Matches in SemOpenAlex for { <https://semopenalex.org/work/W2968405527> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2968405527 endingPage "1610" @default.
- W2968405527 startingPage "1601" @default.
- W2968405527 abstract "Intravitreal injection is among the most frequent treatment strategies for chronic ophthalmic diseases. The last decade has seen a serious increase in the number of intravitreal injections, and with it, adverse effects and drawbacks. To tackle these problems, medical assistive devices for robotized injections have been suggested and are projected to enhance delivery mechanisms for a new generation of pharmacological solutions. In this paper, we present a method aimed at improving the safety characteristics of upcoming robotic systems. Our vision-based method uses a combination of 2D OCT data, numerical simulation and machine learning to classify the range of the force applied by an injection needle on the sclera.We design a neural network to classify force ranges from optical coherence tomography (OCT) images of the sclera directly. To avoid the need for large real data sets, the network is trained on images of simulated deformed sclera. This simulation is based on a finite element method, and the model is parameterized using a Bayesian filter applied to observations of the deformation in OCT images.We validate our approach on real OCT data collected on five ex vivo porcine eyes using a robotically guided needle. The thorough parameterization of the simulations leads to a very good agreement between the virtually generated samples used to train the network and the real OCT acquisitions. Results show that the applied force range on real data can be predicted with 93% accuracy.Through a simulation-trained neural network, our approach estimates the force range applied by a robotically guided needle on the sclera based solely on a single OCT slice of the deformed sclera. Being real-time, this solution can be integrated in the control loop of the system, permitting the prompt withdrawal of the needle for safety reasons." @default.
- W2968405527 created "2019-08-22" @default.
- W2968405527 creator A5040009139 @default.
- W2968405527 creator A5083445640 @default.
- W2968405527 creator A5088268019 @default.
- W2968405527 date "2019-08-16" @default.
- W2968405527 modified "2023-09-29" @default.
- W2968405527 title "Force classification during robotic interventions through simulation-trained neural networks" @default.
- W2968405527 cites W1509929206 @default.
- W2968405527 cites W184127182 @default.
- W2968405527 cites W2034105035 @default.
- W2968405527 cites W2034126085 @default.
- W2968405527 cites W2042793865 @default.
- W2968405527 cites W2058062309 @default.
- W2968405527 cites W2063189491 @default.
- W2968405527 cites W2090113391 @default.
- W2968405527 cites W2100932843 @default.
- W2968405527 cites W2397600741 @default.
- W2968405527 cites W2507622598 @default.
- W2968405527 cites W2581387281 @default.
- W2968405527 cites W2607057921 @default.
- W2968405527 cites W2794322549 @default.
- W2968405527 cites W2890638966 @default.
- W2968405527 cites W4750978 @default.
- W2968405527 doi "https://doi.org/10.1007/s11548-019-02048-3" @default.
- W2968405527 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31420832" @default.
- W2968405527 hasPublicationYear "2019" @default.
- W2968405527 type Work @default.
- W2968405527 sameAs 2968405527 @default.
- W2968405527 citedByCount "13" @default.
- W2968405527 countsByYear W29684055272020 @default.
- W2968405527 countsByYear W29684055272021 @default.
- W2968405527 countsByYear W29684055272022 @default.
- W2968405527 countsByYear W29684055272023 @default.
- W2968405527 crossrefType "journal-article" @default.
- W2968405527 hasAuthorship W2968405527A5040009139 @default.
- W2968405527 hasAuthorship W2968405527A5083445640 @default.
- W2968405527 hasAuthorship W2968405527A5088268019 @default.
- W2968405527 hasBestOaLocation W29684055272 @default.
- W2968405527 hasConcept C108583219 @default.
- W2968405527 hasConcept C118487528 @default.
- W2968405527 hasConcept C119857082 @default.
- W2968405527 hasConcept C141071460 @default.
- W2968405527 hasConcept C154945302 @default.
- W2968405527 hasConcept C2777100477 @default.
- W2968405527 hasConcept C2778818243 @default.
- W2968405527 hasConcept C31972630 @default.
- W2968405527 hasConcept C41008148 @default.
- W2968405527 hasConcept C44154836 @default.
- W2968405527 hasConcept C50644808 @default.
- W2968405527 hasConcept C71924100 @default.
- W2968405527 hasConceptScore W2968405527C108583219 @default.
- W2968405527 hasConceptScore W2968405527C118487528 @default.
- W2968405527 hasConceptScore W2968405527C119857082 @default.
- W2968405527 hasConceptScore W2968405527C141071460 @default.
- W2968405527 hasConceptScore W2968405527C154945302 @default.
- W2968405527 hasConceptScore W2968405527C2777100477 @default.
- W2968405527 hasConceptScore W2968405527C2778818243 @default.
- W2968405527 hasConceptScore W2968405527C31972630 @default.
- W2968405527 hasConceptScore W2968405527C41008148 @default.
- W2968405527 hasConceptScore W2968405527C44154836 @default.
- W2968405527 hasConceptScore W2968405527C50644808 @default.
- W2968405527 hasConceptScore W2968405527C71924100 @default.
- W2968405527 hasIssue "9" @default.
- W2968405527 hasLocation W29684055271 @default.
- W2968405527 hasLocation W29684055272 @default.
- W2968405527 hasLocation W29684055273 @default.
- W2968405527 hasLocation W29684055274 @default.
- W2968405527 hasOpenAccess W2968405527 @default.
- W2968405527 hasPrimaryLocation W29684055271 @default.
- W2968405527 hasRelatedWork W2567615336 @default.
- W2968405527 hasRelatedWork W3014300295 @default.
- W2968405527 hasRelatedWork W3164822677 @default.
- W2968405527 hasRelatedWork W4223943233 @default.
- W2968405527 hasRelatedWork W4225161397 @default.
- W2968405527 hasRelatedWork W4312200629 @default.
- W2968405527 hasRelatedWork W4360585206 @default.
- W2968405527 hasRelatedWork W4364306694 @default.
- W2968405527 hasRelatedWork W4380075502 @default.
- W2968405527 hasRelatedWork W4380086463 @default.
- W2968405527 hasVolume "14" @default.
- W2968405527 isParatext "false" @default.
- W2968405527 isRetracted "false" @default.
- W2968405527 magId "2968405527" @default.
- W2968405527 workType "article" @default.