FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317708809> ?p ?o ?g. }

• W4317708809 endingPage "995" @default.
• W4317708809 startingPage "989" @default.
• W4317708809 abstract "Recently, deep learning using convolutional neural networks (CNNs) has yielded consistent results in image-pattern recognition. This study was aimed at investigating the effectiveness of deep learning using CNNs to differentiate benign and malignant breast masses identified by elastography on ultrasound screening. A data set of the elastography images of 245 breast masses (146 benign, 99 malignant) in 239 consecutive patients was retrospectively obtained. The data set was randomly split into training (55%), validation (25%) and test (20%) cohorts. A deep learning model predicting the probability of malignancy was constructed using GoogLeNet architectures (pre-trained by ImageNet) with 50 epochs. The model was then applied to the test data, and the results were compared with those obtained by evaluating the fat-to-lesion ratio (FLR) and by a 5-point visual color assessment (elasticity score). The receiver operating characteristic (ROC) curve was calculated to evaluate the performance of the model. The DeLong test was used to compare the areas under the ROC curve (AUCs). The CNN, FLR and elasticity score had a sensitivity of 0.800, 0.800 and 0.350; specificity of 0.966, 0.586 and 0.931; accuracy of 0.898, 0.673 and 0.694; positive predictive value of 0.941, 0.571 and 0.778; negative predictive value of 0.875, 0.810 and 0.675; and AUC of 0.895, 0.693 and 0.641, respectively. The AUC of the CNN was significantly higher than that of the FLR or elasticity score (p < 0.001). A CNN-based deep learning model for predicting benign or malignant breast masses revealed better diagnostic performance than did FLR or elasticity score-based estimations on ultrasound elastography. The CNN-based model also increased the positive predictive value from 57%–78% to 94%. Therefore, this model may reduce unnecessary biopsy recommendations for masses detected on breast ultrasound screening. Recently, deep learning using convolutional neural networks (CNNs) has yielded consistent results in image-pattern recognition. This study was aimed at investigating the effectiveness of deep learning using CNNs to differentiate benign and malignant breast masses identified by elastography on ultrasound screening. A data set of the elastography images of 245 breast masses (146 benign, 99 malignant) in 239 consecutive patients was retrospectively obtained. The data set was randomly split into training (55%), validation (25%) and test (20%) cohorts. A deep learning model predicting the probability of malignancy was constructed using GoogLeNet architectures (pre-trained by ImageNet) with 50 epochs. The model was then applied to the test data, and the results were compared with those obtained by evaluating the fat-to-lesion ratio (FLR) and by a 5-point visual color assessment (elasticity score). The receiver operating characteristic (ROC) curve was calculated to evaluate the performance of the model. The DeLong test was used to compare the areas under the ROC curve (AUCs). The CNN, FLR and elasticity score had a sensitivity of 0.800, 0.800 and 0.350; specificity of 0.966, 0.586 and 0.931; accuracy of 0.898, 0.673 and 0.694; positive predictive value of 0.941, 0.571 and 0.778; negative predictive value of 0.875, 0.810 and 0.675; and AUC of 0.895, 0.693 and 0.641, respectively. The AUC of the CNN was significantly higher than that of the FLR or elasticity score (p < 0.001). A CNN-based deep learning model for predicting benign or malignant breast masses revealed better diagnostic performance than did FLR or elasticity score-based estimations on ultrasound elastography. The CNN-based model also increased the positive predictive value from 57%–78% to 94%. Therefore, this model may reduce unnecessary biopsy recommendations for masses detected on breast ultrasound screening." @default.
• W4317708809 created "2023-01-23" @default.
• W4317708809 creator A5001210423 @default.
• W4317708809 creator A5002170800 @default.
• W4317708809 creator A5011495833 @default.
• W4317708809 creator A5012584917 @default.
• W4317708809 creator A5053032425 @default.
• W4317708809 creator A5064584031 @default.
• W4317708809 date "2023-04-01" @default.
• W4317708809 modified "2023-10-01" @default.
• W4317708809 title "Deep Learning for Differentiation of Breast Masses Detected by Screening Ultrasound Elastography" @default.
• W4317708809 cites W1864297777 @default.
• W4317708809 cites W1961632191 @default.
• W4317708809 cites W1969281710 @default.
• W4317708809 cites W1972275693 @default.
• W4317708809 cites W1976937402 @default.
• W4317708809 cites W1994060445 @default.
• W4317708809 cites W2000772884 @default.
• W4317708809 cites W2017439667 @default.
• W4317708809 cites W2026218860 @default.
• W4317708809 cites W2032385383 @default.
