Federated Modality-specific Encoders and Partially Personalized Fusion Decoder for Multimodal Brain Tumor Segmentation

TL;DR

This paper introduces FedMEPD, a federated learning framework with modality-specific encoders and partially personalized decoders, effectively handling intermodal heterogeneity and missing modalities in multimodal brain tumor segmentation.

Contribution

The work proposes a novel FL framework with modality-specific encoders and dynamic personalized decoders, addressing intermodal heterogeneity and incomplete data in medical imaging.

Findings

Outperforms existing methods on BraTS benchmarks

Effectively handles missing modalities with cross-attention calibration

Demonstrates improved personalization and multimodal fusion

Abstract

Most existing federated learning (FL) methods for medical image analysis only considered intramodal heterogeneity, limiting their applicability to multimodal imaging applications. In practice, some FL participants may possess only a subset of the complete imaging modalities, posing intermodal heterogeneity as a challenge to effectively training a global model on all participants' data. Meanwhile, each participant expects a personalized model tailored to its local data characteristics in FL. This work proposes a new FL framework with federated modality-specific encoders and partially personalized multimodal fusion decoders (FedMEPD) to address the two concurrent issues. Specifically, FedMEPD employs an exclusive encoder for each modality to account for the intermodal heterogeneity. While these encoders are fully federated, the decoders are partially personalized to meet individual needs -- using the discrepancy between global and local parameter updates to dynamically determine which decoder filters are personalized. Implementation-wise, a server with full-modal data employs a fusion decoder to fuse representations from all modality-specific encoders, thus bridging the modalities to optimize the encoders via backpropagation. Moreover, multiple anchors are extracted from the fused multimodal representations and distributed to the clients in addition to the model parameters. Conversely, the clients with incomplete modalities calibrate their missing-modal representations toward the global full-modal anchors via scaled dot-product cross-attention, making up for the information loss due to absent modalities. FedMEPD is validated on the BraTS 2018 and 2020 multimodal brain tumor segmentation benchmarks. Results show that it outperforms various up-to-date methods for multimodal and personalized FL, and its novel designs are effective.