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

Brain midline shift (MLS) is one of the most critical factors to beconsidered for clinical diagnosis and treatment decision-making forintracranial hemorrhage. Existing computational methods on MLS quantificationnot only require intensive labeling in millimeter-level measurement but alsosuffer from poor performance due to their dependence on specific landmarks orsimplified anatomical assumptions. In this paper, we propose a novelsemi-supervised framework to accurately measure the scale of MLS from head CTscans. We formulate the MLS measurement task as a deformation estimationproblem and solve it using a few MLS slices with sparse labels. Meanwhile, withthe help of diffusion models, we are able to use a great number of unlabeledMLS data and 2793 non-MLS cases for representation learning and regularization.The extracted representation reflects how the image is different from a non-MLSimage and regularization serves an important role in the sparse-to-denserefinement of the deformation field. Our experiment on a real clinical brainhemorrhage dataset has achieved state-of-the-art performance and can generateinterpretable deformation fields.

Diffusion Model based Semi-supervised Learning on Brain Hemorrhage Images for Efficient Midline Shift Quantification