AMGFormer: Adaptive Multi-Granular Transformer for Brain Tumor Segmentation with Missing Modalities
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_ | 1866914283568234496 |
|---|---|
| author | Guo, Chengxiang Wang, Jian Fei, Junhua Li, Xiao Chen, Chunling Jin, Yun |
| author_facet | Guo, Chengxiang Wang, Jian Fei, Junhua Li, Xiao Chen, Chunling Jin, Yun |
| contents | Multimodal MRI is essential for brain tumor segmentation, yet missing modalities in clinical practice cause existing methods to exhibit >40% performance variance across modality combinations, rendering them clinically unreliable. We propose AMGFormer, achieving significantly improved stability through three synergistic modules: (1) QuadIntegrator Bridge (QIB) enabling spatially adaptive fusion maintaining consistent predictions regardless of available modalities, (2) Multi-Granular Attention Orchestrator (MGAO) focusing on pathological regions to reduce background sensitivity, and (3) Modality Quality-Aware Enhancement (MQAE) preventing error propagation from corrupted sequences. On BraTS 2018, our method achieves 89.33% WT, 82.70% TC, 67.23% ET Dice scores with <0.5% variance across 15 modality combinations, solving the stability crisis. Single-modality ET segmentation shows 40-81% relative improvements over state-of-the-art methods. The method generalizes to BraTS 2020/2021, achieving up to 92.44% WT, 89.91% TC, 84.57% ET. The model demonstrates potential for clinical deployment with 1.2s inference. Code: https://github.com/guochengxiangives/AMGFormer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19349 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AMGFormer: Adaptive Multi-Granular Transformer for Brain Tumor Segmentation with Missing Modalities Guo, Chengxiang Wang, Jian Fei, Junhua Li, Xiao Chen, Chunling Jin, Yun Image and Video Processing Computer Vision and Pattern Recognition Multimodal MRI is essential for brain tumor segmentation, yet missing modalities in clinical practice cause existing methods to exhibit >40% performance variance across modality combinations, rendering them clinically unreliable. We propose AMGFormer, achieving significantly improved stability through three synergistic modules: (1) QuadIntegrator Bridge (QIB) enabling spatially adaptive fusion maintaining consistent predictions regardless of available modalities, (2) Multi-Granular Attention Orchestrator (MGAO) focusing on pathological regions to reduce background sensitivity, and (3) Modality Quality-Aware Enhancement (MQAE) preventing error propagation from corrupted sequences. On BraTS 2018, our method achieves 89.33% WT, 82.70% TC, 67.23% ET Dice scores with <0.5% variance across 15 modality combinations, solving the stability crisis. Single-modality ET segmentation shows 40-81% relative improvements over state-of-the-art methods. The method generalizes to BraTS 2020/2021, achieving up to 92.44% WT, 89.91% TC, 84.57% ET. The model demonstrates potential for clinical deployment with 1.2s inference. Code: https://github.com/guochengxiangives/AMGFormer. |
| title | AMGFormer: Adaptive Multi-Granular Transformer for Brain Tumor Segmentation with Missing Modalities |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.19349 |