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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Amyotrophic Lateral Sclerosis (ALS) is a complex neurodegenerative disorderinvolving motor neuron degeneration. Significant research has begun toestablish brain magnetic resonance imaging (MRI) as a potential biomarker todiagnose and monitor the state of the disease. Deep learning has turned into aprominent class of machine learning programs in computer vision and has beensuccessfully employed to solve diverse medical image analysis tasks. However,deep learning-based methods applied to neuroimaging have not achieved superiorperformance in ALS patients classification from healthy controls due to havinginsignificant structural changes correlated with pathological features.Therefore, the critical challenge in deep models is to determine usefuldiscriminative features with limited training data. By exploiting thelong-range relationship of image features, this study introduces a frameworknamed SF2Former that leverages vision transformer architecture's power todistinguish the ALS subjects from the control group. To further improve thenetwork's performance, spatial and frequency domain information are combinedbecause MRI scans are captured in the frequency domain before being convertedto the spatial domain. The proposed framework is trained with a set ofconsecutive coronal 2D slices, which uses the pre-trained weights on ImageNetby leveraging transfer learning. Finally, a majority voting scheme has beenemployed to those coronal slices of a particular subject to produce the finalclassification decision. Our proposed architecture has been thoroughly assessedwith multi-modal neuroimaging data using two well-organized versions of theCanadian ALS Neuroimaging Consortium (CALSNIC) multi-center datasets. Theexperimental results demonstrate the superiority of our proposed strategy interms of classification accuracy compared with several popular deeplearning-based techniques.

SF2Former: Amyotrophic Lateral Sclerosis Identification From Multi-center MRI Data Using Spatial and Frequency Fusion Transformer