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

2026-05-21

AI Summary

This work addresses the significant performance degradation in multimodal MRI brain tumor segmentation when certain imaging modalities are missing. To tackle this challenge, the authors propose D3Seg, a novel framework that models high-order inter-modal dependencies through multi-hop modality graph fusion and incorporates a lightweight latent-space diffusion mechanism to reconstruct missing T1ce features. Furthermore, segmentation decisions are optimized in a probabilistic space to enhance robustness. Extensive experiments on the BraTS 2023 dataset demonstrate that D3Seg achieves approximately 1.5–2.0% and 1.0% improvements in Dice scores for enhancing tumor and tumor core, respectively, outperforming current state-of-the-art methods while maintaining computational efficiency.

Abstract

Accurate brain tumor segmentation using multiparametric 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 representations in latent space, and probability-space decision refinement to mitigate dominant class overconfidence and improve delineation of underrepresented tumor subregions. Extensive evaluation on BraTS 2023 dataset demonstrates that our D3Seg model consistently improves segmentation performance under missing modality configurations. 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, while maintaining computational efficiency.

Problem

• brain tumor segmentation
• missing modalities
• MRI
• modality dependency
• medical image analysis

Innovation

• Multi-hop Modality Graph Fusion
• Diffusion-based Imputation
• Missing Modality Segmentation
• Probability-space Refinement
• Brain Tumor Segmentation