Domain-Adaptive Transformer for Data-Efficient Glioma Segmentation in Sub-Saharan MRI

TL;DR

This paper introduces SegFormer3D-plus, a novel transformer-based model that improves glioma segmentation in Sub-Saharan MRI by addressing domain shift through radiomics-guided domain adaptation and intensity harmonization.

Contribution

The paper presents a new radiomics-guided transformer architecture with domain-aware sampling and intensity harmonization for robust glioma segmentation in resource-limited settings.

Findings

Enhanced tumor subregion delineation across heterogeneous scans

Improved boundary localization in African clinical MRI data

Effective domain adaptation using radiomics and intensity matching

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.