EUVIMEDEUVIMED entdecken
Crossref

A dual domain reconstruction network for sparse-view spectral CT integrating SSM and cross attention

Qiwei Li iD, Zaifeng Shi iD, Fanning Kong, Yudong Hao, Baijin Song, Bingtao Wen

Journal of X-Ray Science and Technology · 2026-11 · 34 (6) · 750-762

DOI: 10.1177/08953996261476606 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology, online erschienen am 26.08.2026. Verfasst von Qiwei Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Microelectronics, Tianjin University, Tianjin, China. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective Sparse View Computed Tomography (SVCT) is an effective way to reduce radiation dose. However, missing information of projection leads to noise and artifacts. Current SVCT reconstruction networks cannot effectively utilize the correlation information of images from different energies, and linear interpolation in the projection domain brings more secondary artifacts. A dual-domain approach involving data complementation and correction is proposed as a potential solution in this work. Approach We introduce the MHSG-Model for sparse-view spectral CT, designed for integrated processing in both the projection and image domains. This model consists of a Projection Domain Generative Model (PDGM) and an Image Domain Correction Module (IDCM). The PDGM employs a generative model integrated with a selective State Space Model (SSM) to recover missing projection data, reducing secondary artifacts and computational complexity. The IDCM utilizes a novel cross-attention mechanism, incorporating a multi-scale attention for high-energy images and a high-frequency attention for low-energy images, to further enhance reconstruction quality. Main results The MHSG-Model was launched and validated on an abdominal slice simulation dataset and a sparse view spectral CT dataset of the AAPM DL Challenge. The proposed network achieved superior performance metrics, with an RMSE of 0.0111, MAE of 15.91, SSIM of 0.9674, and PSNR of 39.73 dB. The experimental results demonstrate that MHSG-Model has a good performance on preserving detail information and removing artifacts, which show the potential to be applied in clinical sparse view spectral CT reconstruction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedImage Processing, Computer-AssistedAlgorithmsPhantoms, ImagingArtifactsHumans

Stichwörter der Autor:innen

cross attentiondual domaingenerative modelreconstructionsparse-view CT

Autor:innen und Institutionen

  • School of Microelectronics, Tianjin University, Tianjin, China.
  • Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology, Tianjin, China.
  • Department of Orthopaedics, Peking University International Hospital, Beijing, China.

ORCID-Profile: Qiwei Li, Zaifeng Shi

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, Q., Shi, Z., Kong, F., Hao, Y., Song, B., & Wen, B. (2026). A dual domain reconstruction network for sparse-view spectral CT integrating SSM and cross attention. Journal of X-Ray Science and Technology, 34(6), 750-762. https://doi.org/10.1177/08953996261476606

Vancouver

Li Q, Shi Z, Kong F, Hao Y, Song B, Wen B. A dual domain reconstruction network for sparse-view spectral CT integrating SSM and cross attention. Journal of X-Ray Science and Technology. 2026;34(6):750-762. doi:10.1177/08953996261476606

BibTeX
@article{Li2026,
  author = {Li, Qiwei and Shi, Zaifeng and Kong, Fanning and Hao, Yudong and Song, Baijin and Wen, Bingtao},
  title = {A dual domain reconstruction network for sparse-view spectral CT integrating SSM and cross attention},
  journal = {Journal of X-Ray Science and Technology},
  year = {2026},
  volume = {34},
  number = {6},
  pages = {750--762},
  doi = {10.1177/08953996261476606}
}
Kostenlos starten →