quality of deep learning-based virtual monoenergetic images generated from single-energy CT for pulmonary angiography.
  • Retrospective study of 52 sets of SECT pulmonary angiography images
  • DL-based estimation of material basis images using a pretrained model
  • Evaluation by two blinded thoracic radiologists using 5-point Likert scales
  • Objective quality assessed through vessel contrast and contrast-to-noise ratio
  • Statistical analysis with paired t tests and Mann-Whitney U tests.
  • DL-VME images scored significantly higher in subjective image quality and vessel opacification compared to SECT (P ≤0.008)
  • DL-VME showed enhanced average contrast for emboli (1085 vs. 331 HU, P < 0.001)
  • CNR improved in DL-VME images (17.8 vs. 11.1, P < 0.001)
  • No significant VME performance variation across patient sex, scanner model, and radiation dose
  • Vessel opacification scores related to patient weight, with DL-VME providing better results for all weight categories.

Cite This Study

Li et al. (2025) studied this question.

synapsesocial.com/papers/694019192d562116f28f6540https://doi.org/10.1097/rct.0000000000001812
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Enhanced visualization in endoleak detection through iterative and AI-noise optimized spectral reconstructions2024 · 8 citations
  2. 2Deep learning models for pulmonary embolism segmentation on dual-energy CT: performance analysis and image quality correlation2026
  3. 3Clinical feasibility and image quality assessment of deep learning-based virtual contrast enhancement from photon-counting computed tomography2026
  4. 4Comparison of image quality in carotid dual-energy computed tomography angiography at 55 keV virtual monoenergetic imaging using deep learning and adaptive iterative reconstruction algorithm2025
  5. 5Dual-energy CT-based virtual monoenergetic imaging via unsupervised learning2024