Back to all papers

Deep Learning-Based Image Reconstruction in Ultra-High-Resolution CT Venography for Improved Visualization of Cerebral Venous Drainage.

September 23, 2026pubmed logopapers

Authors

Steinmetz S,Grebe AW,Kondova M,Abello Mercado MA,Sanner AP,Kronfeld A,Müller L,Jorg T,Hahn M,Uphaus T,Brockmann MA,Othman AE

Affiliations (2)

  • Department of Neuroradiology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany. [email protected].
  • Department of Neuroradiology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany.

Abstract

To evaluate the diagnostic confidence and image quality of deep-learning-enhanced ultra-high-resolution CT venography (CTV) in venous neurovascular imaging, compared with hybrid iterative reconstruction of ultra-high-resolution CT datasets and normal-resolution CTV. This retrospective, single-center study included 31 consecutive patients with suspected cerebral venous and dural sinus thrombosis who underwent CTV. CTV datasets were reconstructed using hybrid iterative reconstruction with (i) Normal-Resolution CTV (NR-CTV), (ii) an Ultra-High-Resolution CTV (UHR-CTV), and (iii) a deep learning algorithm specifically trained for neurovascular imaging, applied to the UHR-CTV datasets (DL-UHR-CTV). Quantitative analyses included signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and frequency power spectra (FPS). Qualitative evaluation of image quality, contrast, noise, artifacts, diagnostic confidence, and assessability of dural sinuses and intracranial veins was performed by three radiologists using a 4-point Likert scale. A descriptive analysis assessed concordant detection of venous pathologies across reconstructions. SNR and CNR in DL-UHR-CTV were significantly higher than in UHR-CTV (SNR: p = 0.02; CNR: p = 0.01). NR-CTV and DL-UHR-CTV were similar. Compared to NR-CTV and UHR-CTV, DL-UHR-CTV showed a significantly lower FPS amplitude across wide frequency ranges. In qualitative analysis, DL-UHR-CTV outperformed UHR-CTV in all parameters (p < 0.001) except vessel contrast (p = 0.09) and was better than NR-CTV in all categories (p < 0.001). All 20 venous pathologies (12 patients) were detected on all three reconstructions without false-positive findings. Deep-learning-based reconstruction significantly enhances image quality and venous visualization in ultra-high-resolution CT venography compared with conventional iterative reconstruction, enabling detailed depiction of small venous structures.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.