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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Gliomas, the most prevalent primary brain tumors, require precisesegmentation for diagnosis and treatment planning. However, this task posessignificant challenges, particularly in the African population, were limitedaccess to high-quality imaging data hampers algorithm performance. In thisstudy, we propose an innovative approach combining the Segment Anything Model(SAM) and a voting network for multi-modal glioma segmentation. By fine-tuningSAM with bounding box-guided prompts (SAMBA), we adapt the model to thecomplexities of African datasets. Our ensemble strategy, utilizing multiplemodalities and views, produces a robust consensus segmentation, addressingintra-tumoral heterogeneity. Although the low quality of scans presentsdifficulties, our methodology has the potential to profoundly impact clinicalpractice in resource-limited settings such as Africa, improving treatmentdecisions and advancing neuro-oncology research. Furthermore, successfulapplication to other brain tumor types and lesions in the future holds promisefor a broader transformation in neurological imaging, improving healthcareoutcomes across all settings. This study was conducted on the Brain TumorSegmentation (BraTS) Challenge Africa (BraTS-Africa) dataset, which provides avaluable resource for addressing challenges specific to resource-limitedsettings, particularly the African population, and facilitating the developmentof effective and more generalizable segmentation algorithms. To illustrate ourapproach's potential, our experiments on the BraTS-Africa dataset yieldedcompelling results, with SAM attaining a Dice coefficient of 86.6 for binarysegmentation and 60.4 for multi-class segmentation.

Towards SAMBA: Segment Anything Model for Brain Tumor Segmentation in Sub-Sharan African Populations