NAP-CycleGAN: A New Cyclegan-Based CT Images Synthesis Model For Clinical Image Reconstruction Using Brain MR Images
Information Technology and Control · 14.10.2025 · 54 (3) · 937-957
DOI: 10.5755/j01.itc.54.3.38668 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information Technology and Control, online erschienen am 14.10.2025. Verfasst von Li Zhang und 4 weiteren Autor:innen.
Abstract (Originalsprache)
The intricate structure of the brain often necessitates the combined use of magnetic resonance (MR) and computed tomography (CT) imaging for comprehensive diagnostics in clinical care. However, certain patients cannot be exposed to radiation-intensive CT scans, leading to data scarcity and affecting subsequent treatment. In this regard, this paper proposes a new model noise-attention-pix2pix-CycleGAN (NAP-CycleGAN), replacing the generator with pix2pixHD utilizing multi-scale strategies and context-aware modules. By integrating channel attention, the model effectively extracts relevant image features, allowing adaptive weight assignment and handling of long-range dependencies. Additionally, Gaussian noise is introduced to the discriminator to counteract adversarial sample attacks and prevent gradient vanishing. Furthermore, feature matching loss and cycle consistency loss are integrated to reduce image detail distortion. To verify the model validity, it is compared with seven state-of-the-art methods. The experimental results on the public brain dataset brain01 show that the proposed model outperforms these methods, it yields the best, and the synthetic CTs of the proposed model are closest to the original CT (RCT) images.
Zitieren
APA
Zhang, L., Zhu, L., Cao, G., Wang, C., & Qi, Z. (2025). NAP-CycleGAN: A New Cyclegan-Based CT Images Synthesis Model For Clinical Image Reconstruction Using Brain MR Images. Information Technology and Control, 54(3), 937-957. https://doi.org/10.5755/j01.itc.54.3.38668
Vancouver
Zhang L, Zhu L, Cao G, Wang C, Qi Z. NAP-CycleGAN: A New Cyclegan-Based CT Images Synthesis Model For Clinical Image Reconstruction Using Brain MR Images. Information Technology and Control. 2025;54(3):937-957. doi:10.5755/j01.itc.54.3.38668
BibTeX
@article{Zhang2025,
author = {Zhang, Li and Zhu, Lin and Cao, Guorui and Wang, Cancan and Qi, Zhongquan},
title = {NAP-CycleGAN: A New Cyclegan-Based CT Images Synthesis Model For Clinical Image Reconstruction Using Brain MR Images},
journal = {Information Technology and Control},
year = {2025},
volume = {54},
number = {3},
pages = {937--957},
doi = {10.5755/j01.itc.54.3.38668}
}
EUVIMED