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

Machine learning models are becoming commonplace in the domain of medicalimaging, and with these methods comes an ever-increasing need for more data.However, to preserve patient anonymity it is frequently impractical orprohibited to transfer protected health information (PHI) between institutions.Additionally, due to the nature of some studies, there may not be a largepublic dataset available on which to train models. To address this conundrum,we analyze the efficacy of transferring the model itself in lieu of databetween different sites. By doing so we accomplish two goals: 1) the modelgains access to training on a larger dataset that it could not normally obtainand 2) the model better generalizes, having trained on data from separatelocations. In this paper, we implement multi-site learning with disparatedatasets from the National Institutes of Health (NIH) and Vanderbilt UniversityMedical Center (VUMC) without compromising PHI. Three neural networks aretrained to convergence on a computed tomography (CT) brain hematomasegmentation task: one only with NIH data,one only with VUMC data, and onemulti-site model alternating between NIH and VUMC data. Resultant lesion maskswith the multi-site model attain an average Dice similarity coefficient of 0.64and the automatically segmented hematoma volumes correlate to those donemanually with a Pearson correlation coefficient of 0.87,corresponding to an 8%and 5% improvement, respectively, over the single-site model counterparts.

Distributed deep learning for robust multi-site segmentation of CT imaging after traumatic brain injury