English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Current methods for magnetic resonance-based positron emission tomographyattenuation correction (PET-MR AC) are time consuming, and less able thancomputed tomography (CT)-based AC methods to capture inter-individualvariability and skull abnormalities. Deep learning methods have been proposedto produce pseudo-CT from MR images, but these methods have not yet beenevaluated in large clinical cohorts. Methods trained on healthy adult data maynot work in clinical cohorts where skull morphometry may be abnormal, or inpaediatric data where skulls tend to be thinner and smaller. Here, we train aconvolutional neural network based on the U-Net to produce pseudo-CT for PET-MRAC. We trained our network on a mixed cohort of healthy adults and patientsundergoing clinical PET scans for neurology investigations. We show that ourmethod was able to produce pseudo-CT with mean absolute errors (MAE) of 100.4$\pm$ 21.3 HU compared to reference CT, with a Jaccard overlap coefficient of0.73 $\pm$ 0.07 in the skull masks. Linear attenuation maps based on ourpseudo-CT (relative MAE = 8.4 $\pm$ 2.1\%) were more accurate than those basedon a well-performing multi-atlas-based AC method (relative MAE = 13.1 $\pm$1.5\%) when compared with CT-based linear attenuation maps. We refined thetrained network in a clinical paediatric cohort. MAE improved from 174.7 $\pm$33.6 HU when using the existing network to 127.3 $\pm$ 39.9 HU after transferlearning in the paediatric dataset, thus showing that transfer learning canimprove pseudo-CT accuracy in paediatric data.

Brain PET-MR attenuation correction with deep learning: method validation in adult and clinical paediatric data