Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783710041> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2783710041 endingPage "30" @default.
- W2783710041 startingPage "19" @default.
- W2783710041 abstract "Radiologists often have a hard time classifying mammography mass lesions which leads to unnecessary breast biopsies to remove suspicions and this ends up adding exorbitant expenses to an already burdened patient and health care system.In this paper we developed a Computer-aided Diagnosis (CAD) system based on deep Convolutional Neural Networks (CNN) that aims to help the radiologist classify mammography mass lesions. Deep learning usually requires large datasets to train networks of a certain depth from scratch. Transfer learning is an effective method to deal with relatively small datasets as in the case of medical images, although it can be tricky as we can easily start overfitting.In this work, we explore the importance of transfer learning and we experimentally determine the best fine-tuning strategy to adopt when training a CNN model. We were able to successfully fine-tune some of the recent, most powerful CNNs and achieved better results compared to other state-of-the-art methods which classified the same public datasets. For instance we achieved 97.35% accuracy and 0.98 AUC on the DDSM database, 95.50% accuracy and 0.97 AUC on the INbreast database and 96.67% accuracy and 0.96 AUC on the BCDR database. Furthermore, after pre-processing and normalizing all the extracted Regions of Interest (ROIs) from the full mammograms, we merged all the datasets to build one large set of images and used it to fine-tune our CNNs. The CNN model which achieved the best results, a 98.94% accuracy, was used as a baseline to build the Breast Cancer Screening Framework. To evaluate the proposed CAD system and its efficiency to classify new images, we tested it on an independent database (MIAS) and got 98.23% accuracy and 0.99 AUC.The results obtained demonstrate that the proposed framework is performant and can indeed be used to predict if the mass lesions are benign or malignant." @default.
- W2783710041 created "2018-01-26" @default.
- W2783710041 creator A5054600849 @default.
- W2783710041 creator A5060581115 @default.
- W2783710041 creator A5085676778 @default.
- W2783710041 date "2018-04-01" @default.
- W2783710041 modified "2023-10-04" @default.
- W2783710041 title "Deep Convolutional Neural Networks for breast cancer screening" @default.
- W2783710041 cites W2044243109 @default.
- W2783710041 cites W2061715187 @default.
- W2783710041 cites W2064116998 @default.
- W2783710041 cites W2076063813 @default.
- W2783710041 cites W2084202389 @default.
- W2783710041 cites W2098543955 @default.
- W2783710041 cites W2103018059 @default.
- W2783710041 cites W2112467442 @default.
- W2783710041 cites W2124653673 @default.
- W2783710041 cites W2148516878 @default.
- W2783710041 cites W2154051385 @default.
- W2783710041 cites W2163922914 @default.
- W2783710041 cites W2191222448 @default.
- W2783710041 cites W2253429366 @default.
- W2783710041 cites W2284539364 @default.
- W2783710041 cites W2299565249 @default.
- W2783710041 cites W2570618306 @default.
- W2783710041 cites W2919115771 @default.
- W2783710041 cites W304373761 @default.
- W2783710041 cites W4231109964 @default.
- W2783710041 doi "https://doi.org/10.1016/j.cmpb.2018.01.011" @default.
- W2783710041 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29477427" @default.
- W2783710041 hasPublicationYear "2018" @default.
- W2783710041 type Work @default.
- W2783710041 sameAs 2783710041 @default.
- W2783710041 citedByCount "283" @default.
- W2783710041 countsByYear W27837100412018 @default.
- W2783710041 countsByYear W27837100412019 @default.
- W2783710041 countsByYear W27837100412020 @default.
- W2783710041 countsByYear W27837100412021 @default.
- W2783710041 countsByYear W27837100412022 @default.
- W2783710041 countsByYear W27837100412023 @default.
- W2783710041 crossrefType "journal-article" @default.
- W2783710041 hasAuthorship W2783710041A5054600849 @default.
- W2783710041 hasAuthorship W2783710041A5060581115 @default.
- W2783710041 hasAuthorship W2783710041A5085676778 @default.
- W2783710041 hasConcept C108583219 @default.
- W2783710041 hasConcept C119857082 @default.
- W2783710041 hasConcept C121608353 @default.
- W2783710041 hasConcept C126322002 @default.
- W2783710041 hasConcept C150899416 @default.
- W2783710041 hasConcept C153180895 @default.
- W2783710041 hasConcept C154945302 @default.
- W2783710041 hasConcept C22019652 @default.
- W2783710041 hasConcept C2779549770 @default.
- W2783710041 hasConcept C2780472235 @default.
- W2783710041 hasConcept C41008148 @default.
- W2783710041 hasConcept C50644808 @default.
- W2783710041 hasConcept C530470458 @default.
- W2783710041 hasConcept C71924100 @default.
- W2783710041 hasConcept C81363708 @default.
- W2783710041 hasConceptScore W2783710041C108583219 @default.
- W2783710041 hasConceptScore W2783710041C119857082 @default.
- W2783710041 hasConceptScore W2783710041C121608353 @default.
- W2783710041 hasConceptScore W2783710041C126322002 @default.
- W2783710041 hasConceptScore W2783710041C150899416 @default.
- W2783710041 hasConceptScore W2783710041C153180895 @default.
- W2783710041 hasConceptScore W2783710041C154945302 @default.
- W2783710041 hasConceptScore W2783710041C22019652 @default.
- W2783710041 hasConceptScore W2783710041C2779549770 @default.
- W2783710041 hasConceptScore W2783710041C2780472235 @default.
- W2783710041 hasConceptScore W2783710041C41008148 @default.
- W2783710041 hasConceptScore W2783710041C50644808 @default.
- W2783710041 hasConceptScore W2783710041C530470458 @default.
- W2783710041 hasConceptScore W2783710041C71924100 @default.
- W2783710041 hasConceptScore W2783710041C81363708 @default.
- W2783710041 hasLocation W27837100411 @default.
- W2783710041 hasLocation W27837100412 @default.
- W2783710041 hasOpenAccess W2783710041 @default.
- W2783710041 hasPrimaryLocation W27837100411 @default.
- W2783710041 hasRelatedWork W2738221750 @default.
- W2783710041 hasRelatedWork W2783710041 @default.
- W2783710041 hasRelatedWork W2997709384 @default.
- W2783710041 hasRelatedWork W3012393889 @default.
- W2783710041 hasRelatedWork W3021430260 @default.
- W2783710041 hasRelatedWork W3099765033 @default.
- W2783710041 hasRelatedWork W3162092403 @default.
- W2783710041 hasRelatedWork W4220996320 @default.
- W2783710041 hasRelatedWork W4313289428 @default.
- W2783710041 hasRelatedWork W4313526617 @default.
- W2783710041 hasVolume "157" @default.
- W2783710041 isParatext "false" @default.
- W2783710041 isRetracted "false" @default.
- W2783710041 magId "2783710041" @default.
- W2783710041 workType "article" @default.