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

A critical challenge for tumour segmentation models is the ability to adaptto diverse clinical settings, particularly when applied to poor-qualityneuroimaging data. The uncertainty surrounding this adaptation stems from thelack of representative datasets, leaving top-performing models without exposureto common artifacts found in MRI data throughout Sub-Saharan Africa (SSA). Wereplicated a framework that secured the 2nd position in the 2022 BraTScompetition to investigate the impact of dataset composition on modelperformance and pursued four distinct approaches through training a model with:1) BraTS-Africa data only (train_SSA, N=60), 2) BraTS-Adult Glioma data only(train_GLI, N=1251), 3) both datasets together (train_ALL, N=1311), and 4)through further training the train_GLI model with BraTS-Africa data(train_ftSSA). Notably, training on a smaller low-quality dataset alone(train_SSA) yielded subpar results, and training on a larger high-qualitydataset alone (train_GLI) struggled to delineate oedematous tissue in thelow-quality validation set. The most promising approach (train_ftSSA) involvedpre-training a model on high-quality neuroimages and then fine-tuning it on thesmaller, low-quality dataset. This approach outperformed the others, rankingsecond in the MICCAI BraTS Africa global challenge external testing phase.These findings underscore the significance of larger sample sizes and broadexposure to data in improving segmentation performance. Furthermore, wedemonstrated that there is potential for improving such models by fine-tuningthem with a wider range of data locally.

Bridging the Gap: Generalising State-of-the-Art U-Net Models to Sub-Saharan African Populations