Deep-learning denoising for ultrahigh-resolution photon-counting detector CT: phantom and in vivo evaluation of non-calcified coronary plaques.
Authors
Affiliations (15)
Affiliations (15)
- Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, SC, 29425, USA.
- Department of Radiology, LMU University Hospital, LMU Munich, 15 Marchioninistraße, 81377, Munich, Germany.
- Department of Diagnostic and Interventional Radiology, Medical Center, Faculty of Medicine, University of Freiburg, University of Freiburg, 55 Hugstetter Straße, 79106, Freiburg, Germany.
- Department of Diagnostic and Interventional Radiology, University Medical Center of the Johannes Gutenberg-University, 1 Langenbeckstraße, 55131, Mainz, Germany.
- UNICA Radiology, MRI unit Hospital da Luz Lisboa, Católica Medical School, 100 Av. Lusíada, Cardiovascular, Lisboa, 1500-650, CT, Portugal.
- Department of Medicine, UC San Diego School of Medicine, 9500 Gilman Dr, La Jolla, 92093, CA, USA.
- Department of Cardiovascular Division, UC San Diego School of Medicine, 9500 Gilman Dr, La Jolla, 92093, CA, USA.
- Department of Radiology, UC San Diego School of Medicine, 9500 Gilman Dr, La Jolla, 92093, CA, USA.
- Department of Bioengineering, UC San Diego School of Medicine, 9500 Gilman Dr, La Jolla, 92093, CA, USA.
- Department of Cardiology and Radiology, Scripps Clinic, 9888 Genesee Ave, La Jolla, 92037, CA, USA.
- Department of Radiology, Medical Imaging Center, Semmelweis University, 2 Koranyi Sandor street, Budapest, 1083, Hungary.
- Heart and Vascular Centre, Semmelweis University, 68 Varosmajor street, Budapest, 1122, Hungary.
- German Centre for Cardiovascular Research, Partner Site Rhine-Main, 1 Langenbeckstraße, 55131, Mainz, Germany.
- Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, SC, 29425, USA. [email protected].
- Department of Radiology, Medical Imaging Center, Semmelweis University, 2 Koranyi Sandor street, Budapest, 1083, Hungary. [email protected].
Abstract
To assess the value of convolutional neural network (CNN)-based denoising for the evaluation of non-calcified coronary plaques on ultrahigh-resolution (UHR) photon-counting detector (PCD) coronary CT angiography (CCTA). A dynamic phantom containing lipid-rich and fibrotic plaques with 50%-diameter stenosis (PDS) was scanned on PCD-CT under varying conditions. For in-vivo imaging, consecutive patients with non-calcified coronary plaques (NCPs) who underwent CCTA with PCD-CT were included. Image series were reconstructed using a sharp vascular kernel (Bv64) with slice thicknesses of 0.2 mm/0.4 mm, quantum iterative reconstruction (QIR) levels 3/4, and with/without CNN denoising. Phantom-based line-profile analysis yielded edge-width at half maximum (EWHM) and 10-90% rise distance as sharpness metrics. Plaque contrast-to-noise ratio (CNR) and PDS were assessed in the phantom and in patients. Two readers evaluated subjective image quality (noise, diagnostic confidence) using a four-point Likert scale. Pairwise comparisons were performed using a Bonferroni-corrected p < 0.002 for significance. Fifty-five patients (median age 74 [66.5-78] years; 19 women) with 97 NCPs were included. Phantom-based sharpness metrics remained unchanged after denoising (all pairwise p > 0.051). CNN denoising increased plaque CNR consistently in the phantom (fibrotic: 0.80-1.64 to 0.92-2.06; lipid-rich: 0.21-0.34 to 0.35-0.46) and in vivo (0.99-2.07 to 1.37-2.92, all pairwise p < 0.001). Denoising did not alter PDS values in phantom or in vivo plaques (all pairwise p > 0.006). Subjective image noise and diagnostic confidence improved across all reconstructions (all pairwise p < 0.001). CNN-based denoising of UHR PCD-CT improves image quality of non-calcified coronary plaques, while preserving sharpness and quantitative stenosis metrics.