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

Domain:

healthcare

Record type:

papermodel

Creator:

AboUdoOjoOye

Host:

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. 4 pages, 2 figures. Accepted as an abstract at the Women in Machine Learning (WiML) Workshop at NeurIPS 2025

Visit

arxiv.org

Tasks

computer vision

Resource-Efficient Glioma Segmentation on Sub-Saharan MRI

Gliomas are the most prevalent type of primary brain tumors, and their accurate segmentation from MR

Training Beyond Convergence: Grokking nnU-Net for Glioma Segmentation in Sub-Saharan MRI

Gliomas are placing an increasingly clinical burden on Sub-Saharan Africa (SSA). In the region, the

Generative Style Transfer for MRI Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa

In Sub-Saharan Africa (SSA), the utilization of lower-quality Magnetic Resonance Imaging (MRI) techn

Parameter-efficient Fine-tuning for improved Convolutional Baseline for Brain Tumor Segmentation in Sub-Saharan Africa Adult Glioma Dataset

Automating brain tumor segmentation using deep learning methods is an ongoing challenge in medical i

Adult Glioma Segmentation in Sub-Saharan Africa using Transfer Learning on Stratified Finetuning Data

Gliomas, a kind of brain tumor characterized by high mortality, present substantial diagnostic chall

GENERATIVE STYLE TRANSFER FOR MR IMAGE SEGMENTATION: A CASE OF GLIOMA SEGMENTATION IN SUB-SAHARAN AFRICA

GENERATIVE STYLE TRANSFER FOR MR IMAGE SEGMENTATION: A CASE OF GLIOMA SEGMENTATION IN SUB-SAHARAN AFRICA

Poster presented at the Deep Learning Indaba 2023 by Rancy Chepchirchir