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

Deep learning has great potential for accurate detection and classificationof diseases with medical imaging data, but the performance is often limited bythe number of training datasets and memory requirements. In addition, many deeplearning models are considered a "black-box," thereby often limiting theiradoption in clinical applications. To address this, we present a successivesubspace learning model, termed VoxelHop, for accurate classification ofAmyotrophic Lateral Sclerosis (ALS) using T2-weighted structural MRI data.Compared with popular convolutional neural network (CNN) architectures,VoxelHop has modular and transparent structures with fewer parameters withoutany backpropagation, so it is well-suited to small dataset size and 3D imagingdata. Our VoxelHop has four key components, including (1) sequential expansionof near-to-far neighborhood for multi-channel 3D data; (2) subspaceapproximation for unsupervised dimension reduction; (3) label-assistedregression for supervised dimension reduction; and (4) concatenation offeatures and classification between controls and patients. Our experimentalresults demonstrate that our framework using a total of 20 controls and 26patients achieves an accuracy of 93.48$\%$ and an AUC score of 0.9394 indifferentiating patients from controls, even with a relatively small number ofdatasets, showing its robustness and effectiveness. Our thorough evaluationsalso show its validity and superiority to the state-of-the-art 3D CNNclassification methods. Our framework can easily be generalized to otherclassification tasks using different imaging modalities.

VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI