Topology-Driven Fusion of nnU-Net and MedNeXt for Accurate Brain Tumor Segmentation on Sub-Saharan Africa Dataset
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913040964780032 |
|---|---|
| author | Bohara, Prabin Shrestha, Pralhad Kumar Rai, Arpan Lamgade, Usha Poudel Raymond, Confidence Zhang, Dong Lorumbu, Aondona Jones, Craig Shakya, Mahesh Khanal, Bishesh Kulung, Pratibha |
| author_facet | Bohara, Prabin Shrestha, Pralhad Kumar Rai, Arpan Lamgade, Usha Poudel Raymond, Confidence Zhang, Dong Lorumbu, Aondona Jones, Craig Shakya, Mahesh Khanal, Bishesh Kulung, Pratibha |
| contents | 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). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15964 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Topology-Driven Fusion of nnU-Net and MedNeXt for Accurate Brain Tumor Segmentation on Sub-Saharan Africa Dataset Bohara, Prabin Shrestha, Pralhad Kumar Rai, Arpan Lamgade, Usha Poudel Raymond, Confidence Zhang, Dong Lorumbu, Aondona Jones, Craig Shakya, Mahesh Khanal, Bishesh Kulung, Pratibha Image and Video Processing Computer Vision and Pattern Recognition Machine Learning 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). |
| title | Topology-Driven Fusion of nnU-Net and MedNeXt for Accurate Brain Tumor Segmentation on Sub-Saharan Africa Dataset |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.15964 |