# AMGFormer: Adaptive Multi-Granular Transformer for Brain Tumor Segmentation with Missing Modalities

arXiv: https://arxiv.org/abs/2601.19349 · HTML: https://mlsanity.com/paper/2601.19349/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [HeMIS: Hetero-Modal Image Segmentation](https://mlsanity.com/paper/1607.05194/) (2016)
- [Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation](https://mlsanity.com/paper/1907.11150/) (2019)
- [ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities](https://mlsanity.com/paper/2106.14591/) (2021)
- [SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities](https://mlsanity.com/paper/2204.02961/) (2022)
- [Anatomical Consistency Distillation and Inconsistency Synthesis for Brain Tumor Segmentation with Missing Modalities](https://mlsanity.com/paper/2408.13733/) (2024)
- [Enhancing Incomplete Multi-modal Brain Tumor Segmentation with Intra-modal Asymmetry and Inter-modal Dependency](https://mlsanity.com/paper/2406.10175/) (2024)

## Abstract (arXiv)

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.