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

TL;DR

D3Seg is a novel brain tumor segmentation model that maintains high performance even when some MRI modalities are missing, using advanced inter-modality modeling and imputation techniques.

Contribution

The paper introduces D3Seg, which models higher order inter-modality dependencies and employs diffusion-based imputation to improve segmentation with missing MRI modalities.

Findings

D3Seg improves Dice scores by 1.5-2.0% on ET and 1.0% on TC in missing modality scenarios.

The model outperforms current state-of-the-art methods under various missing modality configurations.

D3Seg maintains computational efficiency while enhancing segmentation robustness.

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.