# D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities

arXiv: https://arxiv.org/abs/2605.22249 · HTML: https://mlsanity.com/paper/2605.22249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 67 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 30 of 32)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://mlsanity.com/paper/2305.08891/) (2023)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [Brain Tumor Segmentation with Deep Neural Networks](https://mlsanity.com/paper/1505.03540/) (2015)
- [HeMIS: Hetero-Modal Image Segmentation](https://mlsanity.com/paper/1607.05194/) (2016)
- [Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Network](https://mlsanity.com/paper/1904.12200/) (2019)
- [mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation](https://mlsanity.com/paper/2206.02425/) (2022)
- [Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis](https://mlsanity.com/paper/2305.18453/) (2023)
- [Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentation](https://mlsanity.com/paper/1907.11150/) (2019)
- [Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion](https://mlsanity.com/paper/2002.09708/) (2020)
- [CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis](https://mlsanity.com/paper/2303.14081/) (2023)
- [M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities](https://mlsanity.com/paper/2303.05302/) (2023)
- [The ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2023: Intracranial Meningioma](https://mlsanity.com/paper/2305.07642/) (2023)
- [Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality](https://mlsanity.com/paper/2310.01035/) (2023)
- [ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities](https://mlsanity.com/paper/2106.14591/) (2021)
- [Latent Correlation Representation Learning for Brain Tumor Segmentation with Missing MRI Modalities](https://mlsanity.com/paper/2104.06231/) (2021)
- [Deep Learning Based Brain Tumor Segmentation: A Survey](https://mlsanity.com/paper/2007.09479/) (2020)
- [Brain tumor segmentation with missing modalities via latent multi-source correlation representation](https://mlsanity.com/paper/2003.08870/) (2020)
- [SFusion: Self-attention based N-to-One Multimodal Fusion Block](https://mlsanity.com/paper/2208.12776/) (2022)
- [Enhancing Modality-Agnostic Representations via Meta-Learning for Brain Tumor Segmentation](https://mlsanity.com/paper/2302.04308/) (2023)
- [Feature-enhanced Generation and Multi-modality Fusion based Deep Neural Network for Brain Tumor Segmentation with Missing MR Modalities](https://mlsanity.com/paper/2111.04735/) (2021)
- [CORE: Context-Robust Remasking for Diffusion Language Models](https://mlsanity.com/paper/2602.04096/) (2026)
- [Hypergraph Tversky-Aware Domain Incremental Learning for Brain Tumor Segmentation with Missing Modalities](https://mlsanity.com/paper/2505.16809/) (2025)
- [XLSTM-HVED: Cross-Modal Brain Tumor Segmentation and MRI Reconstruction Method Using Vision XLSTM and Heteromodal Variational Encoder-Decoder](https://mlsanity.com/paper/2412.07804/) (2024)
- [DC-Seg: Disentangled Contrastive Learning for Brain Tumor Segmentation with Missing Modalities](https://mlsanity.com/paper/2505.11921/) (2025)
- [Bridging the Gap in Missing Modalities: Leveraging Knowledge Distillation and Style Matching for Brain Tumor Segmentation](https://mlsanity.com/paper/2507.22626/) (2025)
- [No Modality Left Behind: Adapting to Missing Modalities via Knowledge Distillation for Brain Tumor Segmentation](https://mlsanity.com/paper/2509.15017/) (2025)
- [DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights](https://mlsanity.com/paper/2510.14383/) (2025)

## Abstract (arXiv)

Accurate brain tumor segmentation using multi-parametric MRI is critical for effective treatment planning. However, in clinical settings, complete acquisition of all MRI sequences is not always possible. The absence of certain MRI modalities results in substantial performance degradation in existing segmentation methods, which typically rely on naive feature concatenation or direct fusion strategies. To address this limitation, we propose a novel segmentation model D3Seg which is designed to maintain stable performance under missing-modality settings. D3Seg introduces Multi-hop Modality Graph Fusion (MMGF) to model higher-order inter-modality dependencies, a lightweight diffusion-based imputation mechanism to compensate for missing T1ce and FLAIR feature representations in latent space, and probability-space decision refinement to mitigate dominant-class overconfidence and improve delineation of underrepresented tumor subregions. We evaluate the proposed D3Seg model on BraTS 2023 Glioma as the primary benchmark and further test it on a subset of the external BraTS 2023 Meningioma cohort to assess generalization across tumor pathologies. The results are compared with the state-of-the-art models under different missing-modality conditions. The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing-modality configurations compared to the current state-of-the-art model on BraTS Glioma dataset. Cross-cohort evaluation on BraTS Meningioma dataset demonstrates the generalizability of the proposed model, showing consistent improvements in the challenging TC and ET regions, with approximately 1.5-3.0% and 1.5-6.5% gains respectively across several missing-modality configurations.