Deep Learning for Computed Tomography Image Super-Resolution: A Review
Advances in Engineering Technology Research · 30.06.2026 · 17 (1) · 757
DOI: 10.56028/aetr.17.1.757.2026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Engineering Technology Research, online erschienen am 30.06.2026. Verfasst von Yimeng Yang.
Abstract (Originalsprache)
Computational tomography (CT) imaging technology has become a core tool for clinical diagnosis and disease surveillance due to its fast scanning ability, high tissue contrast and clear presentation of three-dimensional structures. However, the limitations of scanning dose, duration and hardware in CT imaging technology restrict the improvement of imaging resolution [1] [2]. Deep learning super resolution (SR) algorithms can reconstruct high-resolution images from low-dose, low-sampling CT without hardware modification of existing equipment, which makes it a key means to break through the above technical bottlenecks. In addition to systematically reviewing the progress in this field, this paper not only proposes a new classification framework that considers the integration of network architecture design, learning paradigm selection and physical priors, but also compares and analyzes the advantages and limitations of supervision, self-supervision and model-driven methods in low-dose, fast scanning and other scenarios. Moreover, this paper explores core challenges such as data scarcity, physical consistency constraints, model interpretability and clinical generalization capabilities to provide a roadmap for subsequent research.
Zitieren
APA
Yang, Y. (2026). Deep Learning for Computed Tomography Image Super-Resolution: A Review. Advances in Engineering Technology Research, 17(1), 757. https://doi.org/10.56028/aetr.17.1.757.2026
Vancouver
Yang Y. Deep Learning for Computed Tomography Image Super-Resolution: A Review. Advances in Engineering Technology Research. 2026;17(1):757. doi:10.56028/aetr.17.1.757.2026
BibTeX
@article{Yang2026,
author = {Yang, Yimeng},
title = {Deep Learning for Computed Tomography Image Super-Resolution: A Review},
journal = {Advances in Engineering Technology Research},
year = {2026},
volume = {17},
number = {1},
pages = {757},
doi = {10.56028/aetr.17.1.757.2026}
}
EUVIMED