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

Algorithmic image-based diagnosis and prognosis of neurodegenerative diseaseson longitudinal data has drawn great interest from computer vision researchers.The current state-of-the-art models for many image classification tasks arebased on the Convolutional Neural Networks (CNN). However, a key challenge inapplying CNN to biological problems is that the available labeled trainingsamples are very limited. Another issue for CNN to be applied in computer aideddiagnosis applications is that to achieve better diagnosis and prognosisaccuracy, one usually has to deal with the longitudinal dataset, i.e., thedataset of images scanned at different time points. Here we argue that anenhanced CNN model with transfer learning for the joint analysis of tasks frommultiple time points or regions of interests may have a potential to improvethe accuracy of computer aided diagnosis. To reach this goal, we innovate a CNNbased deep learning multi-task dictionary learning framework to address theabove challenges. Firstly, we pre-train CNN on the ImageNet dataset andtransfer the knowledge from the pre-trained model to the medical imagingprogression representation, generating the features for different tasks. Then,we propose a novel unsupervised learning method, termed Multi-task StochasticCoordinate Coding (MSCC), for learning different tasks by using shared andindividual dictionaries and generating the sparse features required to predictthe future cognitive clinical scores. We apply our new model in a publiclyavailable neuroimaging cohort to predict clinical measures with two differentfeature sets and compare them with seven other state-of-the-art methods. Theexperimental results show our proposed method achieved superior results.

Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images