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

Computed tomography is an important method for clinical evaluation of the disease status and the therapeutic efficacy of hepatocellular carcinoma (HCC). In order to effectively reduce the workload of artificial segmentation of CT images and to minimize the obvious influence of subjective factors upon the result, a segmentation algorithm based on the improved U-net network and region growing was proposed. Median filtering and adaptive histogram equalization were performed firstly on abdominal CT images with HCC, secondly the CT images were trained by the improved U-net network in which residual structure and deep separable convolutions layer were used, and then region growing was used for capturing edges of CT images. 126 groups of target CT images were selected for analysis, which were divided into training set, verification set and test set according to the ratio of 8: 1: 1, of which the training set was expanded to 800 by image enhancement technology. By comparing the lesion regions extracted with handled consequences manually labelled by clinicians, the sensitivity reached 83.18%, the accuracy 85.25%, and the Dice coefficient 83.05%. The algorithm revealed a good result on the segmentation of CT image with HCC, and could provide support for the evaluation of the treatment efficacy of HCC.

Design of the Segmentation Algorithm of HCC Based on the Improved U-net Network