FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892235178> ?p ?o ?g. }

• W2892235178 endingPage "696" @default.
• W2892235178 startingPage "686" @default.
• W2892235178 abstract "In this paper, we developed a deep convolutional neural network (CNN) for the classification of malignant and benign masses in digital breast tomosynthesis (DBT) using a multi-stage transfer learning approach that utilized data from similar auxiliary domains for intermediate-stage fine-tuning. Breast imaging data from DBT, digitized screen-film mammography, and digital mammography totaling 4039 unique regions of interest (1797 malignant and 2242 benign) were collected. Using cross validation, we selected the best transfer network from six transfer networks by varying the level up to which the convolutional layers were frozen. In a single-stage transfer learning approach, knowledge from CNN trained on the ImageNet data was fine-tuned directly with the DBT data. In a multi-stage transfer learning approach, knowledge learned from ImageNet was first fine-tuned with the mammography data and then fine-tuned with the DBT data. Two transfer networks were compared for the second-stage transfer learning by freezing most of the CNN structures versus freezing only the first convolutional layer. We studied the dependence of the classification performance on training sample size for various transfer learning and fine-tuning schemes by varying the training data from 1% to 100% of the available sets. The area under the receiver operating characteristic curve (AUC) was used as a performance measure. The view-based AUC on the test set for single-stage transfer learning was 0.85 ± 0.05 and improved significantly (p <; 0.05$ ) to 0.91 ± 0.03 for multi-stage learning. This paper demonstrated that, when the training sample size from the target domain is limited, an additional stage of transfer learning using data from a similar auxiliary domain is advantageous." @default.
• W2892235178 created "2018-09-27" @default.
• W2892235178 creator A5002172019 @default.
• W2892235178 creator A5019785665 @default.
• W2892235178 creator A5027247097 @default.
• W2892235178 creator A5037712788 @default.
• W2892235178 creator A5045764453 @default.
• W2892235178 creator A5073769753 @default.
• W2892235178 date "2019-03-01" @default.
• W2892235178 modified "2023-10-17" @default.
• W2892235178 title "Breast Cancer Diagnosis in Digital Breast Tomosynthesis: Effects of Training Sample Size on Multi-Stage Transfer Learning Using Deep Neural Nets" @default.
• W2892235178 cites W1963790578 @default.
• W2892235178 cites W1975722015 @default.
• W2892235178 cites W1986649315 @default.
• W2892235178 cites W1988452762 @default.
• W2892235178 cites W1996777040 @default.
• W2892235178 cites W2002467976 @default.
• W2892235178 cites W2004007088 @default.
• W2892235178 cites W2015056255 @default.
• W2892235178 cites W2031991286 @default.
• W2892235178 cites W2038037430 @default.
• W2892235178 cites W2044196319 @default.
• W2892235178 cites W2059192589 @default.
• W2892235178 cites W2059331675 @default.
• W2892235178 cites W2075723934 @default.
• W2892235178 cites W2082684500 @default.
• W2892235178 cites W2083927153 @default.
• W2892235178 cites W2084161499 @default.
• W2892235178 cites W2112525988 @default.
• W2892235178 cites W2157117929 @default.
• W2892235178 cites W2158799176 @default.
• W2892235178 cites W2161381512 @default.
• W2892235178 cites W2280541663 @default.
• W2892235178 cites W2523374085 @default.
• W2892235178 cites W2559553341 @default.
• W2892235178 cites W2573334707 @default.
• W2892235178 cites W2587143428 @default.
• W2892235178 cites W2592929672 @default.
• W2892235178 cites W2767016695 @default.
• W2892235178 cites W2962843773 @default.
• W2892235178 cites W4244806232 @default.
• W2892235178 doi "https://doi.org/10.1109/tmi.2018.2870343" @default.
• W2892235178 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6812655" @default.
• W2892235178 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31622238" @default.
• W2892235178 hasPublicationYear "2019" @default.
• W2892235178 type Work @default.
• W2892235178 sameAs 2892235178 @default.
• W2892235178 citedByCount "134" @default.
• W2892235178 countsByYear W28922351782019 @default.
• W2892235178 countsByYear W28922351782020 @default.
• W2892235178 countsByYear W28922351782021 @default.
• W2892235178 countsByYear W28922351782022 @default.
• W2892235178 countsByYear W28922351782023 @default.
• W2892235178 crossrefType "journal-article" @default.
• W2892235178 hasAuthorship W2892235178A5002172019 @default.
• W2892235178 hasAuthorship W2892235178A5019785665 @default.
• W2892235178 hasAuthorship W2892235178A5027247097 @default.
• W2892235178 hasAuthorship W2892235178A5037712788 @default.
• W2892235178 hasAuthorship W2892235178A5045764453 @default.
• W2892235178 hasAuthorship W2892235178A5073769753 @default.
• W2892235178 hasBestOaLocation W28922351782 @default.
• W2892235178 hasConcept C108583219 @default.
• W2892235178 hasConcept C119857082 @default.
• W2892235178 hasConcept C121608353 @default.
• W2892235178 hasConcept C126322002 @default.
• W2892235178 hasConcept C146357865 @default.
• W2892235178 hasConcept C150899416 @default.
• W2892235178 hasConcept C151730666 @default.
• W2892235178 hasConcept C153180895 @default.
• W2892235178 hasConcept C154945302 @default.
• W2892235178 hasConcept C2780472235 @default.
• W2892235178 hasConcept C41008148 @default.
• W2892235178 hasConcept C50644808 @default.
• W2892235178 hasConcept C530470458 @default.
• W2892235178 hasConcept C58471807 @default.
• W2892235178 hasConcept C71924100 @default.
• W2892235178 hasConcept C81363708 @default.
• W2892235178 hasConcept C86803240 @default.
• W2892235178 hasConceptScore W2892235178C108583219 @default.
• W2892235178 hasConceptScore W2892235178C119857082 @default.
• W2892235178 hasConceptScore W2892235178C121608353 @default.
• W2892235178 hasConceptScore W2892235178C126322002 @default.
• W2892235178 hasConceptScore W2892235178C146357865 @default.
• W2892235178 hasConceptScore W2892235178C150899416 @default.
• W2892235178 hasConceptScore W2892235178C151730666 @default.
• W2892235178 hasConceptScore W2892235178C153180895 @default.
• W2892235178 hasConceptScore W2892235178C154945302 @default.
• W2892235178 hasConceptScore W2892235178C2780472235 @default.
• W2892235178 hasConceptScore W2892235178C41008148 @default.
• W2892235178 hasConceptScore W2892235178C50644808 @default.
• W2892235178 hasConceptScore W2892235178C530470458 @default.
• W2892235178 hasConceptScore W2892235178C58471807 @default.
• W2892235178 hasConceptScore W2892235178C71924100 @default.
• W2892235178 hasConceptScore W2892235178C81363708 @default.
• W2892235178 hasConceptScore W2892235178C86803240 @default.
• W2892235178 hasFunder F4320332161 @default.
• W2892235178 hasIssue "3" @default.
• W2892235178 hasLocation W28922351781 @default.

• next