FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090104167> ?p ?o ?g. }

• W3090104167 endingPage "6269" @default.
• W3090104167 startingPage "6257" @default.
• W3090104167 abstract "Purpose In medical image analysis, deep learning has great application potential. Discovering a method for extracting valuable information from medical images and integrating that information closely with medical treatment has recently become a major topic of interest. Because obtaining large volumes of breast lesion ultrasound image data is difficult, transfer learning is usually employed to obtain benign and malignant classification of breast lesions. However, because of blurred unclear regions of interest in breast lesion ultrasound images and severe speckle noise interference, convolutional neural networks have proven ineffective in extracting features, thus providing unreliable classification results. Methods This study employs image decomposition to obtain fuzzy enhanced and bilateral filtered images to enrich input information of breast lesions. Fuzzy enhanced, bilateral filtered, and original ultrasound images comprise multifeature data, which are presented as inputs to a pre‐trained model to realize knowledge fusion. Therefore, effective features of breast lesions are extracted and then used to train fully connected layers with ground truths provided by a doctor to accomplish the classification. Results A pre‐trained VGG16 model was used to extract features from multifeature data, and these features were fused to train the fully connected layers to realize classification. The performance score reported is as follows: accuracy of 93%, sensitivity of 95%, specificity of 88%, F1 score of 0.93, and AUC of 0.97. Conclusions Compared with using a single original ultrasound image for feature extraction, multifeature data based on image decomposition enables the pre‐trained model to extract more relevant features, thereby providing better classification results than those from traditional transfer learning techniques." @default.
• W3090104167 created "2020-10-08" @default.
• W3090104167 creator A5001905103 @default.
• W3090104167 creator A5028683328 @default.
• W3090104167 creator A5038348585 @default.
• W3090104167 creator A5042251884 @default.
• W3090104167 creator A5054999570 @default.
• W3090104167 creator A5064712079 @default.
• W3090104167 date "2020-10-20" @default.
• W3090104167 modified "2023-10-03" @default.
• W3090104167 title "Breast ultrasound lesion classification based on image decomposition and transfer learning" @default.
• W3090104167 cites W1982471090 @default.
• W3090104167 cites W2009022232 @default.
• W3090104167 cites W2110505741 @default.
• W3090104167 cites W2159269332 @default.
• W3090104167 cites W2165698076 @default.
• W3090104167 cites W2169949947 @default.
• W3090104167 cites W2183341477 @default.
• W3090104167 cites W2194775991 @default.
• W3090104167 cites W2588960758 @default.
• W3090104167 cites W2725008604 @default.
• W3090104167 cites W2740028789 @default.
• W3090104167 cites W2788508510 @default.
• W3090104167 cites W2889646458 @default.
• W3090104167 cites W2896124416 @default.
• W3090104167 cites W2973595854 @default.
• W3090104167 cites W4256291304 @default.
• W3090104167 doi "https://doi.org/10.1002/mp.14510" @default.
• W3090104167 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33012047" @default.
• W3090104167 hasPublicationYear "2020" @default.
• W3090104167 type Work @default.
• W3090104167 sameAs 3090104167 @default.
• W3090104167 citedByCount "16" @default.
• W3090104167 countsByYear W30901041672021 @default.
• W3090104167 countsByYear W30901041672022 @default.
• W3090104167 countsByYear W30901041672023 @default.
• W3090104167 crossrefType "journal-article" @default.
• W3090104167 hasAuthorship W3090104167A5001905103 @default.
• W3090104167 hasAuthorship W3090104167A5028683328 @default.
• W3090104167 hasAuthorship W3090104167A5038348585 @default.
• W3090104167 hasAuthorship W3090104167A5042251884 @default.
• W3090104167 hasAuthorship W3090104167A5054999570 @default.
• W3090104167 hasAuthorship W3090104167A5064712079 @default.
• W3090104167 hasConcept C102290492 @default.
• W3090104167 hasConcept C108583219 @default.
• W3090104167 hasConcept C115961682 @default.
• W3090104167 hasConcept C121608353 @default.
• W3090104167 hasConcept C126322002 @default.
• W3090104167 hasConcept C126838900 @default.
• W3090104167 hasConcept C138885662 @default.
• W3090104167 hasConcept C143753070 @default.
• W3090104167 hasConcept C150899416 @default.
• W3090104167 hasConcept C153180895 @default.
• W3090104167 hasConcept C154945302 @default.
• W3090104167 hasConcept C180940675 @default.
• W3090104167 hasConcept C2776401178 @default.
• W3090104167 hasConcept C2777423100 @default.
• W3090104167 hasConcept C2780472235 @default.
• W3090104167 hasConcept C31601959 @default.
• W3090104167 hasConcept C31972630 @default.
• W3090104167 hasConcept C41008148 @default.
• W3090104167 hasConcept C41895202 @default.
• W3090104167 hasConcept C52622490 @default.
• W3090104167 hasConcept C530470458 @default.
• W3090104167 hasConcept C58166 @default.
• W3090104167 hasConcept C71924100 @default.
• W3090104167 hasConcept C75294576 @default.
• W3090104167 hasConcept C81363708 @default.
• W3090104167 hasConceptScore W3090104167C102290492 @default.
• W3090104167 hasConceptScore W3090104167C108583219 @default.
• W3090104167 hasConceptScore W3090104167C115961682 @default.
• W3090104167 hasConceptScore W3090104167C121608353 @default.
• W3090104167 hasConceptScore W3090104167C126322002 @default.
• W3090104167 hasConceptScore W3090104167C126838900 @default.
• W3090104167 hasConceptScore W3090104167C138885662 @default.
• W3090104167 hasConceptScore W3090104167C143753070 @default.
• W3090104167 hasConceptScore W3090104167C150899416 @default.
• W3090104167 hasConceptScore W3090104167C153180895 @default.
• W3090104167 hasConceptScore W3090104167C154945302 @default.
• W3090104167 hasConceptScore W3090104167C180940675 @default.
• W3090104167 hasConceptScore W3090104167C2776401178 @default.
• W3090104167 hasConceptScore W3090104167C2777423100 @default.
• W3090104167 hasConceptScore W3090104167C2780472235 @default.
• W3090104167 hasConceptScore W3090104167C31601959 @default.
• W3090104167 hasConceptScore W3090104167C31972630 @default.
• W3090104167 hasConceptScore W3090104167C41008148 @default.
• W3090104167 hasConceptScore W3090104167C41895202 @default.
• W3090104167 hasConceptScore W3090104167C52622490 @default.
• W3090104167 hasConceptScore W3090104167C530470458 @default.
• W3090104167 hasConceptScore W3090104167C58166 @default.
• W3090104167 hasConceptScore W3090104167C71924100 @default.
• W3090104167 hasConceptScore W3090104167C75294576 @default.
• W3090104167 hasConceptScore W3090104167C81363708 @default.
• W3090104167 hasFunder F4320310972 @default.
• W3090104167 hasFunder F4320321001 @default.
• W3090104167 hasIssue "12" @default.
• W3090104167 hasLocation W30901041671 @default.
• W3090104167 hasOpenAccess W3090104167 @default.

• next