EUVIMEDEUVIMED entdecken
Crossref

Dual-Domain Pretraining Foundation Model for CT Image Reconstruction

Tao Dai, Yang Lin, Shuying Wang, Mengle Qiu, Changsheng Feng, Hang Guo, Jianhua Ma, Ji He

IEEE Transactions on Radiation and Plasma Medical Sciences · 2026-11 · 10 (8) · 1195-1211

DOI: 10.1109/trpms.2026.3669428 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Radiation and Plasma Medical Sciences, 2026-11. Verfasst von Tao Dai und 7 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) has been widely and successfully used for low-dose CT (LDCT), sparse-view CT (SVCT), and limited-angle CT (LACT) image reconstructions, which aims to decrease X-ray radiation dose during CT scanning. However, most existing DL-based CT image reconstruction methods are typically developed in a task-specific manner and require the prior knowledge of degradation types and levels that can be very complicated in practice, thus limiting their application in real-world clinical scenarios. To address this issue, in this paper, we propose a dual-domain pretraining foundation model (CTPretrain) for multiple low-quality CT reconstruction tasks (i.e., LDCT, SVCT, LACT). Specifically, CTPretrain consists of a sinogram-domain restoration transformer (SRT) and an image-domain restoration transformer (IRT). First, the IRT module was pre-trained through a learnable Gaussian bandpass decomposition module for high/low-frequency separation, mining, and modulation, enabling adaptive weighting of informationrich frequency bands to address diverse degradation types and intensities. By employing a composite low-frequency degradation contrastive loss, positive sample pairs were brought closer while negative pairs were pushed apart in the feature space, thereby enhancing the model’s discriminative capability across degradation patterns. Subsequently, the frozen IRT module’s reconstruction outputs were utilized to effectively compensate for sparse projection data, which served as inputs to the SRT module to stabilize reconstruction performance in the projection domain. Experimental results demonstrate that our CTPretrain surpasses state-of-the-art methods on the hybrid dataset, achieving the capability to address multiple LDCT, SVCT and LACT tasks. Code and models will be available at https://github.com/LinY-ct/CTPretrain.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Dai, T., Lin, Y., Wang, S., Qiu, M., Feng, C., Guo, H., Ma, J., & He, J. (2026). Dual-Domain Pretraining Foundation Model for CT Image Reconstruction. IEEE Transactions on Radiation and Plasma Medical Sciences, 10(8), 1195-1211. https://doi.org/10.1109/trpms.2026.3669428

Vancouver

Dai T, Lin Y, Wang S, Qiu M, Feng C, Guo H, et al. Dual-Domain Pretraining Foundation Model for CT Image Reconstruction. IEEE Transactions on Radiation and Plasma Medical Sciences. 2026;10(8):1195-1211. doi:10.1109/trpms.2026.3669428

BibTeX
@article{Dai2026,
  author = {Dai, Tao and Lin, Yang and Wang, Shuying and Qiu, Mengle and Feng, Changsheng and Guo, Hang and Ma, Jianhua and He, Ji},
  title = {Dual-Domain Pretraining Foundation Model for CT Image Reconstruction},
  journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
  year = {2026},
  volume = {10},
  number = {8},
  pages = {1195--1211},
  doi = {10.1109/trpms.2026.3669428}
}
Kostenlos starten →