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

Freezing of gait (FOG) is a common and debilitating gait impairment inParkinson's disease. Further insight into this phenomenon is hampered by thedifficulty to objectively assess FOG. To meet this clinical need, this paperproposes an automated motion-capture-based FOG assessment method driven by anovel deep neural network. Automated FOG assessment can be formulated as anaction segmentation problem, where temporal models are tasked to recognize andtemporally localize the FOG segments in untrimmed motion capture trials. Thispaper takes a closer look at the performance of state-of-the-art actionsegmentation models when tasked to automatically assess FOG. Furthermore, anovel deep neural network architecture is proposed that aims to better capturethe spatial and temporal dependencies than the state-of-the-art baselines. Theproposed network, termed multi-stage spatial-temporal graph convolutionalnetwork (MS-GCN), combines the spatial-temporal graph convolutional network(ST-GCN) and the multi-stage temporal convolutional network (MS-TCN). TheST-GCN captures the hierarchical spatial-temporal motion among the jointsinherent to motion capture, while the multi-stage component reducesover-segmentation errors by refining the predictions over multiple stages. Theexperiments indicate that the proposed model outperforms four state-of-the-artbaselines. Moreover, FOG outcomes derived from MS-GCN predictions had anexcellent (r=0.93 [0.87, 0.97]) and moderately strong (r=0.75 [0.55, 0.87])linear relationship with FOG outcomes derived from manual annotations. Theproposed MS-GCN may provide an automated and objective alternative tolabor-intensive clinician-based FOG assessment. Future work is now possiblethat aims to assess the generalization of MS-GCN to a larger and more variedverification cohort.

Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks