Research
Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital
Published

A deep learning-based whole-body solution for PET/MRI attenuation correction

Research output: Contribution to journalJournal articleResearchpeer-review

  1. Aortic valve imaging using 18F-sodium fluoride: impact of triple motion correction

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Feasibility of positron range correction in 82-Rubidium cardiac PET/CT

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Deep learning for Dixon MRI-based attenuation correction in PET/MRI of head and neck cancer patients

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. A Nordic survey of CT doses in hybrid PET/CT and SPECT/CT examinations

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. [(123)I]FP-CIT ENC-DAT normal database: the impact of the reconstruction and quantification methods

    Research output: Contribution to journalJournal articleResearchpeer-review

  1. Deep learning based low-activity PET reconstruction of [11C]PiB and [18F]FE-PE2I in neurodegenerative disorders

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Assessment of Artificial Intelligence Automatic Multiple Sclerosis Lesion Delineation Tool for Clinical Use

    Research output: Contribution to journalJournal articleResearchpeer-review

View graph of relations

BACKGROUND: Deep convolutional neural networks have demonstrated robust and reliable PET attenuation correction (AC) as an alternative to conventional AC methods in integrated PET/MRI systems. However, its whole-body implementation is still challenging due to anatomical variations and the limited MRI field of view. The aim of this study is to investigate a deep learning (DL) method to generate voxel-based synthetic CT (sCT) from Dixon MRI and use it as a whole-body solution for PET AC in a PET/MRI system.

MATERIALS AND METHODS: Fifteen patients underwent PET/CT followed by PET/MRI with whole-body coverage from skull to feet. We performed MRI truncation correction and employed co-registered MRI and CT images for training and leave-one-out cross-validation. The network was pretrained with region-specific images. The accuracy of the AC maps and reconstructed PET images were assessed by performing a voxel-wise analysis and calculating the quantification error in SUV obtained using DL-based sCT (PETsCT) and a vendor-provided atlas-based method (PETAtlas), with the CT-based reconstruction (PETCT) serving as the reference. In addition, region-specific analysis was performed to compare the performances of the methods in brain, lung, liver, spine, pelvic bone, and aorta.

RESULTS: Our DL-based method resulted in better estimates of AC maps with a mean absolute error of 62 HU, compared to 109 HU for the atlas-based method. We found an excellent voxel-by-voxel correlation between PETCT and PETsCT (R2 = 0.98). The absolute percentage difference in PET quantification for the entire image was 6.1% for PETsCT and 11.2% for PETAtlas. The regional analysis showed that the average errors and the variability for PETsCT were lower than PETAtlas in all regions. The largest errors were observed in the lung, while the smallest biases were observed in the brain and liver.

CONCLUSIONS: Experimental results demonstrated that a DL approach for whole-body PET AC in PET/MRI is feasible and allows for more accurate results compared with conventional methods. Further evaluation using a larger training cohort is required for more accurate and robust performance.

Original languageEnglish
Article number55
JournalEJNMMI Physics
Volume9
Issue number1
Pages (from-to)55
ISSN2197-7364
DOIs
Publication statusPublished - 17 Aug 2022

Bibliographical note

© 2022. The Author(s).

ID: 80462259