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

Recent works have shown that the computational efficiency of 3D medical image(e.g. CT and MRI) segmentation can be impressively improved by dynamicinference based on slice-wise complexity. As a pioneering work, a dynamicarchitecture network for medical volumetric segmentation (i.e. Med-DANet) hasachieved a favorable accuracy and efficiency trade-off by dynamically selectinga suitable 2D candidate model from the pre-defined model bank for differentslices. However, the issues of incomplete data analysis, high training costs,and the two-stage pipeline in Med-DANet require further improvement. To thisend, this paper further explores a unified formulation of the dynamic inferenceframework from the perspective of both the data itself and the model structure.For each slice of the input volume, our proposed method dynamically selects animportant foreground region for segmentation based on the policy generated byour Decision Network and Crop Position Network. Besides, we propose to insert astage-wise quantization selector to the employed segmentation model (e.g.U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019and 2020 show that our method achieves comparable or better performance thanprevious state-of-the-art methods with much less model complexity. Comparedwith previous methods Med-DANet and TransBTS with dynamic and staticarchitecture respectively, our framework improves the model efficiency by up tonearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019.

Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation