Evaluation of deep learning techniques on a novel hierarchical surgical tool dataset

Simple item page
dc.contributor.authorRodrigues, Mark Williamen_NZ
dc.contributor.authorMayo, Michaelen_NZ
dc.contributor.authorPatros, Panosen_NZ
dc.contributor.editorLong, G.en_NZ
dc.contributor.editorYu, X.en_NZ
dc.contributor.editorWang, S.en_NZ
dc.coverage.spatialCham, Switzerlanden_NZ
dc.date.accessioned2022-07-26T20:42:03Z
dc.date.available2022-07-26T20:42:03Z
dc.date.issued2022en_NZ
dc.description.abstractA new hierarchically organised dataset for artificial intelligence and machine learning research is presented, focusing on intelligent management of surgical tools. In addition to 360 surgical tool classes, we create a four level hierarchical structure for our dataset defined by 2 specialities, 12 packs and 35 sets. We employ different convolutional neural network training strategies to evaluate image classification and retrieval performance on this dataset, including the utilisation of prior information in the form of a taxonomic hierarchy tree structure. We evaluate the effects of image size and the number of images per class on model predictive performance. Experiments with the mapping of image features and class embeddings in semantic space using measures of semantic similarity between classes show that providing prior information results in a significant improvement in image retrieval performance on our dataset.
dc.format.mimetypeapplication/pdf
dc.identifier.doi10.1007/978-3-030-97546-3_14en_NZ
dc.identifier.eissn1611-3349en_NZ
dc.identifier.isbn978-3-030-97545-6en_NZ
dc.identifier.issn0302-9743en_NZ
dc.identifier.urihttps://hdl.handle.net/10289/14991
dc.language.isoen
dc.publisherSpringer Nature Switzerland AGen_NZ
dc.relation.isPartOfAI 2021: ADVANCES IN ARTIFICIAL INTELLIGENCEen_NZ
dc.rights©2022 Springer Nature Switzerland AG.This is the author's accepted version. The final publication is available at Springer via dx.doi.org/10.1007/978-3-030-97546-3_14
dc.source34th Australasian Joint Conference on Artificial Intelligence (AI)en_NZ
dc.subjectScience & Technologyen_NZ
dc.subjectTechnologyen_NZ
dc.subjectComputer Science, Artificial Intelligenceen_NZ
dc.subjectComputer Scienceen_NZ
dc.subjectSurgical tool dataseten_NZ
dc.subjectSemantic similarityen_NZ
dc.subjectHierarchy treeen_NZ
dc.subjectSurgery hierarchyen_NZ
dc.subjectSURGERYen_NZ
dc.titleEvaluation of deep learning techniques on a novel hierarchical surgical tool dataseten_NZ
dc.typeConference Contribution
pubs.begin-page169
pubs.elements-id264975
pubs.end-page180
pubs.finish-date2022-02-04en_NZ
pubs.organisational-group/Waikato
pubs.organisational-group/Waikato/2025 PBRF
pubs.organisational-group/Waikato/DHECS
pubs.organisational-group/Waikato/DHECS/2025 PBRF - DHEC
pubs.organisational-group/Waikato/DHECS/SCMS
pubs.organisational-group/Waikato/DHECS/SCMS/2025 PBRF - SCMS
pubs.organisational-group/Waikato/DHECS/SHEA
pubs.publication-statusPublisheden_NZ
pubs.start-date2022-02-02en_NZ
pubs.user.infoPatros, Panagiotis (ppatros@waikato.ac.nz)
pubs.user.infoMayo, Michael (mmayo@waikato.ac.nz)
pubs.user.infoRodrigues, Mark (mrodrigu@waikato.ac.nz)
pubs.volume13151en_NZ
uow.verification.statusverified
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
AJCAI_Final_paper.pdf
Size:
389.22 KB
Format:
Adobe Portable Document Format
Description:
Accepted version
Thumbnail Image
Name: AJCAI_Final_paper.pdf
Size: 389.22 KB
Kind: Adobe PDF
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Research Commons Deposit Agreement 2017.pdf
Size:
188.11 KB
Format:
Adobe Portable Document Format
Description:
Name: Research Commons Deposit Agreement 2017.pdf
Size: 188.11 KB
Kind: Adobe PDF
Collections
Computing and Mathematical Sciences Papers