Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386470319> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4386470319 endingPage "1" @default.
- W4386470319 startingPage "1" @default.
- W4386470319 abstract "Deep neural networks are often applied to medical images to automate the problem of medical diagnosis. However, a more clinically relevant question that practitioners usually face is how to predict the future trajectory of a disease. Current methods for prognosis or disease trajectory forecasting often require domain knowledge and are complicated to apply. In this paper, we formulate the prognosis prediction problem as a one-to-many prediction problem. Inspired by a clinical decision-making process with two agents – a radiologist and a general practitioner – we predict prognosis with two transformer-based components that share information with each other. The first transformer in this framework aims to analyze the imaging data, and the second one leverages its internal states as inputs, also fusing them with auxiliary clinical data. The temporal nature of the problem is modeled within the transformer states, allowing us to treat the forecasting problem as a multi-task classification, for which we propose a novel loss. We show the effectiveness of our approach in predicting the development of structural knee osteoarthritis changes and forecasting Alzheimer’s disease clinical status directly from raw multi-modal data. The proposed method outperforms multiple state-of-the-art baselines with respect to performance and calibration, both of which are needed for real-world applications. An open-source implementation of our method is made publicly available at https://github.com/Oulu-IMEDS/CLIMATv2." @default.
- W4386470319 created "2023-09-07" @default.
- W4386470319 creator A5051498728 @default.
- W4386470319 creator A5067156682 @default.
- W4386470319 creator A5071275238 @default.
- W4386470319 creator A5077783791 @default.
- W4386470319 date "2023-01-01" @default.
- W4386470319 modified "2023-10-01" @default.
- W4386470319 title "Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal Data" @default.
- W4386470319 doi "https://doi.org/10.1109/tmi.2023.3312524" @default.
- W4386470319 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37672368" @default.
- W4386470319 hasPublicationYear "2023" @default.
- W4386470319 type Work @default.
- W4386470319 citedByCount "1" @default.
- W4386470319 countsByYear W43864703192023 @default.
- W4386470319 crossrefType "journal-article" @default.
- W4386470319 hasAuthorship W4386470319A5051498728 @default.
- W4386470319 hasAuthorship W4386470319A5067156682 @default.
- W4386470319 hasAuthorship W4386470319A5071275238 @default.
- W4386470319 hasAuthorship W4386470319A5077783791 @default.
- W4386470319 hasBestOaLocation W43864703191 @default.
- W4386470319 hasConcept C108583219 @default.
- W4386470319 hasConcept C119857082 @default.
- W4386470319 hasConcept C121332964 @default.
- W4386470319 hasConcept C124101348 @default.
- W4386470319 hasConcept C1276947 @default.
- W4386470319 hasConcept C13662910 @default.
- W4386470319 hasConcept C154945302 @default.
- W4386470319 hasConcept C165801399 @default.
- W4386470319 hasConcept C41008148 @default.
- W4386470319 hasConcept C62520636 @default.
- W4386470319 hasConcept C66322947 @default.
- W4386470319 hasConceptScore W4386470319C108583219 @default.
- W4386470319 hasConceptScore W4386470319C119857082 @default.
- W4386470319 hasConceptScore W4386470319C121332964 @default.
- W4386470319 hasConceptScore W4386470319C124101348 @default.
- W4386470319 hasConceptScore W4386470319C1276947 @default.
- W4386470319 hasConceptScore W4386470319C13662910 @default.
- W4386470319 hasConceptScore W4386470319C154945302 @default.
- W4386470319 hasConceptScore W4386470319C165801399 @default.
- W4386470319 hasConceptScore W4386470319C41008148 @default.
- W4386470319 hasConceptScore W4386470319C62520636 @default.
- W4386470319 hasConceptScore W4386470319C66322947 @default.
- W4386470319 hasFunder F4320310907 @default.
- W4386470319 hasFunder F4320321108 @default.
- W4386470319 hasLocation W43864703191 @default.
- W4386470319 hasLocation W43864703192 @default.
- W4386470319 hasOpenAccess W4386470319 @default.
- W4386470319 hasPrimaryLocation W43864703191 @default.
- W4386470319 hasRelatedWork W3014300295 @default.
- W4386470319 hasRelatedWork W3164822677 @default.
- W4386470319 hasRelatedWork W4223943233 @default.
- W4386470319 hasRelatedWork W4225161397 @default.
- W4386470319 hasRelatedWork W4250304930 @default.
- W4386470319 hasRelatedWork W4312200629 @default.
- W4386470319 hasRelatedWork W4360585206 @default.
- W4386470319 hasRelatedWork W4364306694 @default.
- W4386470319 hasRelatedWork W4380075502 @default.
- W4386470319 hasRelatedWork W4380086463 @default.
- W4386470319 isParatext "false" @default.
- W4386470319 isRetracted "false" @default.
- W4386470319 workType "article" @default.