M$^4$oE: A Foundation Model for Medical Multimodal Image Segmentation with Mixture of Experts

TL;DR

The paper introduces M$^4$oE, a multimodal medical image segmentation model using a mixture of experts approach with a gating network, improving accuracy, interpretability, and efficiency across diverse datasets.

Contribution

It proposes a novel mixture of experts framework for medical multimodal segmentation that enhances generalization, interpretability, and computational efficiency.

Findings

Achieves up to 11.93% improvement over baseline models.

Reduces training time by 7 hours compared to similar methods.

Maintains only 30% of the parameters of comparable models.

Abstract

Medical imaging data is inherently heterogeneous across different modalities and clinical centers, posing unique challenges for developing generalizable foundation models. Conventional entails training distinct models per dataset or using a shared encoder with modality-specific decoders. However, these approaches incur heavy computational overheads and suffer from poor scalability. To address these limitations, we propose the Medical Multimodal Mixture of Experts (M$^4$oE) framework, leveraging the SwinUNet architecture. Specifically, M$^4$oE comprises modality-specific experts; each separately initialized to learn features encoding domain knowledge. Subsequently, a gating network is integrated during fine-tuning to modulate each expert's contribution to the collective predictions dynamically. This enhances model interpretability and generalization ability while retaining expertise specialization. Simultaneously, the M$^4$oE architecture amplifies the model's parallel processing capabilities, and it also ensures the model's adaptation to new modalities with ease. Experiments across three modalities reveal that M$^4$oE can achieve 3.45% over STU-Net-L, 5.11% over MED3D, and 11.93% over SAM-Med2D across the MICCAI FLARE22, AMOS2022, and ATLAS2023 datasets. Moreover, M$^4$oE showcases a significant reduction in training duration with 7 hours less while maintaining a parameter count that is only 30% of its compared methods. The code is available at https://github.com/JefferyJiang-YF/M4oE.