EUVIMEDScopri EUVIMED
Crossref

Strategies for deep learning‐based attenuation and scatter correction of brain 18 F‐FDG PET images in the image domain

Reza Jahangir, Alireza Kamali-Asl, Hossein Arabi, Habib Zaidi

Medical Physics · 2024

DOI: 10.1002/mp.16914 ↗

At a glance

Journal article in Medical Physics, 2024. Written by Reza Jahangir and 3 co-authors. Institution: Department of Medical Radiation Engineering, Shahid Beheshti University, Tehran, Iran. Major MEDLINE topics: Positron Emission Tomography Computed Tomography, Deep Learning. Cited 18 times so far (Crossref); 44 references. Funded by: Swiss National Science Foundation, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

Attenuation and scatter correction is crucial for quantitative positron emission tomography (PET) imaging. Direct attenuation correction (AC) in the image domain using deep learning approaches has been recently proposed for combined PET/MR and standalone PET modalities lacking transmission scanning devices or anatomical imaging.

Purpose

In this study, different input settings were considered in the model training to investigate deep learning‐based AC in the image space.

Methods

Three different deep learning methods were developed for direct AC in the image space: (i) use of non‐attenuation‐corrected PET images as input (NonAC‐PET), (ii) use of attenuation‐corrected PET images with a simple two‐class AC map (composed of soft‐tissue and background air) obtained from NonAC‐PET images (PET segmentation‐based AC [SegAC‐PET]), and (iii) use of both NonAC‐PET and SegAC‐PET images in a Double‐Channel fashion to predict ground truth attenuation corrected PET images with Computed Tomography images (CTAC‐PET). Since a simple two‐class AC map (generated from NonAC‐PET images) can easily be generated, this work assessed the added value of incorporating SegAC‐PET images into direct AC in the image space. A 4‐fold cross‐validation scheme was adopted to train and evaluate the different models based using 80 brain 18 F‐Fluorodeoxyglucose PET/CT images. The voxel‐wise and region‐wise accuracy of the models were examined via measuring the standardized uptake value (SUV) quantification bias in different regions of the brain.

Results

The overall root mean square error (RMSE) for the Double‐Channel setting was 0.157 ± 0.08 SUV in the whole brain region, while RMSEs of 0.214 ± 0.07 and 0.189 ± 0.14 SUV were observed in NonAC‐PET and SegAC‐PET models, respectively. A mean SUV bias of 0.01 ± 0.26% was achieved by the Double‐Channel model regarding the activity concentration in cerebellum region, as opposed to 0.08 ± 0.28% and 0.05 ± 0.28% SUV biases for the network that uniquely used NonAC‐PET or SegAC‐PET as input, respectively. SegAC‐PET images with an SUV bias of ‐1.15 ± 0.54%, served as a benchmark for clinically accepted errors. In general, the Double‐Channel network, relying on both SegAC‐PET and NonAC‐PET images, outperformed the other AC models.

Conclusion

Since the generation of two‐class AC maps from non‐AC PET images is straightforward, the current study investigated the potential added value of incorporating SegAC‐PET images into a deep learning‐based direct AC approach. Altogether, compared with models that use only NonAC‐PET and SegAC‐PET images, the Double‐Channel deep learning network exhibited superior attenuation correction accuracy.

Subjects

MeSH terms (MEDLINE)

Positron Emission Tomography Computed TomographyDeep LearningFluorodeoxyglucose F18Image Processing, Computer-AssistedMagnetic Resonance ImagingPositron-Emission TomographyBrain

Author keywords

PETattenuation correctiondeep learningquantitative imagingradiomics

Substances

Fluorodeoxyglucose F18

Authors and institutions

  • Department of Medical Radiation Engineering, Shahid Beheshti University, Tehran, Iran.
  • Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
  • Geneva University Neurocenter, Geneva University, Geneva, Switzerland.
  • Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands.
  • Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark.

Funding

  • Swiss National Science Foundation
  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Cite

APA

Jahangir, R., Kamali-Asl, A., Arabi, H., & Zaidi, H. (2024). Strategies for deep learning‐based attenuation and scatter correction of brain 18 F‐FDG PET images in the image domain. Medical Physics. https://doi.org/10.1002/mp.16914

Vancouver

Jahangir R, Kamali-Asl A, Arabi H, Zaidi H. Strategies for deep learning‐based attenuation and scatter correction of brain 18 F‐FDG PET images in the image domain. Medical Physics. 2024. doi:10.1002/mp.16914

BibTeX
@article{Jahangir2024,
  author = {Jahangir, Reza and Kamali-Asl, Alireza and Arabi, Hossein and Zaidi, Habib},
  title = {Strategies for deep learning‐based attenuation and scatter correction of brain 18 F‐FDG PET images in the image domain},
  journal = {Medical Physics},
  year = {2024},
  doi = {10.1002/mp.16914}
}
Start for free →