Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285217265> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4285217265 endingPage "633" @default.
- W4285217265 startingPage "625" @default.
- W4285217265 abstract "The early detection of breast cancer tumors by mammography is critical to minimizing the disease's complications and ensuring a successful cure. False-positive findings from a mammogram might lead to unnecessary biopsy procedures, which could harm a patient's chances of survival. Since the incidence of inaccurate diagnosis and misinterpretations of breast masses may be reduced by techniques that learn to distinguish breast masses, Conventional classification methods rely on domain-specific feature extraction approaches to solve a given issue. The various problems with feature-based methods are being addressed by deep learning algorithms, which are emerging as viable alternatives. Convolutional Neural Network (CNN)-based deep learning is used in this research to extract features at different densities and to distinguish between normal and suspicious areas in mammography. This paper includes a comparison of the VGG-16, MobileNetV2, and ResNet50 models. As can be shown, the testing accuracy of these models starts low in epoch 1 and rapidly improves until epoch 50. Finally, it achieves 97.22%, 98.61%, and 100.00% accuracy for VGG-16, MobileNetV2, and ResNet50, respectively. The suggested model's improvement and validation apply to traditional pathological techniques, which might potentially lessen pathologists’ stress when predicting clinical outcomes by evaluating patients’ mammography pictures." @default.
- W4285217265 created "2022-07-14" @default.
- W4285217265 creator A5044493626 @default.
- W4285217265 creator A5075573544 @default.
- W4285217265 creator A5078422400 @default.
- W4285217265 date "2022-01-01" @default.
- W4285217265 modified "2023-10-16" @default.
- W4285217265 title "Deep Learning Based Framework for Breast Cancer Mammography Classification Using Resnet50" @default.
- W4285217265 cites W2194775991 @default.
- W4285217265 cites W2602554322 @default.
- W4285217265 cites W2798462210 @default.
- W4285217265 cites W2809504579 @default.
- W4285217265 cites W2900144270 @default.
- W4285217265 cites W2908052439 @default.
- W4285217265 cites W2914010220 @default.
- W4285217265 cites W2915919874 @default.
- W4285217265 cites W2928842276 @default.
- W4285217265 cites W2991603289 @default.
- W4285217265 cites W3004970330 @default.
- W4285217265 cites W3148831051 @default.
- W4285217265 cites W4210973595 @default.
- W4285217265 doi "https://doi.org/10.1007/978-981-19-3089-8_58" @default.
- W4285217265 hasPublicationYear "2022" @default.
- W4285217265 type Work @default.
- W4285217265 citedByCount "1" @default.
- W4285217265 countsByYear W42852172652023 @default.
- W4285217265 crossrefType "book-chapter" @default.
- W4285217265 hasAuthorship W4285217265A5044493626 @default.
- W4285217265 hasAuthorship W4285217265A5075573544 @default.
- W4285217265 hasAuthorship W4285217265A5078422400 @default.
- W4285217265 hasConcept C108583219 @default.
- W4285217265 hasConcept C119857082 @default.
- W4285217265 hasConcept C121608353 @default.
- W4285217265 hasConcept C126322002 @default.
- W4285217265 hasConcept C138885662 @default.
- W4285217265 hasConcept C154945302 @default.
- W4285217265 hasConcept C2776401178 @default.
- W4285217265 hasConcept C2780472235 @default.
- W4285217265 hasConcept C41008148 @default.
- W4285217265 hasConcept C41895202 @default.
- W4285217265 hasConcept C530470458 @default.
- W4285217265 hasConcept C71924100 @default.
- W4285217265 hasConcept C81363708 @default.
- W4285217265 hasConceptScore W4285217265C108583219 @default.
- W4285217265 hasConceptScore W4285217265C119857082 @default.
- W4285217265 hasConceptScore W4285217265C121608353 @default.
- W4285217265 hasConceptScore W4285217265C126322002 @default.
- W4285217265 hasConceptScore W4285217265C138885662 @default.
- W4285217265 hasConceptScore W4285217265C154945302 @default.
- W4285217265 hasConceptScore W4285217265C2776401178 @default.
- W4285217265 hasConceptScore W4285217265C2780472235 @default.
- W4285217265 hasConceptScore W4285217265C41008148 @default.
- W4285217265 hasConceptScore W4285217265C41895202 @default.
- W4285217265 hasConceptScore W4285217265C530470458 @default.
- W4285217265 hasConceptScore W4285217265C71924100 @default.
- W4285217265 hasConceptScore W4285217265C81363708 @default.
- W4285217265 hasLocation W42852172651 @default.
- W4285217265 hasOpenAccess W4285217265 @default.
- W4285217265 hasPrimaryLocation W42852172651 @default.
- W4285217265 hasRelatedWork W2337926734 @default.
- W4285217265 hasRelatedWork W2731899572 @default.
- W4285217265 hasRelatedWork W2963958939 @default.
- W4285217265 hasRelatedWork W3173182854 @default.
- W4285217265 hasRelatedWork W4311257506 @default.
- W4285217265 hasRelatedWork W4312417841 @default.
- W4285217265 hasRelatedWork W4313526617 @default.
- W4285217265 hasRelatedWork W4320802194 @default.
- W4285217265 hasRelatedWork W4321369474 @default.
- W4285217265 hasRelatedWork W4366224123 @default.
- W4285217265 isParatext "false" @default.
- W4285217265 isRetracted "false" @default.
- W4285217265 workType "book-chapter" @default.