Domain-Adaptive Transformer for Data-Efficient Glioma Segmentation in Sub-Saharan MRI
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908629413658624 |
|---|---|
| author | Abolade, Ilerioluwakiiye Udo, Aniekan Ojo, Augustine Oyetunji, Abdulbasit Ajigbotosho, Hammed Iorumbur, Aondana Raymond, Confidence Adewole, Maruf |
| author_facet | Abolade, Ilerioluwakiiye Udo, Aniekan Ojo, Augustine Oyetunji, Abdulbasit Ajigbotosho, Hammed Iorumbur, Aondana Raymond, Confidence Adewole, Maruf |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02928 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Domain-Adaptive Transformer for Data-Efficient Glioma Segmentation in Sub-Saharan MRI Abolade, Ilerioluwakiiye Udo, Aniekan Ojo, Augustine Oyetunji, Abdulbasit Ajigbotosho, Hammed Iorumbur, Aondana Raymond, Confidence Adewole, Maruf Image and Video Processing Computer Vision and Pattern Recognition I.2.10; I.4.8; J.3 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. |
| title | Domain-Adaptive Transformer for Data-Efficient Glioma Segmentation in Sub-Saharan MRI |
| topic | Image and Video Processing Computer Vision and Pattern Recognition I.2.10; I.4.8; J.3 |
| url | https://arxiv.org/abs/2511.02928 |