• W4317708809 cites W2036769582 @default.
• W4317708809 cites W2044167357 @default.
• W4317708809 cites W2050902205 @default.
• W4317708809 cites W2074711425 @default.
• W4317708809 cites W2098947733 @default.
• W4317708809 cites W2102804137 @default.
• W4317708809 cites W2121960517 @default.
• W4317708809 cites W2132290789 @default.
• W4317708809 cites W2149988868 @default.
• W4317708809 cites W2153099981 @default.
• W4317708809 cites W2155329254 @default.
• W4317708809 cites W2156110922 @default.
• W4317708809 cites W2167669297 @default.
• W4317708809 cites W2474943170 @default.
• W4317708809 cites W2608231518 @default.
• W4317708809 cites W2740028789 @default.
• W4317708809 cites W2919115771 @default.
• W4317708809 cites W2939142770 @default.
• W4317708809 cites W3033243763 @default.
• W4317708809 doi "https://doi.org/10.1016/j.ultrasmedbio.2022.12.003" @default.
• W4317708809 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36681608" @default.
• W4317708809 hasPublicationYear "2023" @default.
• W4317708809 type Work @default.
• W4317708809 citedByCount "0" @default.
• W4317708809 crossrefType "journal-article" @default.
• W4317708809 hasAuthorship W4317708809A5001210423 @default.
• W4317708809 hasAuthorship W4317708809A5002170800 @default.
• W4317708809 hasAuthorship W4317708809A5011495833 @default.
• W4317708809 hasAuthorship W4317708809A5012584917 @default.
• W4317708809 hasAuthorship W4317708809A5053032425 @default.
• W4317708809 hasAuthorship W4317708809A5064584031 @default.
• W4317708809 hasBestOaLocation W43177088091 @default.
• W4317708809 hasConcept C108583219 @default.
• W4317708809 hasConcept C112705442 @default.
• W4317708809 hasConcept C121608353 @default.
• W4317708809 hasConcept C126322002 @default.
• W4317708809 hasConcept C126838900 @default.
• W4317708809 hasConcept C143753070 @default.
• W4317708809 hasConcept C154945302 @default.
• W4317708809 hasConcept C169903167 @default.
• W4317708809 hasConcept C2777423100 @default.
• W4317708809 hasConcept C2777432617 @default.
• W4317708809 hasConcept C2777690781 @default.
• W4317708809 hasConcept C2779098232 @default.
• W4317708809 hasConcept C2779399171 @default.
• W4317708809 hasConcept C2780472235 @default.
• W4317708809 hasConcept C2984842247 @default.
• W4317708809 hasConcept C3020225094 @default.
• W4317708809 hasConcept C41008148 @default.
• W4317708809 hasConcept C530470458 @default.
• W4317708809 hasConcept C58471807 @default.
• W4317708809 hasConcept C71924100 @default.
• W4317708809 hasConcept C76318530 @default.
• W4317708809 hasConcept C81363708 @default.
• W4317708809 hasConceptScore W4317708809C108583219 @default.
• W4317708809 hasConceptScore W4317708809C112705442 @default.
• W4317708809 hasConceptScore W4317708809C121608353 @default.
• W4317708809 hasConceptScore W4317708809C126322002 @default.
• W4317708809 hasConceptScore W4317708809C126838900 @default.
• W4317708809 hasConceptScore W4317708809C143753070 @default.
• W4317708809 hasConceptScore W4317708809C154945302 @default.
• W4317708809 hasConceptScore W4317708809C169903167 @default.
• W4317708809 hasConceptScore W4317708809C2777423100 @default.
• W4317708809 hasConceptScore W4317708809C2777432617 @default.
• W4317708809 hasConceptScore W4317708809C2777690781 @default.
• W4317708809 hasConceptScore W4317708809C2779098232 @default.
• W4317708809 hasConceptScore W4317708809C2779399171 @default.
• W4317708809 hasConceptScore W4317708809C2780472235 @default.
• W4317708809 hasConceptScore W4317708809C2984842247 @default.
• W4317708809 hasConceptScore W4317708809C3020225094 @default.
• W4317708809 hasConceptScore W4317708809C41008148 @default.
• W4317708809 hasConceptScore W4317708809C530470458 @default.
• W4317708809 hasConceptScore W4317708809C58471807 @default.
• W4317708809 hasConceptScore W4317708809C71924100 @default.
• W4317708809 hasConceptScore W4317708809C76318530 @default.
• W4317708809 hasConceptScore W4317708809C81363708 @default.
• W4317708809 hasIssue "4" @default.

• next