Matches in SemOpenAlex for { <https://semopenalex.org/work/W3101476080> ?p ?o ?g. }
- W3101476080 endingPage "566" @default.
- W3101476080 startingPage "556" @default.
- W3101476080 abstract "This work presents a novel approach for the early recognition of the type of a laparoscopic surgery from its video. Early recognition algorithms can be beneficial to the development of 'smart' OR systems that can provide automatic context-aware assistance, and also enable quick database indexing. The task is however ridden with challenges specific to videos belonging to the domain of laparoscopy, such as high visual similarity across surgeries and large variations in video durations. To capture the spatio-temporal dependencies in these videos, we choose as our model a combination of a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network. We then propose two complementary approaches for improving early recognition performance. The first approach is a CNN fine-tuning method that encourages surgeries to be distinguished based on the initial frames of laparoscopic videos. The second approach, referred to as 'Future-State Predicting LSTM', trains an LSTM to predict information related to future frames, which helps in distinguishing between the different types of surgeries. We evaluate our approaches on a large dataset of 425 laparoscopic videos containing 9 types of surgeries (Laparo425), and achieve on average an accuracy of 75% having observed only the first 10 minutes of a surgery. These results are quite promising from a practical standpoint and also encouraging for other types of image-guided surgeries." @default.
- W3101476080 created "2020-11-23" @default.
- W3101476080 creator A5001288886 @default.
- W3101476080 creator A5015981897 @default.
- W3101476080 creator A5040194824 @default.
- W3101476080 creator A5071976104 @default.
- W3101476080 creator A5081252567 @default.
- W3101476080 date "2020-03-01" @default.
- W3101476080 modified "2023-10-15" @default.
- W3101476080 title "Future-State Predicting LSTM for Early Surgery Type Recognition" @default.
- W3101476080 cites W100441416 @default.
- W3101476080 cites W2064675550 @default.
- W3101476080 cites W2105101328 @default.
- W3101476080 cites W2127069950 @default.
- W3101476080 cites W2142194269 @default.
- W3101476080 cites W2194775991 @default.
- W3101476080 cites W2216536810 @default.
- W3101476080 cites W2266464013 @default.
- W3101476080 cites W2422305492 @default.
- W3101476080 cites W2507009361 @default.
- W3101476080 cites W2600088275 @default.
- W3101476080 cites W2605300166 @default.
- W3101476080 cites W2606308270 @default.
- W3101476080 cites W2963692464 @default.
- W3101476080 cites W72393350 @default.
- W3101476080 doi "https://doi.org/10.1109/tmi.2019.2931158" @default.
- W3101476080 hasPublicationYear "2020" @default.
- W3101476080 type Work @default.
- W3101476080 sameAs 3101476080 @default.
- W3101476080 citedByCount "21" @default.
- W3101476080 countsByYear W31014760802019 @default.
- W3101476080 countsByYear W31014760802020 @default.
- W3101476080 countsByYear W31014760802021 @default.
- W3101476080 countsByYear W31014760802022 @default.
- W3101476080 countsByYear W31014760802023 @default.
- W3101476080 crossrefType "journal-article" @default.
- W3101476080 hasAuthorship W3101476080A5001288886 @default.
- W3101476080 hasAuthorship W3101476080A5015981897 @default.
- W3101476080 hasAuthorship W3101476080A5040194824 @default.
- W3101476080 hasAuthorship W3101476080A5071976104 @default.
- W3101476080 hasAuthorship W3101476080A5081252567 @default.
- W3101476080 hasBestOaLocation W31014760802 @default.
- W3101476080 hasConcept C108583219 @default.
- W3101476080 hasConcept C119857082 @default.
- W3101476080 hasConcept C134306372 @default.
- W3101476080 hasConcept C147168706 @default.
- W3101476080 hasConcept C151730666 @default.
- W3101476080 hasConcept C153180895 @default.
- W3101476080 hasConcept C154945302 @default.
- W3101476080 hasConcept C162324750 @default.
- W3101476080 hasConcept C187736073 @default.
- W3101476080 hasConcept C2779343474 @default.
- W3101476080 hasConcept C2780451532 @default.
- W3101476080 hasConcept C33923547 @default.
- W3101476080 hasConcept C36503486 @default.
- W3101476080 hasConcept C41008148 @default.
- W3101476080 hasConcept C50644808 @default.
- W3101476080 hasConcept C75165309 @default.
- W3101476080 hasConcept C81363708 @default.
- W3101476080 hasConcept C86803240 @default.
- W3101476080 hasConceptScore W3101476080C108583219 @default.
- W3101476080 hasConceptScore W3101476080C119857082 @default.
- W3101476080 hasConceptScore W3101476080C134306372 @default.
- W3101476080 hasConceptScore W3101476080C147168706 @default.
- W3101476080 hasConceptScore W3101476080C151730666 @default.
- W3101476080 hasConceptScore W3101476080C153180895 @default.
- W3101476080 hasConceptScore W3101476080C154945302 @default.
- W3101476080 hasConceptScore W3101476080C162324750 @default.
- W3101476080 hasConceptScore W3101476080C187736073 @default.
- W3101476080 hasConceptScore W3101476080C2779343474 @default.
- W3101476080 hasConceptScore W3101476080C2780451532 @default.
- W3101476080 hasConceptScore W3101476080C33923547 @default.
- W3101476080 hasConceptScore W3101476080C36503486 @default.
- W3101476080 hasConceptScore W3101476080C41008148 @default.
- W3101476080 hasConceptScore W3101476080C50644808 @default.
- W3101476080 hasConceptScore W3101476080C75165309 @default.
- W3101476080 hasConceptScore W3101476080C81363708 @default.
- W3101476080 hasConceptScore W3101476080C86803240 @default.
- W3101476080 hasFunder F4320320883 @default.
- W3101476080 hasIssue "3" @default.
- W3101476080 hasLocation W31014760801 @default.
- W3101476080 hasLocation W31014760802 @default.
- W3101476080 hasLocation W31014760803 @default.
- W3101476080 hasLocation W31014760804 @default.
- W3101476080 hasLocation W31014760805 @default.
- W3101476080 hasOpenAccess W3101476080 @default.
- W3101476080 hasPrimaryLocation W31014760801 @default.
- W3101476080 hasRelatedWork W2337926734 @default.
- W3101476080 hasRelatedWork W2732542196 @default.
- W3101476080 hasRelatedWork W2738221750 @default.
- W3101476080 hasRelatedWork W2793022090 @default.
- W3101476080 hasRelatedWork W3156786002 @default.
- W3101476080 hasRelatedWork W4298168912 @default.
- W3101476080 hasRelatedWork W4311257506 @default.
- W3101476080 hasRelatedWork W4320802194 @default.
- W3101476080 hasRelatedWork W4366224123 @default.
- W3101476080 hasRelatedWork W564581980 @default.
- W3101476080 hasVolume "39" @default.