Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386350545> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4386350545 abstract "Idiopathic Rem sleep Behavior Disorder (iRBD) is a significant biomarker for the development of alpha-synucleinopathies, such as Parkinson's disease (PD) or Dementia with Lewy bodies (DLB). Methods to identify patterns in iRBD patients can help in the prediction of the future conversion to these diseases during the long prodromal phase when symptoms are non-specific. These methods are essential for disease management and clinical trial recruitment. Brain PET scans with 18F-FDG PET radiotracers have recently shown promise, however, the scarcity of longitudinal data and PD/DLB conversion information makes the use of representation learning approaches such as deep convolutional networks not feasible if trained in a supervised manner. In this work, we propose a self-supervised learning strategy to learn features by comparing the brain hemispheres of iRBD non-convertor subjects, which allows for pre-training a convolutional network on a small data regimen. We introduce a loss function called hemisphere dissimilarity loss (HDL), which extends the Barlow Twins loss, that promotes the creation of invariant and non-redundant features for brain hemispheres of the same subject, and the opposite for hemispheres of different subjects. This loss enables the pre-training of a network without any information about the disease, which is then used to generate full brain feature vectors that are fine-tuned to two downstream tasks: follow-up conversion, and the type of conversion (PD or DLB) using baseline 18F-FDG PET. In our results, we find that the HDL outperforms the variational autoencoder with different forms of inputs." @default.
- W4386350545 created "2023-09-02" @default.
- W4386350545 creator A5026804774 @default.
- W4386350545 creator A5049564203 @default.
- W4386350545 creator A5069997978 @default.
- W4386350545 creator A5083708156 @default.
- W4386350545 creator A5085297755 @default.
- W4386350545 creator A5088970392 @default.
- W4386350545 date "2023-04-18" @default.
- W4386350545 modified "2023-09-30" @default.
- W4386350545 title "Brain Hemisphere Dissimilarity, a Self-Supervised Learning Approach for alpha-synucleinopathies prediction with FDG PET" @default.
- W4386350545 cites W1994605917 @default.
- W4386350545 cites W2112455323 @default.
- W4386350545 cites W2154744699 @default.
- W4386350545 cites W2623521763 @default.
- W4386350545 cites W2755418381 @default.
- W4386350545 cites W2888873632 @default.
- W4386350545 cites W2904404980 @default.
- W4386350545 cites W2948978827 @default.
- W4386350545 cites W3037156928 @default.
- W4386350545 cites W3157083093 @default.
- W4386350545 cites W4292641319 @default.
- W4386350545 doi "https://doi.org/10.1109/isbi53787.2023.10230560" @default.
- W4386350545 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37706192" @default.
- W4386350545 hasPublicationYear "2023" @default.
- W4386350545 type Work @default.
- W4386350545 citedByCount "0" @default.
- W4386350545 crossrefType "proceedings-article" @default.
- W4386350545 hasAuthorship W4386350545A5026804774 @default.
- W4386350545 hasAuthorship W4386350545A5049564203 @default.
- W4386350545 hasAuthorship W4386350545A5069997978 @default.
- W4386350545 hasAuthorship W4386350545A5083708156 @default.
- W4386350545 hasAuthorship W4386350545A5085297755 @default.
- W4386350545 hasAuthorship W4386350545A5088970392 @default.
- W4386350545 hasConcept C108583219 @default.
- W4386350545 hasConcept C119857082 @default.
- W4386350545 hasConcept C142724271 @default.
- W4386350545 hasConcept C153180895 @default.
- W4386350545 hasConcept C154945302 @default.
- W4386350545 hasConcept C15744967 @default.
- W4386350545 hasConcept C2778548049 @default.
- W4386350545 hasConcept C2779134260 @default.
- W4386350545 hasConcept C2779483572 @default.
- W4386350545 hasConcept C2779734285 @default.
- W4386350545 hasConcept C41008148 @default.
- W4386350545 hasConcept C59404180 @default.
- W4386350545 hasConcept C71924100 @default.
- W4386350545 hasConceptScore W4386350545C108583219 @default.
- W4386350545 hasConceptScore W4386350545C119857082 @default.
- W4386350545 hasConceptScore W4386350545C142724271 @default.
- W4386350545 hasConceptScore W4386350545C153180895 @default.
- W4386350545 hasConceptScore W4386350545C154945302 @default.
- W4386350545 hasConceptScore W4386350545C15744967 @default.
- W4386350545 hasConceptScore W4386350545C2778548049 @default.
- W4386350545 hasConceptScore W4386350545C2779134260 @default.
- W4386350545 hasConceptScore W4386350545C2779483572 @default.
- W4386350545 hasConceptScore W4386350545C2779734285 @default.
- W4386350545 hasConceptScore W4386350545C41008148 @default.
- W4386350545 hasConceptScore W4386350545C59404180 @default.
- W4386350545 hasConceptScore W4386350545C71924100 @default.
- W4386350545 hasLocation W43863505451 @default.
- W4386350545 hasLocation W43863505452 @default.
- W4386350545 hasOpenAccess W4386350545 @default.
- W4386350545 hasPrimaryLocation W43863505451 @default.
- W4386350545 hasRelatedWork W2029029464 @default.
- W4386350545 hasRelatedWork W2038563492 @default.
- W4386350545 hasRelatedWork W3014300295 @default.
- W4386350545 hasRelatedWork W4223943233 @default.
- W4386350545 hasRelatedWork W4225161397 @default.
- W4386350545 hasRelatedWork W4312200629 @default.
- W4386350545 hasRelatedWork W4360585206 @default.
- W4386350545 hasRelatedWork W4364306694 @default.
- W4386350545 hasRelatedWork W4380075502 @default.
- W4386350545 hasRelatedWork W4380086463 @default.
- W4386350545 isParatext "false" @default.
- W4386350545 isRetracted "false" @default.
- W4386350545 workType "article" @default.