AUTHOR=Liu Dongnan , Cabezas Mariano , Wang Dongang , Tang Zihao , Bai Lei , Zhan Geng , Luo Yuling , Kyle Kain , Ly Linda , Yu James , Shieh Chun-Chien , Nguyen Aria , Kandasamy Karuppiah Ettikan , Sullivan Ryan , Calamante Fernando , Barnett Michael , Ouyang Wanli , Cai Weidong , Wang Chenyu TITLE=Multiple sclerosis lesion segmentation: revisiting weighting mechanisms for federated learning JOURNAL=Frontiers in Neuroscience VOLUME=17 YEAR=2023 URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1167612 DOI=10.3389/fnins.2023.1167612 ISSN=1662-453X ABSTRACT=Background and introduction

Federated learning (FL) has been widely employed for medical image analysis to facilitate multi-client collaborative learning without sharing raw data. Despite great success, FL's applications remain suboptimal in neuroimage analysis tasks such as lesion segmentation in multiple sclerosis (MS), due to variance in lesion characteristics imparted by different scanners and acquisition parameters.

Methods

In this work, we propose the first FL MS lesion segmentation framework via two effective re-weighting mechanisms. Specifically, a learnable weight is assigned to each local node during the aggregation process, based on its segmentation performance. In addition, the segmentation loss function in each client is also re-weighted according to the lesion volume for the data during training.

Results

The proposed method has been validated on two FL MS segmentation scenarios using public and clinical datasets. Specifically, the case-wise and voxel-wise Dice score of the proposed method under the first public dataset is 65.20 and 74.30, respectively. On the second in-house dataset, the case-wise and voxel-wise Dice score is 53.66, and 62.31, respectively.

Discussions and conclusions

The Comparison experiments on two FL MS segmentation scenarios using public and clinical datasets have demonstrated the effectiveness of the proposed method by significantly outperforming other FL methods. Furthermore, the segmentation performance of FL incorporating our proposed aggregation mechanism can achieve comparable performance to that from centralized training with all the raw data.