2021 | OriginalPaper | Buchkapitel
Federated Contrastive Learning for Decentralized Unlabeled Medical Images
verfasst von : Nanqing Dong, Irina Voiculescu
Erschienen in: Medical Image Computing and Computer Assisted Intervention – MICCAI 2021
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
FedMoCo
, a robust federated contrastive learning (FCL) framework, which makes efficient use of decentralized unlabeled medical data. FedMoCo
has two novel modules: metadata transfer, an inter-node statistical data augmentation module, and self-adaptive aggregation, an aggregation module based on representational similarity analysis. To the best of our knowledge, this is the first FCL work on medical images. Our experiments show that FedMoCo
can consistently outperform FedAvg
, a seminal federated learning framework, in extracting meaningful representations for downstream tasks. We further show that FedMoCo
can substantially reduce the amount of labeled data required in a downstream task, such as COVID-19 detection, to achieve a reasonable performance.