Topology-Driven Fusion of nnU-Net and MedNeXt for Accurate Brain Tumor Segmentation on Sub-Saharan Africa Dataset

TL;DR

This paper presents a topology-driven fusion approach combining nnU-Net and MedNeXt, enhanced with topology refinement, to improve brain tumor segmentation accuracy on low-quality MRI data from Sub-Saharan Africa.

Contribution

It introduces a topology refinement module to address topological errors, improving segmentation performance on challenging low-quality MRI datasets.

Findings

Achieved NSD scores of 0.810, 0.829, and 0.895 on different tumor regions.

Pre-trained models on BraTS 2025 data improved fine-tuning results.

Topology refinement reduced deformation errors in segmentation predictions.

Abstract

Accurate automatic brain tumor segmentation in Low and Middle-Income (LMIC) countries is challenging due to the lack of defined national imaging protocols, diverse imaging data, extensive use of low-field Magnetic Resonance Imaging (MRI) scanners and limited health-care resources. As part of the Brain Tumor Segmentation (BraTS) Africa 2025 Challenge, we applied topology refinement to the state-of-the-art segmentation models like nnU-Net, MedNeXt, and a combination of both. Since the BraTS-Africa dataset has low MRI image quality, we incorporated the BraTS 2025 challenge data of pre-treatment adult glioma (Task 1) to pre-train the segmentation model and use it to fine-tune on the BraTS-Africa dataset. We added an extra topology refinement module to address the issue of deformation in prediction that arose due to topological error. With the introduction of this module, we achieved a better Normalized Surface Distance (NSD) of 0.810, 0.829, and 0.895 on Surrounding Non-Enhancing FLAIR Hyperintensity (SNFH) , Non-Enhancing Tumor Core (NETC) and Enhancing tumor (ET).