Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376988762> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4376988762 abstract "Robotic ultrasound (US) systems have shown great potential to make US examinations easier and more accurate. Recently, various machine learning techniques have been proposed to realize automatic US image interpretation for robotic US acquisition tasks. However, obtaining large amounts of real US imaging data for training is usually expensive or even unfeasible in some clinical applications. An alternative is to build a simulator to generate synthetic US data for training, but the differences between simulated and real US images may result in poor model performance. This work presents a Sim2Real framework to efficiently learn robotic US image analysis tasks based only on simulated data for real-world deployment. A style transfer module is proposed based on unsupervised contrastive learning and used as a preprocessing step to convert the real US images into the simulation style. Thereafter, a task-relevant model is designed to combine CNNs with vision transformers to generate the task-dependent prediction with improved generalization ability. We demonstrate the effectiveness of our method in an image regression task to predict the probe position based on US images in robotic transesophageal echocardiography (TEE). Our results show that using only simulated US data and a small amount of unlabelled real data for training, our method can achieve comparable performance to semi-supervised and fully supervised learning methods. Moreover, the effectiveness of our previously proposed CT-based US image simulation method is also indirectly confirmed." @default.
- W4376988762 created "2023-05-18" @default.
- W4376988762 creator A5002466280 @default.
- W4376988762 creator A5053035784 @default.
- W4376988762 creator A5058963021 @default.
- W4376988762 creator A5059605240 @default.
- W4376988762 creator A5062972206 @default.
- W4376988762 creator A5073511720 @default.
- W4376988762 date "2023-05-16" @default.
- W4376988762 modified "2023-10-16" @default.
- W4376988762 title "Style Transfer Enabled Sim2Real Framework for Efficient Learning of Robotic Ultrasound Image Analysis Using Simulated Data" @default.
- W4376988762 doi "https://doi.org/10.48550/arxiv.2305.09169" @default.
- W4376988762 hasPublicationYear "2023" @default.
- W4376988762 type Work @default.
- W4376988762 citedByCount "0" @default.
- W4376988762 crossrefType "posted-content" @default.
- W4376988762 hasAuthorship W4376988762A5002466280 @default.
- W4376988762 hasAuthorship W4376988762A5053035784 @default.
- W4376988762 hasAuthorship W4376988762A5058963021 @default.
- W4376988762 hasAuthorship W4376988762A5059605240 @default.
- W4376988762 hasAuthorship W4376988762A5062972206 @default.
- W4376988762 hasAuthorship W4376988762A5073511720 @default.
- W4376988762 hasBestOaLocation W43769887621 @default.
- W4376988762 hasConcept C10551718 @default.
- W4376988762 hasConcept C115961682 @default.
- W4376988762 hasConcept C119857082 @default.
- W4376988762 hasConcept C127413603 @default.
- W4376988762 hasConcept C134306372 @default.
- W4376988762 hasConcept C150899416 @default.
- W4376988762 hasConcept C154945302 @default.
- W4376988762 hasConcept C177148314 @default.
- W4376988762 hasConcept C201995342 @default.
- W4376988762 hasConcept C2780451532 @default.
- W4376988762 hasConcept C31972630 @default.
- W4376988762 hasConcept C33923547 @default.
- W4376988762 hasConcept C34736171 @default.
- W4376988762 hasConcept C41008148 @default.
- W4376988762 hasConceptScore W4376988762C10551718 @default.
- W4376988762 hasConceptScore W4376988762C115961682 @default.
- W4376988762 hasConceptScore W4376988762C119857082 @default.
- W4376988762 hasConceptScore W4376988762C127413603 @default.
- W4376988762 hasConceptScore W4376988762C134306372 @default.
- W4376988762 hasConceptScore W4376988762C150899416 @default.
- W4376988762 hasConceptScore W4376988762C154945302 @default.
- W4376988762 hasConceptScore W4376988762C177148314 @default.
- W4376988762 hasConceptScore W4376988762C201995342 @default.
- W4376988762 hasConceptScore W4376988762C2780451532 @default.
- W4376988762 hasConceptScore W4376988762C31972630 @default.
- W4376988762 hasConceptScore W4376988762C33923547 @default.
- W4376988762 hasConceptScore W4376988762C34736171 @default.
- W4376988762 hasConceptScore W4376988762C41008148 @default.
- W4376988762 hasLocation W43769887621 @default.
- W4376988762 hasOpenAccess W4376988762 @default.
- W4376988762 hasPrimaryLocation W43769887621 @default.
- W4376988762 hasRelatedWork W2020564930 @default.
- W4376988762 hasRelatedWork W2148258325 @default.
- W4376988762 hasRelatedWork W2353388427 @default.
- W4376988762 hasRelatedWork W2382928216 @default.
- W4376988762 hasRelatedWork W2889453578 @default.
- W4376988762 hasRelatedWork W2899307613 @default.
- W4376988762 hasRelatedWork W2972878997 @default.
- W4376988762 hasRelatedWork W2997394683 @default.
- W4376988762 hasRelatedWork W4308262314 @default.
- W4376988762 hasRelatedWork W1966592431 @default.
- W4376988762 isParatext "false" @default.
- W4376988762 isRetracted "false" @default.
- W4376988762 workType "article" @default.