EUVIMEDEUVIMED entdecken
Crossref

The Impact of Deep Learning Reconstruction Algorithm Combined with Ultra-high Resolution Detector on Orbital CT Image Quality

Yiang ZHAO, Yuhe CHENG, Zixuan MA, Yongxian ZHANG, Dandan LIU

CT Lilun yu yingyong yanjiu · 2026-01 · 35 (1) · 80-85

DOI: 10.15953/j.ctta.2025.282 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CT Lilun yu yingyong yanjiu, 2026-01. Verfasst von Yiang ZHAO und 4 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

This study investigates the effect of a 0.3125 mm ultra-high-resolution detector combined with a ClearInfinity (CI) deep-learning reconstruction algorithm on the image quality of orbital computed tomography (CT).

Methods

Scans were performed using a NeuViz Epoch Elite CT scanner on a Catphan 600 phantom and three 7-year-old rhesus monkeys. The collimation widths were set to 64 mm×0.625 mm and 128 mm×0.3125 mm. Images were acquired using filtered back projection (FBP), 60% adaptive iterative reconstruction algorithm ClearView (CV), and 60% deep learning reconstruction algorithm CI. Image quality was evaluated using objective indicators such as the modulation transfer function (MTF) and contrast-to-noise ratio (CNR), as well as using double-blind subjective scoring. Additionally, statistical analyses were performed.

Results

In phantom experiments, under standard and bone algorithms, images with a collimation width of 128×0.3125 mm showed significantly better performances in terms of MTF50%, MTF10%, and some CNR indicators compared with those with a collimation width of 64×0.625 mm. The CNR of the CI algorithm was significantly higher than those of the FBP and CV algorithms. In animal experiments, the CNR of the medial rectus in images with a 128×0.3125 mm collimation width was significantly higher than that in images with a 64×0.625 mm collimation width. The CI algorithm achieved the optimal CNR for the medial rectus and eyeball, as well as the highest subjective scores, with good consistency between two radiologists’ subjective scores (Kappa≥0.75).

Conclusion

The 0.3125 mm ultra-high-resolution detector combined with the CI deep-learning algorithm significantly improved the resolution and contrast of orbital CT images as well as reduced noise and artifacts, thereby demonstrating promising clinical-application prospects.

Schlagwörter

ultra-high-resolution detectordeep learning reconstruction algorithmorbital ct

Zitieren

APA

ZHAO, Y., CHENG, Y., MA, Z., ZHANG, Y., & LIU, D. (2026). The Impact of Deep Learning Reconstruction Algorithm Combined with Ultra-high Resolution Detector on Orbital CT Image Quality. CT Lilun yu yingyong yanjiu, 35(1), 80-85. https://doi.org/10.15953/j.ctta.2025.282

Vancouver

ZHAO Y, CHENG Y, MA Z, ZHANG Y, LIU D. The Impact of Deep Learning Reconstruction Algorithm Combined with Ultra-high Resolution Detector on Orbital CT Image Quality. CT Lilun yu yingyong yanjiu. 2026;35(1):80-85. doi:10.15953/j.ctta.2025.282

BibTeX
@article{ZHAO2026,
  author = {ZHAO, Yiang and CHENG, Yuhe and MA, Zixuan and ZHANG, Yongxian and LIU, Dandan},
  title = {The Impact of Deep Learning Reconstruction Algorithm Combined with Ultra-high Resolution Detector on Orbital CT Image Quality},
  journal = {CT Lilun yu yingyong yanjiu},
  year = {2026},
  volume = {35},
  number = {1},
  pages = {80--85},
  doi = {10.15953/j.ctta.2025.282}
}
Kostenlos starten →