Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385879930> ?p ?o ?g. }
- W4385879930 endingPage "107330" @default.
- W4385879930 startingPage "107330" @default.
- W4385879930 abstract "Magnetic resonance imaging (MRI) is extensively utilized in clinical practice for diagnostic purposes, owing to its non-invasive nature and remarkable ability to provide detailed characterization of soft tissues. However, its drawback lies in the prolonged scanning time. To accelerate MR imaging, how to reconstruct MR images from under-sampled data quickly and accurately has drawn intensive research interest; it, however, remains a challenging task. While some deep learning models have achieved promising performance in MRI reconstruction, these models usually require a substantial quantity of paired data for training, which proves challenging to gather and share owing to high scanning costs and data privacy concerns. Federated learning (FL) is a potential tool to alleviate these difficulties. It enables multiple clinical clients to collaboratively train a global model without compromising privacy. However, it is extremely challenging to fit a single model to diverse data distributions of different clients. Moreover, existing FL algorithms treat the features of each channel equally, lacking discriminative learning ability across feature channels, and hence hindering their representational capability. In this study, we propose a novel Adaptive Channel-Modulated Federal learning framework for personalized MRI reconstruction, dubbed as ACM-FedMRI. Specifically, considering each local client may focus on features in different channels, we first design a client-specific hypernetwork to guide the channel selection operation in order to optimize the extracted features. Additionally, we introduce a performance-based channel decoupling scheme, which dynamically separates the global model at the channel level to facilitate personalized adjustments based on the performance of individual clients. This approach eliminates the need for heuristic design of specific personalization layers. Extensive experiments on four datasets under two different settings show that our ACM-FedMRI achieves outstanding results compared to other cutting-edge federated learning techniques in the field of MRI reconstruction." @default.
- W4385879930 created "2023-08-17" @default.
- W4385879930 creator A5031202827 @default.
- W4385879930 creator A5063943130 @default.
- W4385879930 creator A5080804199 @default.
- W4385879930 creator A5085132583 @default.
- W4385879930 creator A5085254957 @default.
- W4385879930 date "2023-10-01" @default.
- W4385879930 modified "2023-10-04" @default.
- W4385879930 title "Adaptive channel-modulated personalized federated learning for magnetic resonance image reconstruction" @default.
- W4385879930 cites W1641498739 @default.
- W4385879930 cites W2018443449 @default.
- W4385879930 cites W2029816571 @default.
- W4385879930 cites W2101675075 @default.
- W4385879930 cites W2107906890 @default.
- W4385879930 cites W2168668658 @default.
- W4385879930 cites W2398196955 @default.
- W4385879930 cites W2594014149 @default.
- W4385879930 cites W2604388535 @default.
- W4385879930 cites W2611467245 @default.
- W4385879930 cites W2778924750 @default.
- W4385879930 cites W2791621240 @default.
- W4385879930 cites W2804263814 @default.
- W4385879930 cites W2908867979 @default.
- W4385879930 cites W2969768983 @default.
- W4385879930 cites W2995191368 @default.
- W4385879930 cites W3004715589 @default.
- W4385879930 cites W3034223847 @default.
- W4385879930 cites W3034546843 @default.
- W4385879930 cites W3086590218 @default.
- W4385879930 cites W3119085955 @default.
- W4385879930 cites W3164944602 @default.
- W4385879930 cites W3165750456 @default.
- W4385879930 cites W3175307072 @default.
- W4385879930 cites W3197279620 @default.
- W4385879930 cites W4206501708 @default.
- W4385879930 cites W4285736212 @default.
- W4385879930 doi "https://doi.org/10.1016/j.compbiomed.2023.107330" @default.
- W4385879930 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37611426" @default.
- W4385879930 hasPublicationYear "2023" @default.
- W4385879930 type Work @default.
- W4385879930 citedByCount "0" @default.
- W4385879930 crossrefType "journal-article" @default.
- W4385879930 hasAuthorship W4385879930A5031202827 @default.
- W4385879930 hasAuthorship W4385879930A5063943130 @default.
- W4385879930 hasAuthorship W4385879930A5080804199 @default.
- W4385879930 hasAuthorship W4385879930A5085132583 @default.
- W4385879930 hasAuthorship W4385879930A5085254957 @default.
- W4385879930 hasBestOaLocation W43858799301 @default.
- W4385879930 hasConcept C108583219 @default.
- W4385879930 hasConcept C119857082 @default.
- W4385879930 hasConcept C124101348 @default.
- W4385879930 hasConcept C127162648 @default.
- W4385879930 hasConcept C127413603 @default.
- W4385879930 hasConcept C133731056 @default.
- W4385879930 hasConcept C138885662 @default.
- W4385879930 hasConcept C154945302 @default.
- W4385879930 hasConcept C162324750 @default.
- W4385879930 hasConcept C187736073 @default.
- W4385879930 hasConcept C205606062 @default.
- W4385879930 hasConcept C2776401178 @default.
- W4385879930 hasConcept C2780451532 @default.
- W4385879930 hasConcept C31258907 @default.
- W4385879930 hasConcept C41008148 @default.
- W4385879930 hasConcept C41895202 @default.
- W4385879930 hasConcept C97931131 @default.
- W4385879930 hasConceptScore W4385879930C108583219 @default.
- W4385879930 hasConceptScore W4385879930C119857082 @default.
- W4385879930 hasConceptScore W4385879930C124101348 @default.
- W4385879930 hasConceptScore W4385879930C127162648 @default.
- W4385879930 hasConceptScore W4385879930C127413603 @default.
- W4385879930 hasConceptScore W4385879930C133731056 @default.
- W4385879930 hasConceptScore W4385879930C138885662 @default.
- W4385879930 hasConceptScore W4385879930C154945302 @default.
- W4385879930 hasConceptScore W4385879930C162324750 @default.
- W4385879930 hasConceptScore W4385879930C187736073 @default.
- W4385879930 hasConceptScore W4385879930C205606062 @default.
- W4385879930 hasConceptScore W4385879930C2776401178 @default.
- W4385879930 hasConceptScore W4385879930C2780451532 @default.
- W4385879930 hasConceptScore W4385879930C31258907 @default.
- W4385879930 hasConceptScore W4385879930C41008148 @default.
- W4385879930 hasConceptScore W4385879930C41895202 @default.
- W4385879930 hasConceptScore W4385879930C97931131 @default.
- W4385879930 hasLocation W43858799301 @default.
- W4385879930 hasLocation W43858799302 @default.
- W4385879930 hasOpenAccess W4385879930 @default.
- W4385879930 hasPrimaryLocation W43858799301 @default.
- W4385879930 hasRelatedWork W2970216048 @default.
- W4385879930 hasRelatedWork W3014300295 @default.
- W4385879930 hasRelatedWork W3164822677 @default.
- W4385879930 hasRelatedWork W4223943233 @default.
- W4385879930 hasRelatedWork W4225161397 @default.
- W4385879930 hasRelatedWork W4312200629 @default.
- W4385879930 hasRelatedWork W4360585206 @default.
- W4385879930 hasRelatedWork W4364306694 @default.
- W4385879930 hasRelatedWork W4380075502 @default.
- W4385879930 hasRelatedWork W4380086463 @default.
- W4385879930 hasVolume "165" @default.