FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890596001> ?p ?o ?g. }

• W2890596001 abstract "In the U.S., breast cancer is diagnosed in about 12 % of women during their lifetime and it is the second leading reason for women's death. Since early diagnosis could improve treatment outcomes and longer survival times for breast cancer patients, it is significant to develop breast cancer detection techniques. The Convolutional Neural Network (CNN) can extract features from images automatically and then perform classification. To train the CNN from scratch, however, requires a large number of labeled images, which is infeasible for some kinds of medical image data such as mammographic tumor images. A promising solution is to apply transfer learning in CNN. In this paper, we firstly tested three training methods on the MIAS database: 1) trained a CNN from scratch, 2) applied the pre-trained VGG-16 model to extract features from input mammograms and used these features to train a Neural Network (NN)-classifier, 3) updated the weights in several final layers of the pre-trained VGG-16 model by back-propagation (fine-tuning) to detect abnormal regions. We found that method 2) is ideal for study because the classification accuracy of fine-tuning model was just 0.008 higher than that of feature extraction model but time cost of feature extraction model was only about 5% of that of the fine-tuning model. Then, we used method 2) to classify regions: benign vs. normal, malignant vs. normal and abnormal vs. normal from the DDSM database with 10-fold cross validation. The average validation accuracy converged at about 0.905 for abnormal vs. normal cases, and there was no obvious overfitting. This study shows that applying transfer learning in CNN can detect breast cancer from mammograms, and training a NN-classifier by feature extraction is a faster method in transfer learning." @default.
• W2890596001 created "2018-09-27" @default.
• W2890596001 creator A5020362391 @default.
• W2890596001 creator A5071064016 @default.
• W2890596001 date "2017-10-01" @default.
• W2890596001 modified "2023-10-06" @default.
• W2890596001 title "Breast Cancer Detection Using Transfer Learning in Convolutional Neural Networks" @default.
• W2890596001 cites W1516595210 @default.
• W2890596001 cites W1570613334 @default.
• W2890596001 cites W16705017 @default.
• W2890596001 cites W1677182931 @default.
• W2890596001 cites W1822639386 @default.
• W2890596001 cites W1830454849 @default.
• W2890596001 cites W1912954554 @default.
• W2890596001 cites W1920702274 @default.
• W2890596001 cites W1982896147 @default.
• W2890596001 cites W2063217105 @default.
• W2890596001 cites W2084369411 @default.
• W2890596001 cites W2084783417 @default.
• W2890596001 cites W2112467442 @default.
• W2890596001 cites W2113641540 @default.
• W2890596001 cites W2117539524 @default.
• W2890596001 cites W2120580182 @default.
• W2890596001 cites W2149291062 @default.
• W2890596001 cites W2235523093 @default.
• W2890596001 cites W2253429366 @default.
• W2890596001 cites W2299565249 @default.
• W2890596001 cites W2310869573 @default.
• W2890596001 cites W2339197954 @default.
• W2890596001 cites W2345524222 @default.
• W2890596001 cites W2346062110 @default.
• W2890596001 cites W2400264455 @default.
• W2890596001 cites W2527654160 @default.
• W2890596001 cites W2581082771 @default.
• W2890596001 cites W2583337654 @default.
• W2890596001 cites W2605260836 @default.
• W2890596001 cites W948663339 @default.
• W2890596001 doi "https://doi.org/10.1109/aipr.2017.8457948" @default.
• W2890596001 hasPublicationYear "2017" @default.
• W2890596001 type Work @default.
• W2890596001 sameAs 2890596001 @default.
• W2890596001 citedByCount "35" @default.
• W2890596001 countsByYear W28905960012019 @default.
• W2890596001 countsByYear W28905960012020 @default.
• W2890596001 countsByYear W28905960012021 @default.
• W2890596001 countsByYear W28905960012022 @default.
• W2890596001 countsByYear W28905960012023 @default.
• W2890596001 crossrefType "proceedings-article" @default.
• W2890596001 hasAuthorship W2890596001A5020362391 @default.
• W2890596001 hasAuthorship W2890596001A5071064016 @default.
• W2890596001 hasConcept C119857082 @default.
• W2890596001 hasConcept C121608353 @default.
• W2890596001 hasConcept C126322002 @default.
• W2890596001 hasConcept C150899416 @default.
• W2890596001 hasConcept C154945302 @default.
• W2890596001 hasConcept C2985322473 @default.
• W2890596001 hasConcept C41008148 @default.
• W2890596001 hasConcept C50644808 @default.
• W2890596001 hasConcept C530470458 @default.
• W2890596001 hasConcept C71924100 @default.
• W2890596001 hasConcept C81363708 @default.
• W2890596001 hasConceptScore W2890596001C119857082 @default.
• W2890596001 hasConceptScore W2890596001C121608353 @default.
• W2890596001 hasConceptScore W2890596001C126322002 @default.
• W2890596001 hasConceptScore W2890596001C150899416 @default.
• W2890596001 hasConceptScore W2890596001C154945302 @default.
• W2890596001 hasConceptScore W2890596001C2985322473 @default.
• W2890596001 hasConceptScore W2890596001C41008148 @default.
• W2890596001 hasConceptScore W2890596001C50644808 @default.
• W2890596001 hasConceptScore W2890596001C530470458 @default.
• W2890596001 hasConceptScore W2890596001C71924100 @default.
• W2890596001 hasConceptScore W2890596001C81363708 @default.
• W2890596001 hasLocation W28905960011 @default.
• W2890596001 hasOpenAccess W2890596001 @default.
• W2890596001 hasPrimaryLocation W28905960011 @default.
• W2890596001 hasRelatedWork W2972069047 @default.
• W2890596001 hasRelatedWork W3012393889 @default.
• W2890596001 hasRelatedWork W3014041368 @default.
• W2890596001 hasRelatedWork W3018421652 @default.
• W2890596001 hasRelatedWork W3021430260 @default.
• W2890596001 hasRelatedWork W3091976719 @default.
• W2890596001 hasRelatedWork W3166467183 @default.
• W2890596001 hasRelatedWork W3189091156 @default.
• W2890596001 hasRelatedWork W3192840557 @default.
• W2890596001 hasRelatedWork W4206156330 @default.
• W2890596001 isParatext "false" @default.
• W2890596001 isRetracted "false" @default.
• W2890596001 magId "2890596001" @default.
• W2890596001 workType "article" @default.