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

Liver cancer is one of the most common malignant diseases in the world.Segmentation and labeling of liver tumors and blood vessels in CT images canprovide convenience for doctors in liver tumor diagnosis and surgicalintervention. In the past decades, many state-of-the-art medical imagesegmentation algorithms appeared during this period. With the development ofembedded devices, embedded deployment for medical segmentation and automaticreconstruction brings prospects for future automated surgical tasks. Yet, mostof the existing segmentation methods mostly care about the spatial featurecontext and have a perception defect in the semantic relevance of medicalimages, which significantly affects the segmentation accuracy of liver tumorsand blood vessels. Deploying large and complex models into embedded devicesrequires a reasonable trade-off between model accuracy, reasoning speed andmodel capacity. Given these problems, we introduce a multi-scale feature fusionnetwork called TransFusionNet based on Transformer. This network achieved verycompetitive performance for liver vessel and liver tumor segmentation tasks,meanwhile it can improve the recognition of morphologic margins of liver tumorsby exploiting the global information of CT images. Experiments show that invessel segmentation task TransFusionNet achieved mean Dice coefficients of0.899 and in liver tumor segmentation task TransFusionNet achieved mean Dicecoefficients of 0.961. Compared with the state-of-the-art framework, our modelachieves the best segmentation result. In addition, we deployed the model intoan embedded micro-structure and constructed an integrated model for liver tumorvascular segmentation and reconstruction. This proprietary structure will bethe exclusive component of the future medical field.

Exploiting full Resolution Feature Context for Liver Tumor and Vessel  Segmentation via Integrate Framework: Application to Liver Tumor and Vessel  3D Reconstruction under embedded microprocessor