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

Positron Emission Tomography (PET) is an imaging method that can assessphysiological function rather than structural disturbances by measuringcerebral perfusion or glucose consumption. However, this imaging techniquerelies on injection of radioactive tracers and is expensive. On the contrary,Arterial Spin Labeling (ASL) MRI is a non-invasive, non-radioactive, andrelatively cheap imaging technique for brain hemodynamic measurements, whichallows quantification to some extent. In this paper we propose a convolutionalneural network (CNN) based model for translating ASL to PET images, which couldbenefit patients as well as the healthcare system in terms of expenses andadverse side effects. However, acquiring a sufficient number of paired ASL-PETscans for training a CNN is prohibitive for many reasons. To tackle thisproblem, we present a new semi-supervised multitask CNN which is trained onboth paired data, i.e. ASL and PET scans, and unpaired data, i.e. only ASLscans, which alleviates the problem of training a network on limited paireddata. Moreover, we present a new residual-based-attention guided mechanism toimprove the contextual features during the training process. Also, we show thatincorporating T1-weighted scans as an input, due to its high resolution andavailability of anatomical information, improves the results. We performed atwo-stage evaluation based on quantitative image metrics by conducting a 7-foldcross validation followed by a double-blind observer study. The proposednetwork achieved structural similarity index measure (SSIM), mean squared error(MSE) and peak signal-to-noise ratio (PSNR) values of $0.85\pm0.08$,$0.01\pm0.01$, and $21.8\pm4.5$ respectively, for translating from 2D ASL andT1-weighted images to PET data. The proposed model is publicly available viahttps://github.com/yousefis/ASL2PET.

ASL to PET Translation by a Semi-supervised Residual-based Attention-guided Convolutional Neural Network