Research
Print page Print page
Switch language
Rigshospitalet - a part of Copenhagen University Hospital
Published

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

Research output: Contribution to journalJournal articleResearchpeer-review

  1. Non-invasive quantification of cerebral glucose metabolism using Gjedde-Patlak plot and image-derived input function from the aorta

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Validation of kinetic modeling of [15O]H2O PET using an image derived input function on hybrid PET/MRI

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. A high-resolution in vivo atlas of the human brain's benzodiazepine binding site of GABAA receptors

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. The structure of the serotonin system: A PET imaging study

    Research output: Contribution to journalJournal articleResearchpeer-review

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

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Automated ictal EEG source imaging: A retrospective, blinded clinical validation study

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Membrane transporters control cerebrospinal fluid formation independently of conventional osmosis to modulate intracranial pressure

    Research output: Contribution to journalJournal articleResearchpeer-review

View graph of relations

PURPOSE: Positron Emission Tomography (PET) can support a diagnosis of neurodegenerative disorder by identifying disease-specific pathologies. Our aim was to investigate the feasibility of using activity reduction in clinical [18F]FE-PE2I and [11C]PiB PET/CT scans, simulating low injected activity or scanning time reduction, in combination with AI-assisted denoising.

METHODS: A total of 162 patients with clinically uncertain Alzheimer's disease underwent amyloid [11C]PiB PET/CT and 509 patients referred for clinically uncertain Parkinson's disease underwent dopamine transporter (DAT) [18F]FE-PE2I PET/CT. Simulated low-activity data were obtained by random sampling of 5% of the events from the list-mode file and a 5% time window extraction in the middle of the scan. A three-dimensional convolutional neural network (CNN) was trained to denoise the resulting PET images for each disease cohort.

RESULTS: Noise reduction of low-activity PET images was successful for both cohorts using 5% of the original activity with improvement in visual quality and all similarity metrics with respect to the ground-truth images. Clinically relevant metrics extracted from the low-activity images deviated <2% compared to ground-truth values, which were not significantly changed when extracting the metrics from the denoised images.

CONCLUSION: The presented models were based on the same network architecture and proved to be a robust tool for denoising brain PET images with two widely different tracer distributions (delocalized, ([11C]PiB, and highly localized, [18F]FE-PE2I). This broad and robust application makes the presented network a good choice for improving the quality of brain images to the level of the standard-activity images without degrading clinical metric extraction. This will allow for reduced dose or scan time in PET/CT to be implemented clinically.

Original languageEnglish
Article number119412
JournalNeuroImage
Volume259
Pages (from-to)119412
ISSN1053-8119
DOIs
Publication statusPublished - 1 Oct 2022

Bibliographical note

Copyright © 2022. Published by Elsevier Inc.

    Research areas

  • Deep Learning, Humans, Nortropanes, Parkinson Disease, Positron Emission Tomography Computed Tomography, Positron-Emission Tomography/methods, Deep learning, [ F]FE-PE2I, Parkinson's disease, PET denoising, [ C]PiB, Alzheimer's disease

ID: 79048744