D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 67 references that are in the map. First posted on arXiv 21 May 2026.
Builds on
32 of 67 references.
References · 32
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
- 2021The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classificationcited by 507
- 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
- 2023Multi-modal Learning with Missing Modality via Shared-Specific Feature Modellingcited by 159
- 2015Brain Tumor Segmentation with Deep Neural Networkscited by 137
- 2016HeMIS: Hetero-Modal Image Segmentationcited by 102
- 2019Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Networkcited by 98
- 2022mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentationcited by 94
- 2023Conditional Diffusion Models for Semantic 3D Brain MRI Synthesiscited by 85
- 2019Hetero-Modal Variational Encoder-Decoder for Joint Modality Completion and Segmentationcited by 68
- 2020Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusioncited by 67
20 more
- 2023CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesiscited by 64
- 2023M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalitiescited by 56
- 2023The ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2023: Intracranial Meningiomacited by 51
- 2023Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modalitycited by 44
- 2021ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalitiescited by 43
- 2021Latent Correlation Representation Learning for Brain Tumor Segmentation with Missing MRI Modalitiescited by 42
- 2020Deep Learning Based Brain Tumor Segmentation: A Surveycited by 30
- 2020Brain tumor segmentation with missing modalities via latent multi-source correlation representationcited by 19
- 2022SFusion: Self-attention based N-to-One Multimodal Fusion Blockcited by 14
- 2023Enhancing Modality-Agnostic Representations via Meta-Learning for Brain Tumor Segmentationcited by 14
- 2021Feature-enhanced Generation and Multi-modality Fusion based Deep Neural Network for Brain Tumor Segmentation with Missing MR Modalitiescited by 13
- 2026CORE: Context-Robust Remasking for Diffusion Language Modelscited by 10
- 2025Hypergraph Tversky-Aware Domain Incremental Learning for Brain Tumor Segmentation with Missing Modalitiescited by 7
- 2024XLSTM-HVED: Cross-Modal Brain Tumor Segmentation and MRI Reconstruction Method Using Vision XLSTM and Heteromodal Variational Encoder-Decodercited by 5
- 2025DC-Seg: Disentangled Contrastive Learning for Brain Tumor Segmentation with Missing Modalitiescited by 5
- 2025Bridging the Gap in Missing Modalities: Leveraging Knowledge Distillation and Style Matching for Brain Tumor Segmentationcited by 4
- 2025No Modality Left Behind: Adapting to Missing Modalities via Knowledge Distillation for Brain Tumor Segmentationcited by 4
- 2025DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insightscited by 3
- 2025Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalitiescited by 2
- 2024A Multimodal Feature Distillation with Mamba-Transformer Network for Brain Tumor Segmentation with Incomplete Modalitiescited by 1
Built on by
Not cited yet.