Medical imaging · Domain shift
GLIMS-MedNeXt
Brain tumor segmentation under domain shift
Adapting volumetric segmentation models from high-quality MRI to the imaging conditions represented in BraTS Sub-Saharan Africa.
My contribution
First author · Model development and experimental evaluation
I developed and evaluated an ensemble of GLIMS and MedNeXt, using transfer learning, SSA fine-tuning, and fusion experiments to study segmentation performance under domain shift.
01 / Problem
What needed solving
MRI quality and data availability vary across imaging settings. A model trained on high-quality scans needs evaluation and adaptation before its results can be trusted on a different domain.
02 / Approach
Methods & data
BraTS GLI for pretraining → BraTS SSA for adaptation and evaluation; four MRI modalities.
- Prepare multimodal MRI inputs
- Pretrain and adapt the two segmentation models
- Fuse predictions and evaluate segmentation quality
03 / Outcome
BraTS-Lighthouse 2025 submission
The ensemble work was published in the MICCAI 2025 challenge proceedings in 2026. The paper reports improved accuracy and robustness on BraTS-SSA. See the publication for its full evaluation protocol.
Research evaluation on BraTS data; clinical deployment has not been established. Conformal risk-control experiments are a separate, ongoing research direction.
Read the published evaluationPublication
GLIMS-MedNeXt: An Ensemble Framework for Brain MRI Segmentation in Sub-Saharan Africa
Segmentation, Classification, and Synthesis for Brain Tumors and Traumatic Brain Injuries · 2026