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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Convolutional Neural Networks (CNNs) have exhibited strong performance inmedical image segmentation tasks by capturing high-level (local) information,such as edges and textures. However, due to the limited field of view ofconvolution kernel, it is hard for CNNs to fully represent global information.Recently, transformers have shown good performance for medical imagesegmentation due to their ability to better model long-range dependencies.Nevertheless, transformers struggle to capture high-level spatial features aseffectively as CNNs. A good segmentation model should learn a betterrepresentation from local and global features to be both precise andsemantically accurate. In our previous work, we proposed CATS, which is aU-shaped segmentation network augmented with transformer encoder. In this work,we further extend this model and propose CATS v2 with hybrid encoders.Specifically, hybrid encoders consist of a CNN-based encoder path paralleled toa transformer path with a shifted window, which better leverage both local andglobal information to produce robust 3D medical image segmentation. We fuse theinformation from the convolutional encoder and the transformer at the skipconnections of different resolutions to form the final segmentation. Theproposed method is evaluated on two public challenge datasets: Cross-ModalityDomain Adaptation (CrossMoDA) and task 5 of Medical Segmentation Decathlon(MSD-5), to segment vestibular schwannoma (VS) and prostate, respectively.Compared with the state-of-the-art methods, our approach demonstrates superiorperformance in terms of higher Dice scores.

CATS v2: Hybrid encoders for robust medical segmentation