Simultaneous synthesis of perfusion and ventilation images from CT using a dual‐decoder residual attention network for lung disease diagnosis
Journal of Applied Clinical Medical Physics · 2026-03 · 27 (3)
DOI: 10.1002/acm2.70498 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, online erschienen am 26.02.2026. Verfasst von Meng Wang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Medicine, Peking University Third Hospital, Beijing, China. Hauptthemen laut MEDLINE: Lung Diseases, Image Processing, Computer-Assisted, Deep Learning, Tomography, X-Ray Computed. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Beijing Municipal Commission of Science and Technology Collaborative Innovation Project, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Background
Deep learning algorithms can synthesize pulmonary functional images from CT images. However, previous studies have only been able to predict either ventilation or perfusion from CT, limiting the holistic evaluation of lung function.
Purpose
This study aimed to develop a deep learning‐based framework for simultaneously generating lung perfusion and ventilation images from three‐dimensional CT.
Methods
A total of 98 cases who underwent single‐photon emission CT perfusion images (SPECT PI) with 99m Tc‐labeled macroaggregated albumin, ventilation images (VI) with 99m Tc‐Technegas, and three‐dimensional CT images were collected. The three‐dimensional CT and SPECT images were registered and cropped to include only the lung parenchyma. A dual‐decoder residual attention network (DDRAN) was constructed to generate both PI and VI simultaneously from three‐dimensional CT images. For comparative assessment, we additionally employed a conventional single‐decoder residual attention network (RAN) to individually generate PI and VI. The structural similarity index (SSIM) and Spearman's rank correlation coefficient (Rs) were utilized to assess voxel‐wise agreement. Additionally, the Dice similarity coefficient (DSC) was applied to evaluate function‐wise concordance. We used the Wilcoxon signed‐rank test to statistically evaluate the differences between the images synthesized by DDRAN and RAN. Beyond image‐similarity metrics, we evaluated overall model performance using threshold‐based classification. Lastly, a two‐part reader study was conducted: (I) qualitative image acceptability for clinical review, and (II) illustrative diagnostic interpretation based on synthesized image pairs alone.
Results
Overall, DDRAN and RAN achieved comparable performance. The average SSIM values of the DDRAN/RAN model were 0.871/0.866 ( p < 0.05) for PI and 0.830/0.825 ( p < 0.05) for VI, and the Rs values were 0.836/0.819 and 0.732/0.731, respectively. The DDRAN/RAN model achieved average DSC values of 0.795/0.796 for PI and 0.708/0.718 for VI in low‐function regions, and 0.857/0.849 for PI and 0.793/0.793 for VI in high‐function regions. In the two‐part reader study, the synthesized perfusion and ventilation images received almost acceptable scores across all experience levels and demonstrated diagnostic potential.
Conclusions
We have developed a dual‐decoder residual attention network that enables the simultaneous synthesis of lung perfusion and ventilation images from three‐dimensional CT. Preliminary results indicate moderate‐to‐high structural‐wise and functional‐wise concordances, and our proposed model demonstrates comparable accuracy when benchmarked against single‐decoder models. The synthesized perfusion and ventilation images can potentially be used for precise diagnosis and guiding functional lung avoidance radiotherapy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Nuclear Medicine, Peking University Third Hospital, Beijing, China.
- School of Physics, Beihang University, Beijing, China.
- Department of Radiation Oncology, Cancer Center, Peking University Third Hospital, Beijing, China.
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China.
- Peng Huanwu Collaborative Center for Research and Education, Beihang University, Beijing, China.
- Medical Physics Graduate Program, Duke Kunshan University, Kunshan, China.
ORCID-Profile: Xi Liu, Weifang Zhang, Ruijie Yang
Förderung
- National Key R&D Program of China
- Beijing Municipal Commission of Science and Technology Collaborative Innovation Project
- Beijing Natural Science Foundation
- National Natural Science Foundation of China
- Non-Profit Central Research Institute Fund of Chinese Academy of Medical Sciences
- China Medical Health Development Foundation and Key Clinical Project of Peking University Third Hospital
- National Key Research and Development Program of China
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Wang, M., Liu, X., Li, H., Zhao, M., Xiong, T., Huang, D., Cai, J., Zhang, W., Geng, L. S., & Yang, R. (2026). Simultaneous synthesis of perfusion and ventilation images from CT using a dual‐decoder residual attention network for lung disease diagnosis. Journal of Applied Clinical Medical Physics, 27(3). https://doi.org/10.1002/acm2.70498
Vancouver
Wang M, Liu X, Li H, Zhao M, Xiong T, Huang D, et al. Simultaneous synthesis of perfusion and ventilation images from CT using a dual‐decoder residual attention network for lung disease diagnosis. Journal of Applied Clinical Medical Physics. 2026;27(3). doi:10.1002/acm2.70498
BibTeX
@article{Wang2026,
author = {Wang, Meng and Liu, Xi and Li, Haoze and Zhao, Meixin and Xiong, Tianyu and Huang, David and Cai, Jing and Zhang, Weifang and Geng, Li-Sheng and Yang, Ruijie},
title = {Simultaneous synthesis of perfusion and ventilation images from CT using a dual‐decoder residual attention network for lung disease diagnosis},
journal = {Journal of Applied Clinical Medical Physics},
year = {2026},
volume = {27},
number = {3},
doi = {10.1002/acm2.70498}
}
EUVIMED