Rate-My-LoRA: Efficient and Adaptive Federated Model Tuning for Cardiac MRI Segmentation

TL;DR

This paper introduces Rate-My-LoRA, a federated learning approach for cardiac MRI segmentation that enhances model accuracy and efficiency by reducing communication costs and adapting to data heterogeneity across hospitals.

Contribution

The paper proposes a novel adaptive federated learning method using LoRA and a new aggregation technique to improve cardiac MRI segmentation performance in privacy-preserving settings.

Findings

Outperforms existing LoRA-based federated learning methods.

Reduces communication overhead in federated training.

Achieves better generalization across heterogeneous datasets.

Abstract

Cardiovascular disease (CVD) and cardiac dyssynchrony are major public health problems in the United States. Precise cardiac image segmentation is crucial for extracting quantitative measures that help categorize cardiac dyssynchrony. However, achieving high accuracy often depends on centralizing large datasets from different hospitals, which can be challenging due to privacy concerns. To solve this problem, Federated Learning (FL) is proposed to enable decentralized model training on such data without exchanging sensitive information. However, bandwidth limitations and data heterogeneity remain as significant challenges in conventional FL algorithms. In this paper, we propose a novel efficient and adaptive federate learning method for cardiac segmentation that improves model performance while reducing the bandwidth requirement. Our method leverages the low-rank adaptation (LoRA) to regularize model weight update and reduce communication overhead. We also propose a \mymethod{} aggregation technique to address data heterogeneity among clients. This technique adaptively penalizes the aggregated weights from different clients by comparing the validation accuracy in each client, allowing better generalization performance and fast local adaptation. In-client and cross-client evaluations on public cardiac MR datasets demonstrate the superiority of our method over other LoRA-based federate learning approaches.