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

Neuroimaging is essential in brain studies for the diagnosis andidentification of disease, structure, and function of the brain in its healthyand disease states. Literature shows that there are advantages of multitaskingwith some deep learning (DL) schemes in challenging neuroimaging applications.This study examines the feasibility of using multitasking in three differentapplications, including tissue segmentation, cross-modality conversion, andbias-field correction. These applications reflect five different scenarios inwhich multitasking is explored and 280 training and testing sessions conductedfor empirical evaluations. Two well-known networks, U-Net as a well-knownconvolutional neural network architecture, and a closed architecture based onthe conditional generative adversarial network are implemented. Differentmetrics such as the normalized cross-correlation coefficient and Dice scoresare used for comparison of methods and results of the different experiments.Statistical analysis is also provided by paired t-test. The present studyexplores the pros and cons of these methods and their practical impacts onmultitasking in different implementation scenarios. This investigation showsthat bias correction and cross-modality conversion applications aresignificantly easier than the segmentation application, and having multitaskingwith segmentation is not reasonable if one of them is identified as the maintarget application. However, when the main application is the segmentation oftissues, multitasking with cross-modality conversion is beneficial, especiallyfor the U-net architecture.

Feasibility Assessment of Multitasking in MRI Neuroimaging Analysis: Tissue Segmentation, Cross-Modality Conversion and Bias correction