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

The sharing of medical imaging datasets between institutions, and even insidethe same institution, is limited by various regulations/legal barriers.Although these limitations are necessities for protecting patient privacy andsetting strict boundaries for data ownership, medical research projects thatrequire large datasets suffer considerably as a result. Machine learning hasbeen revolutionized with the emerging deep neural network approaches overrecent years, making the data-related limitations even a larger problem asthese novel techniques commonly require immense imaging datasets. This paperintroduces constrained Generative Adversarial Network ensembles (cGANe) toaddress this problem by altering the representation of the imaging data,whereas containing the significant information, enabling the reproduction ofsimilar research results elsewhere with the sharable data. Accordingly, aframework representing the generation of a cGANe is described, and the approachis validated for the generation of synthetic 3D brain metastatic region datafrom T1-weighted contrast-enhanced MRI studies. For 90% brain metastases (BM)detection sensitivity, our previously reported detection algorithm produced onaverage 9.12 false-positive BM detections per patient after training with theoriginal data, whereas producing 9.53 false-positives after training with thecGANe generated synthetic data. Although the applicability of the introducedapproach needs further validation studies with a range of medical imaging datatypes, the results suggest that the BM-detection algorithm can achievecomparable performance by using cGANe generated synthetic data. Hence, thegeneralization of the proposed approach for various modalities may occur in thenear future.

Constrained Generative Adversarial Network Ensembles for Sharable Synthetic Data Generation