EUVIMEDEUVIMED entdecken
Open Access

A Deep-Learning–Based Partial-Volume Correction Method for Quantitative 177 Lu SPECT/CT Imaging

Julian Leube, Johan Gustafsson, Michael Lassmann, Maikol Salas-Ramirez, Johannes Tran-Gia

Journal of Nuclear Medicine · 2024-06 · 65 (6) · 980-987

DOI: 10.2967/jnumed.123.266889 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Nuclear Medicine, online erschienen am 18.04.2024. Verfasst von Julian Leube und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany; and leube_j@ukw.de tran_j@ukw.de. Hauptthemen laut MEDLINE: Single Photon Emission Computed Tomography Computed Tomography, Deep Learning, Image Processing, Computer-Assisted, Phantoms, Imaging. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the development of new radiopharmaceutical therapies, quantitative SPECT/CT has progressively emerged as a crucial tool for dosimetry. One major obstacle of SPECT is its poor resolution, which results in blurring of the activity distribution. Especially for small objects, this so-called partial-volume effect limits the accuracy of activity quantification. Numerous methods for partial-volume correction (PVC) have been proposed, but most methods have the disadvantage of assuming a spatially invariant resolution of the imaging system, which does not hold for SPECT. Furthermore, most methods require a segmentation based on anatomic information.

Methods

We introduce DL-PVC, a methodology for PVC of 177Lu SPECT/CT imaging using deep learning (DL). Training was based on a dataset of 10,000 random activity distributions placed in extended cardiac-torso body phantoms. Realistic SPECT acquisitions were created using the SIMIND Monte Carlo simulation program. SPECT reconstructions without and with resolution modeling were performed using the CASToR and STIR reconstruction software, respectively. The pairs of ground-truth activity distributions and simulated SPECT images were used for training various U-Nets. Quantitative analysis of the performance of these U-Nets was based on metrics such as the structural similarity index measure or normalized root-mean-square error, but also on volume activity accuracy, a new metric that describes the fraction of voxels in which the determined activity concentration deviates from the true activity concentration by less than a certain margin. On the basis of this analysis, the optimal parameters for normalization, input size, and network architecture were identified.

Results

Our simulation-based analysis revealed that DL-PVC (0.95/7.8%/35.8% for structural similarity index measure/normalized root-mean-square error/volume activity accuracy) outperforms SPECT without PVC (0.89/10.4%/12.1%) and after iterative Yang PVC (0.94/8.6%/15.1%). Additionally, we validated DL-PVC on 177Lu SPECT/CT measurements of 3-dimensionally printed phantoms of different geometries. Although DL-PVC showed activity recovery similar to that of the iterative Yang method, no segmentation was required. In addition, DL-PVC was able to correct other image artifacts such as Gibbs ringing, making it clearly superior at the voxel level.

Conclusion

In this work, we demonstrate the added value of DL-PVC for quantitative 177Lu SPECT/CT. Our analysis validates the functionality of DL-PVC and paves the way for future deployment on clinical image data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single Photon Emission Computed Tomography Computed TomographyDeep LearningImage Processing, Computer-AssistedPhantoms, ImagingLutetiumRadioisotopesHumansMonte Carlo Method

Stichwörter der Autor:innen

Monte Carlo simulationSPECT/CTdeep learningdosimetryimage processingpartial-volume correction

Substanzen

LutetiumLutetium-177Radioisotopes

Autor:innen und Institutionen

  • Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany; and leube_j@ukw.de tran_j@ukw.de.
  • Medical Radiation Physics, Lund, Lund University, Lund, Sweden.
  • Department of Nuclear Medicine, University Hospital Würzburg, Würzburg, Germany; and.

Zitieren

APA

Leube, J., Gustafsson, J., Lassmann, M., Salas-Ramirez, M., & Tran-Gia, J. (2024). A Deep-Learning–Based Partial-Volume Correction Method for Quantitative 177 Lu SPECT/CT Imaging. Journal of Nuclear Medicine, 65(6), 980-987. https://doi.org/10.2967/jnumed.123.266889

Vancouver

Leube J, Gustafsson J, Lassmann M, Salas-Ramirez M, Tran-Gia J. A Deep-Learning–Based Partial-Volume Correction Method for Quantitative 177 Lu SPECT/CT Imaging. Journal of Nuclear Medicine. 2024;65(6):980-987. doi:10.2967/jnumed.123.266889

BibTeX
@article{Leube2024,
  author = {Leube, Julian and Gustafsson, Johan and Lassmann, Michael and Salas-Ramirez, Maikol and Tran-Gia, Johannes},
  title = {A Deep-Learning–Based Partial-Volume Correction Method for Quantitative 177 Lu SPECT/CT Imaging},
  journal = {Journal of Nuclear Medicine},
  year = {2024},
  volume = {65},
  number = {6},
  pages = {980--987},
  doi = {10.2967/jnumed.123.266889}
}
Kostenlos starten →