EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning-aided respiratory motion compensation in PET/CT: addressing motion induced resolution loss, attenuation correction artifacts and PET-CT misalignment

Yihuan Lu, Fei Kang, Duo Zhang, Yue Li, Hao Liu, Chen Sun, Hao Zeng, Lei Shi, Yumo Zhao, Jing Wang

European Journal of Nuclear Medicine and Molecular Imaging · 2024-12 · 52 (1) · 62-73

DOI: 10.1007/s00259-024-06872-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, online erschienen am 13.08.2024. Verfasst von Yihuan Lu und 9 weiteren Autor:innen. Beteiligte Einrichtung: United Imaging Healthcare, No. 2258 Chengbei Road, Shanghai, 201807, China. yihuan.lu@united-imaging.com. Hauptthemen laut MEDLINE: Positron Emission Tomography Computed Tomography, Artifacts, Deep Learning, Respiration. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, STI2030-Major Projects.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Respiratory motion (RM) significantly impacts image quality in thoracoabdominal PET/CT imaging. This study introduces a unified data-driven respiratory motion correction (uRMC) method, utilizing deep learning neural networks, to solve all the major issues caused by RM, i.e., PET resolution loss, attenuation correction artifacts, and PET-CT misalignment.

Methods

In a retrospective study, 737 patients underwent [ 18 F]FDG PET/CT scans using the uMI Panorama PET/CT scanner. Ninety-nine patients, who also had respiration monitoring device (VSM), formed the validation set. The remaining data of the 638 patients were used to train neural networks used in the uRMC. The uRMC primarily consists of three key components: (1) data-driven respiratory signal extraction, (2) attenuation map generation, and (3) PET-CT alignment. SUV metrics were calculated within 906 lesions for three approaches, i.e., data-driven uRMC (proposed), VSM-based uRMC, and OSEM without motion correction (NMC). RM magnitude of major organs were estimated. Results uRMC enhanced diagnostic capabilities by revealing previously undetected lesions, sharpening lesion contours, increasing SUV values, and improving PET-CT alignment. Compared to NMC, uRMC showed increases of 10% and 17% in SUV max and SUV mean across 906 lesions. Sub-group analysis showed significant SUV increases in small and medium-sized lesions with uRMC. Minor differences were found between VSM-based and data-driven uRMC methods, with the SUV max was found statistically marginal significant or insignificant between the two methods. The study observed varied motion amplitudes in major organs, typically ranging from 10 to 20 mm.

Conclusion

A data-driven solution for respiratory motion in PET/CT has been developed, validated and evaluated. To the best of our knowledge, this is the first unified solution that compensates for the motion blur within PET, the attenuation mismatch artifacts caused by PET-CT misalignment, and the misalignment between PET and CT.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Positron Emission Tomography Computed TomographyArtifactsDeep LearningRespirationImage Processing, Computer-AssistedMovementHumansMaleFemaleMiddle AgedRetrospective StudiesAgedFluorodeoxyglucose F18Adult

Stichwörter der Autor:innen

Data-drivenDeep learningPETRespiratory motion correctionuExcel OncoFocusuMI Panorama

Substanzen

Fluorodeoxyglucose F18

Autor:innen und Institutionen

  • United Imaging Healthcare, No. 2258 Chengbei Road, Shanghai, 201807, China. yihuan.lu@united-imaging.com.
  • Department of Nuclear Medicine, Xijing Hospital, Fourth Military Medical University, 127 West Changle Road, Xi'an, 710032, China.
  • United Imaging Healthcare, No. 2258 Chengbei Road, Shanghai, 201807, China.
  • Department of Nuclear Medicine, Xijing Hospital, Fourth Military Medical University, 127 West Changle Road, Xi'an, 710032, China. 13909245902@163.com.

Förderung

  • National Natural Science Foundation of China
  • STI2030-Major Projects

Zitieren

APA

Lu, Y., Kang, F., Zhang, D., Li, Y., Liu, H., Sun, C., Zeng, H., Shi, L., Zhao, Y., & Wang, J. (2024). Deep learning-aided respiratory motion compensation in PET/CT: addressing motion induced resolution loss, attenuation correction artifacts and PET-CT misalignment. European Journal of Nuclear Medicine and Molecular Imaging, 52(1), 62-73. https://doi.org/10.1007/s00259-024-06872-x

Vancouver

Lu Y, Kang F, Zhang D, Li Y, Liu H, Sun C, et al. Deep learning-aided respiratory motion compensation in PET/CT: addressing motion induced resolution loss, attenuation correction artifacts and PET-CT misalignment. European Journal of Nuclear Medicine and Molecular Imaging. 2024;52(1):62-73. doi:10.1007/s00259-024-06872-x

BibTeX
@article{Lu2024,
  author = {Lu, Yihuan and Kang, Fei and Zhang, Duo and Li, Yue and Liu, Hao and Sun, Chen and Zeng, Hao and Shi, Lei and Zhao, Yumo and Wang, Jing},
  title = {Deep learning-aided respiratory motion compensation in PET/CT: addressing motion induced resolution loss, attenuation correction artifacts and PET-CT misalignment},
  journal = {European Journal of Nuclear Medicine and Molecular Imaging},
  year = {2024},
  volume = {52},
  number = {1},
  pages = {62--73},
  doi = {10.1007/s00259-024-06872-x}
}
Kostenlos starten →