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

A critical challenge for tumour segmentation models is the ability to adapt to diverse clinical settings, particularly when applied to poor-quality neuroimaging data. The uncertainty surrounding this adaptation stems from the lack of representative datasets, leaving top-performing models without exposure to common artifacts found in MRI data throughout Sub-Saharan Africa (SSA). We replicated a framework that secured the 2nd position in the 2022 BraTS competition to investigate the impact of dataset composition on model performance and pursued four distinct approaches through training a model with: 1) BraTS-Africa data only (trainSSA, N=60), 2) BraTS-Adult Glioma data only (trainGLI, N=1251), 3) both datasets together (trainALL, N=1311), and 4) through further training the trainGLI model with BraTS-Africa data (trainftSSA). Notably, training on a smaller low-quality dataset alone (trainSSA) yielded subpar results, and training on a larger high-quality dataset alone (trainGLI) struggled to delineate oedematous tissue in the low-quality validation set. The most promising approach (trainftSSA) involved pre-training a model on high-quality neuroimages and then fine-tuning it on the smaller, low-quality dataset. This approach outperformed the others, ranking second in the MICCAI BraTS Africa global challenge external testing phase. These findings underscore the significance of larger sample sizes and broad exposure to data in improving segmentation performance. Furthermore, we demonstrated that there is potential for improving such models by fine-tuning them with a wider range of data locally.