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

The coronavirus disease 2019 (COVID-19) affects billions of lives around theworld and has a significant impact on public healthcare. Due to risingskepticism towards the sensitivity of RT-PCR as screening method, medicalimaging like computed tomography offers great potential as alternative. Forthis reason, automated image segmentation is highly desired as clinicaldecision support for quantitative assessment and disease monitoring. However,publicly available COVID-19 imaging data is limited which leads to overfittingof traditional approaches. To address this problem, we propose an innovativeautomated segmentation pipeline for COVID-19 infected regions, which is able tohandle small datasets by utilization as variant databases. Our method focuseson on-the-fly generation of unique and random image patches for training byperforming several preprocessing methods and exploiting extensive dataaugmentation. For further reduction of the overfitting risk, we implemented astandard 3D U-Net architecture instead of new or computational complex neuralnetwork architectures. Through a 5-fold cross-validation on 20 CT scans ofCOVID-19 patients, we were able to develop a highly accurate as well as robustsegmentation model for lungs and COVID-19 infected regions without overfittingon the limited data. Our method achieved Dice similarity coefficients of 0.956for lungs and 0.761 for infection. We demonstrated that the proposed methodoutperforms related approaches, advances the state-of-the-art for COVID-19segmentation and improves medical image analysis with limited data. The codeand model are available under the following link:https://github.com/frankkramer-lab/covid19.MIScnn

Automated Chest CT Image Segmentation of COVID-19 Lung Infection based on 3D U-Net