FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964283648> ?p ?o ?g. }

• W2964283648 endingPage "1087" @default.
• W2964283648 startingPage "1079" @default.
• W2964283648 abstract "For many applications in the field of computer-assisted surgery, such as providing the position of a tumor, specifying the most probable tool required next by the surgeon or determining the remaining duration of surgery, methods for surgical workflow analysis are a prerequisite. Often machine learning-based approaches serve as basis for analyzing the surgical workflow. In general, machine learning algorithms, such as convolutional neural networks (CNN), require large amounts of labeled data. While data is often available in abundance, many tasks in surgical workflow analysis need annotations by domain experts, making it difficult to obtain a sufficient amount of annotations.The aim of using active learning to train a machine learning model is to reduce the annotation effort. Active learning methods determine which unlabeled data points would provide the most information according to some metric, such as prediction uncertainty. Experts will then be asked to only annotate these data points. The model is then retrained with the new data and used to select further data for annotation. Recently, active learning has been applied to CNN by means of deep Bayesian networks (DBN). These networks make it possible to assign uncertainties to predictions. In this paper, we present a DBN-based active learning approach adapted for image-based surgical workflow analysis task. Furthermore, by using a recurrent architecture, we extend this network to video-based surgical workflow analysis. To decide which data points should be labeled next, we explore and compare different metrics for expressing uncertainty.We evaluate these approaches and compare different metrics on the Cholec80 dataset by performing instrument presence detection and surgical phase segmentation. Here we are able to show that using a DBN-based active learning approach for selecting what data points to annotate next can significantly outperform a baseline based on randomly selecting data points. In particular, metrics such as entropy and variation ratio perform consistently on the different tasks.We show that using DBN-based active learning strategies make it possible to selectively annotate data, thereby reducing the required amount of labeled training in surgical workflow-related tasks." @default.
• W2964283648 created "2019-07-30" @default.
• W2964283648 creator A5003648994 @default.
• W2964283648 creator A5008345394 @default.
• W2964283648 creator A5014919291 @default.
• W2964283648 creator A5027275363 @default.
• W2964283648 creator A5034437528 @default.
• W2964283648 creator A5052772677 @default.
• W2964283648 creator A5056857657 @default.
• W2964283648 creator A5070201649 @default.
• W2964283648 creator A5086965439 @default.
• W2964283648 date "2019-04-09" @default.
• W2964283648 modified "2023-10-16" @default.
• W2964283648 title "Active learning using deep Bayesian networks for surgical workflow analysis" @default.
• W2964283648 cites W2016545368 @default.
• W2964283648 cites W2047607378 @default.
• W2964283648 cites W2064675550 @default.
• W2964283648 cites W2100592824 @default.
• W2964283648 cites W2168571645 @default.
• W2964283648 cites W2266464013 @default.
• W2964283648 cites W2488552272 @default.
• W2964283648 cites W2751405240 @default.
• W2964283648 cites W2777273430 @default.
• W2964283648 cites W2884036902 @default.
• W2964283648 cites W2895654826 @default.
• W2964283648 cites W2949071206 @default.
• W2964283648 cites W2962914239 @default.
• W2964283648 cites W2962936819 @default.
• W2964283648 cites W3102408484 @default.
• W2964283648 cites W4252684946 @default.
• W2964283648 doi "https://doi.org/10.1007/s11548-019-01963-9" @default.
• W2964283648 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30968355" @default.
• W2964283648 hasPublicationYear "2019" @default.
• W2964283648 type Work @default.
• W2964283648 sameAs 2964283648 @default.
• W2964283648 citedByCount "37" @default.
• W2964283648 countsByYear W29642836482020 @default.
• W2964283648 countsByYear W29642836482021 @default.
• W2964283648 countsByYear W29642836482022 @default.
• W2964283648 countsByYear W29642836482023 @default.
• W2964283648 crossrefType "journal-article" @default.
• W2964283648 hasAuthorship W2964283648A5003648994 @default.
• W2964283648 hasAuthorship W2964283648A5008345394 @default.
• W2964283648 hasAuthorship W2964283648A5014919291 @default.
• W2964283648 hasAuthorship W2964283648A5027275363 @default.
• W2964283648 hasAuthorship W2964283648A5034437528 @default.
• W2964283648 hasAuthorship W2964283648A5052772677 @default.
• W2964283648 hasAuthorship W2964283648A5056857657 @default.
• W2964283648 hasAuthorship W2964283648A5070201649 @default.
• W2964283648 hasAuthorship W2964283648A5086965439 @default.
• W2964283648 hasBestOaLocation W29642836482 @default.
• W2964283648 hasConcept C108583219 @default.
• W2964283648 hasConcept C119857082 @default.
• W2964283648 hasConcept C124101348 @default.
• W2964283648 hasConcept C154945302 @default.
• W2964283648 hasConcept C162324750 @default.
• W2964283648 hasConcept C176217482 @default.
• W2964283648 hasConcept C177212765 @default.
• W2964283648 hasConcept C21547014 @default.
• W2964283648 hasConcept C2776321320 @default.
• W2964283648 hasConcept C33724603 @default.
• W2964283648 hasConcept C41008148 @default.
• W2964283648 hasConcept C77088390 @default.
• W2964283648 hasConcept C81363708 @default.
• W2964283648 hasConcept C82142266 @default.
• W2964283648 hasConceptScore W2964283648C108583219 @default.
• W2964283648 hasConceptScore W2964283648C119857082 @default.
• W2964283648 hasConceptScore W2964283648C124101348 @default.
• W2964283648 hasConceptScore W2964283648C154945302 @default.
• W2964283648 hasConceptScore W2964283648C162324750 @default.
• W2964283648 hasConceptScore W2964283648C176217482 @default.
• W2964283648 hasConceptScore W2964283648C177212765 @default.
• W2964283648 hasConceptScore W2964283648C21547014 @default.
• W2964283648 hasConceptScore W2964283648C2776321320 @default.
• W2964283648 hasConceptScore W2964283648C33724603 @default.
• W2964283648 hasConceptScore W2964283648C41008148 @default.
• W2964283648 hasConceptScore W2964283648C77088390 @default.
• W2964283648 hasConceptScore W2964283648C81363708 @default.
• W2964283648 hasConceptScore W2964283648C82142266 @default.
• W2964283648 hasIssue "6" @default.
• W2964283648 hasLocation W29642836481 @default.
• W2964283648 hasLocation W29642836482 @default.
• W2964283648 hasLocation W29642836483 @default.
• W2964283648 hasOpenAccess W2964283648 @default.
• W2964283648 hasPrimaryLocation W29642836481 @default.
• W2964283648 hasRelatedWork W2731899572 @default.
• W2964283648 hasRelatedWork W2999805992 @default.
• W2964283648 hasRelatedWork W3116150086 @default.
• W2964283648 hasRelatedWork W3133861977 @default.
• W2964283648 hasRelatedWork W4200173597 @default.
• W2964283648 hasRelatedWork W4223943233 @default.
• W2964283648 hasRelatedWork W4291897433 @default.
• W2964283648 hasRelatedWork W4312417841 @default.
• W2964283648 hasRelatedWork W4321369474 @default.
• W2964283648 hasRelatedWork W4380075502 @default.
• W2964283648 hasVolume "14" @default.
• W2964283648 isParatext "false" @default.
• W2964283648 isRetracted "false" @default.

• next