FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2985490935> ?p ?o ?g. }

• W2985490935 abstract "Multiple instance learning (MIL) is a supervised learning methodology that aims to allow models to learn instance class labels from bag class labels, where a bag is defined to contain multiple instances. MIL is gaining traction for learning from weak labels but has not been widely applied to 3D medical imaging. MIL is well-suited to clinical CT acquisitions since (1) the highly anisotropic voxels hinder application of traditional 3D networks and (2) patch-based networks have limited ability to learn whole volume labels. In this work, we apply MIL with a deep convolutional neural network to identify whether clinical CT head image volumes possess one or more large hemorrhages (> 20cm$^3$), resulting in a learned 2D model without the need for 2D slice annotations. Individual image volumes are considered separate bags, and the slices in each volume are instances. Such a framework sets the stage for incorporating information obtained in clinical reports to help train a 2D segmentation approach. Within this context, we evaluate the data requirements to enable generalization of MIL by varying the amount of training data. Our results show that a training size of at least 400 patient image volumes was needed to achieve accurate per-slice hemorrhage detection. Over a five-fold cross-validation, the leading model, which made use of the maximum number of training volumes, had an average true positive rate of 98.10%, an average true negative rate of 99.36%, and an average precision of 0.9698. The models have been made available along with source code to enabled continued exploration and adaption of MIL in CT neuroimaging." @default.
• W2985490935 created "2019-11-22" @default.
• W2985490935 creator A5005891853 @default.
• W2985490935 creator A5010406734 @default.
• W2985490935 creator A5012909412 @default.
• W2985490935 creator A5018571955 @default.
• W2985490935 creator A5025305700 @default.
• W2985490935 creator A5026908064 @default.
• W2985490935 creator A5068129399 @default.
• W2985490935 creator A5075735203 @default.
• W2985490935 creator A5077742771 @default.
• W2985490935 date "2019-11-13" @default.
• W2985490935 modified "2023-09-26" @default.
• W2985490935 title "Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection" @default.
• W2985490935 cites W1261214144 @default.
• W2985490935 cites W1938425378 @default.
• W2985490935 cites W2036200541 @default.
• W2985490935 cites W2110119381 @default.
• W2985490935 cites W2112467442 @default.
• W2985490935 cites W2150487955 @default.
• W2985490935 cites W2290321704 @default.
• W2985490935 cites W2306541384 @default.
• W2985490935 cites W2344858100 @default.
• W2985490935 cites W2402144811 @default.
• W2985490935 cites W2468387181 @default.
• W2985490935 cites W2523005792 @default.
• W2985490935 cites W2525205678 @default.
• W2985490935 cites W2621042378 @default.
• W2985490935 cites W2804540468 @default.
• W2985490935 cites W2891378267 @default.
• W2985490935 cites W2915396376 @default.
• W2985490935 cites W2920884867 @default.
• W2985490935 cites W2949650786 @default.
• W2985490935 cites W2952234052 @default.
• W2985490935 cites W2963122731 @default.
• W2985490935 cites W2963610932 @default.
• W2985490935 cites W2964227007 @default.
• W2985490935 cites W2964275459 @default.
• W2985490935 cites W2769910914 @default.
• W2985490935 hasPublicationYear "2019" @default.
• W2985490935 type Work @default.
• W2985490935 sameAs 2985490935 @default.
• W2985490935 citedByCount "0" @default.
• W2985490935 crossrefType "posted-content" @default.
• W2985490935 hasAuthorship W2985490935A5005891853 @default.
• W2985490935 hasAuthorship W2985490935A5010406734 @default.
• W2985490935 hasAuthorship W2985490935A5012909412 @default.
• W2985490935 hasAuthorship W2985490935A5018571955 @default.
• W2985490935 hasAuthorship W2985490935A5025305700 @default.
• W2985490935 hasAuthorship W2985490935A5026908064 @default.
• W2985490935 hasAuthorship W2985490935A5068129399 @default.
• W2985490935 hasAuthorship W2985490935A5075735203 @default.
• W2985490935 hasAuthorship W2985490935A5077742771 @default.
• W2985490935 hasConcept C108583219 @default.
• W2985490935 hasConcept C115961682 @default.
• W2985490935 hasConcept C119857082 @default.
• W2985490935 hasConcept C121332964 @default.
• W2985490935 hasConcept C134306372 @default.
• W2985490935 hasConcept C151730666 @default.
• W2985490935 hasConcept C153180895 @default.
• W2985490935 hasConcept C154945302 @default.
• W2985490935 hasConcept C177148314 @default.
• W2985490935 hasConcept C20556612 @default.
• W2985490935 hasConcept C2777212361 @default.
• W2985490935 hasConcept C2779343474 @default.
• W2985490935 hasConcept C33923547 @default.
• W2985490935 hasConcept C41008148 @default.
• W2985490935 hasConcept C50644808 @default.
• W2985490935 hasConcept C54170458 @default.
• W2985490935 hasConcept C62520636 @default.
• W2985490935 hasConcept C81363708 @default.
• W2985490935 hasConcept C86803240 @default.
• W2985490935 hasConcept C89600930 @default.
• W2985490935 hasConceptScore W2985490935C108583219 @default.
• W2985490935 hasConceptScore W2985490935C115961682 @default.
• W2985490935 hasConceptScore W2985490935C119857082 @default.
• W2985490935 hasConceptScore W2985490935C121332964 @default.
• W2985490935 hasConceptScore W2985490935C134306372 @default.
• W2985490935 hasConceptScore W2985490935C151730666 @default.
• W2985490935 hasConceptScore W2985490935C153180895 @default.
• W2985490935 hasConceptScore W2985490935C154945302 @default.
• W2985490935 hasConceptScore W2985490935C177148314 @default.
• W2985490935 hasConceptScore W2985490935C20556612 @default.
• W2985490935 hasConceptScore W2985490935C2777212361 @default.
• W2985490935 hasConceptScore W2985490935C2779343474 @default.
• W2985490935 hasConceptScore W2985490935C33923547 @default.
• W2985490935 hasConceptScore W2985490935C41008148 @default.
• W2985490935 hasConceptScore W2985490935C50644808 @default.
• W2985490935 hasConceptScore W2985490935C54170458 @default.
• W2985490935 hasConceptScore W2985490935C62520636 @default.
• W2985490935 hasConceptScore W2985490935C81363708 @default.
• W2985490935 hasConceptScore W2985490935C86803240 @default.
• W2985490935 hasConceptScore W2985490935C89600930 @default.
• W2985490935 hasOpenAccess W2985490935 @default.
• W2985490935 hasRelatedWork W2403658856 @default.
• W2985490935 hasRelatedWork W2611197392 @default.
• W2985490935 hasRelatedWork W2793307712 @default.
• W2985490935 hasRelatedWork W2883718946 @default.
• W2985490935 hasRelatedWork W2956648989 @default.
• W2985490935 hasRelatedWork W2966739465 @default.

• next