InspirationOnly: synthesizing expiratory CT from inspiratory CT to estimate parametric response map
Medical & Biological Engineering & Computing · 2025
DOI: 10.1007/s11517-025-03322-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2025. Verfasst von Tiande Zhang und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Pulmonary Disease, Chronic Obstructive, Inhalation, Exhalation. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Chronic obstructive pulmonary disease (COPD) is a highly heterogeneous disease with various phenotypes. Registered inspiratory and expiratory CT images can generate the parametric response map (PRM) that characterizes phenotypes' spatial distribution and proportions. However, increased radiation dosage, scan time, quality control, and patient cooperation requirements limit the utility of PRM. This study aims to synthesize a PRM using only inspiratory CT scans. First, a CycleGAN with perceptual loss and a multiscale discriminator (MPCycleGAN) is proposed and trained to synthesize registered expiratory CT images from inspiratory images. Next, a strategy named InspirationOnly is introduced, where synthesized images replace actual expiratory CT images. The image synthesizer outperformed state-of-the-art models, achieving a mean absolute error of 105.66 ± 36.64 HU, a peak signal-to-noise ratio of 21.43 ± 1.87 dB, and a structural similarity of 0.84 ± 0.02. The intraclass correlation coefficients of emphysema, fSAD, and normal proportions between the InspirationOnly and ground truth were 0.995, 0.829, and 0.914, respectively. The proposed MPCycleGAN enables the InspirationOnly strategy to yield PRM using only inspiratory CT. The estimated COPD phenotypes are consistent with those from dual-phase CT and correlated with the spirometry parameters. This offers a potential tool for characterizing phenotypes of COPD, particularly when expiratory CT images are unavailable.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China.
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China.
- School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing, China.
- State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The National Center for Respiratory Medicine, The First Affiliated Hospi…
- Respiratory Department, Central Hospital Affiliated to Shenyang Medical College, Shenyang, China.
- Department of Radiology, The First Affiliated Hospital of Xi'an Jiao Tong University, Xi'an, China.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Zhang, T., Pang, H., Wu, Y., Xu, J., Liang, Z., Xia, S., Jin, C., Chen, R., & Qi, S. (2025). InspirationOnly: synthesizing expiratory CT from inspiratory CT to estimate parametric response map. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-025-03322-0
Vancouver
Zhang T, Pang H, Wu Y, Xu J, Liang Z, Xia S, et al. InspirationOnly: synthesizing expiratory CT from inspiratory CT to estimate parametric response map. Medical & Biological Engineering & Computing. 2025. doi:10.1007/s11517-025-03322-0
BibTeX
@article{Zhang2025,
author = {Zhang, Tiande and Pang, Haowen and Wu, Yanan and Xu, Jiaxuan and Liang, Zhenyu and Xia, Shuyue and Jin, Chenwang and Chen, Rongchang and Qi, Shouliang},
title = {InspirationOnly: synthesizing expiratory CT from inspiratory CT to estimate parametric response map},
journal = {Medical & Biological Engineering & Computing},
year = {2025},
doi = {10.1007/s11517-025-03322-0}
}
EUVIMED