{"ID":2846370,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.02928","arxiv_id":"2511.02928","title":"Domain-Adaptive Transformer for Data-Efficient Glioma Segmentation in Sub-Saharan MRI","abstract":"Glioma segmentation is critical for diagnosis and treatment planning, yet remains challenging in Sub-Saharan Africa due to limited MRI infrastructure and heterogeneous acquisition protocols that induce severe domain shift. We propose SegFormer3D-plus, a radiomics-guided transformer architecture designed for robust segmentation under domain variability. Our method combines: (1) histogram matching for intensity harmonization across scanners, (2) radiomic feature extraction with PCA-reduced k-means for domain-aware stratified sampling, (3) a dual-pathway encoder with frequency-aware feature extraction and spatial-channel attention, and (4) composite Dice-Cross-Entropy loss for boundary refinement. Pretrained on BraTS 2023 and fine-tuned on BraTS-Africa data, SegFormer3D-plus demonstrates improved tumor subregion delineation and boundary localization across heterogeneous African clinical scans, highlighting the value of radiomics-guided domain adaptation for resource-limited settings.","short_abstract":"Glioma segmentation is critical for diagnosis and treatment planning, yet remains challenging in Sub-Saharan Africa due to limited MRI infrastructure and heterogeneous acquisition protocols that induce severe domain shift. We propose SegFormer3D-plus, a radiomics-guided transformer architecture designed for robust segm...","url_abs":"https://arxiv.org/abs/2511.02928","url_pdf":"https://arxiv.org/pdf/2511.02928v1","authors":"[\"Ilerioluwakiiye Abolade\",\"Aniekan Udo\",\"Augustine Ojo\",\"Abdulbasit Oyetunji\",\"Hammed Ajigbotosho\",\"Aondana Iorumbur\",\"Confidence Raymond\",\"Maruf Adewole\"]","published":"2025-11-04T19:20:55Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}