Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313444148> ?p ?o ?g. }
- W4313444148 endingPage "104536" @default.
- W4313444148 startingPage "104536" @default.
- W4313444148 abstract "In breast tumor diagnostic tasks, joint analysis of multiple sequences of MRI can improve the accuracy of diagnosis. More and more studies focus on the correlation between sequences and try applying multiple MRI sequences to computer-aided diagnosis. The deep neural network plays a vital role in this process because of its good feature extraction ability. However, the inevitable presence of missing or unavailable sequences in clinical can lead to degraded performance or even failure of multi-input networks. The key problem solved in this paper is to ensure the diagnostic accuracy of the network despite the presence of missing input sequences. A new breast tumor diagnosis deep learning method, ESF-NET, is proposed. First, ESF-NET combines the attention mechanism for adversarial learning to obtain the potential mapping and relationship between sequences and completes the generation of features for the missing sequences. Then the extended sequence fusion module with different fusion strategies is designed, which makes the final fusion results benefit from the feature enhancement resulting from all fusion strategies. These strategies can be adaptively weighted. We apply EST-NET to a dataset of MRI images of 98 women at high risk of breast cancer, including 33 benign and 65 malignant lesions. Each patient data contains several two-dimensional slices with different axial planes, the dataset consists of 2245 slices. In the presence of sequence missing, ESF-NET achieves a diagnostic accuracy of 85.61% at the slice level and 89.66% at the patient level, an improvement of 8.39% compared to using only a single sequence." @default.
- W4313444148 created "2023-01-06" @default.
- W4313444148 creator A5019485133 @default.
- W4313444148 creator A5043415956 @default.
- W4313444148 creator A5053326897 @default.
- W4313444148 creator A5065208984 @default.
- W4313444148 creator A5066140816 @default.
- W4313444148 creator A5080470815 @default.
- W4313444148 date "2023-04-01" @default.
- W4313444148 modified "2023-10-17" @default.
- W4313444148 title "Feature generation and multi-sequence fusion based deep convolutional network for breast tumor diagnosis with missing MR sequences" @default.
- W4313444148 cites W2064418656 @default.
- W4313444148 cites W2502805798 @default.
- W4313444148 cites W2608353599 @default.
- W4313444148 cites W2725008604 @default.
- W4313444148 cites W2744198280 @default.
- W4313444148 cites W2751909359 @default.
- W4313444148 cites W2766451787 @default.
- W4313444148 cites W2767044624 @default.
- W4313444148 cites W2767947179 @default.
- W4313444148 cites W2776110434 @default.
- W4313444148 cites W2789908311 @default.
- W4313444148 cites W2882978096 @default.
- W4313444148 cites W2888743781 @default.
- W4313444148 cites W2898653582 @default.
- W4313444148 cites W2912128568 @default.
- W4313444148 cites W2929959569 @default.
- W4313444148 cites W2953992968 @default.
- W4313444148 cites W2955805844 @default.
- W4313444148 cites W2962793481 @default.
- W4313444148 cites W2963276418 @default.
- W4313444148 cites W2963730812 @default.
- W4313444148 cites W2963931909 @default.
- W4313444148 cites W2978111064 @default.
- W4313444148 cites W2979878425 @default.
- W4313444148 cites W2999333317 @default.
- W4313444148 cites W2999932276 @default.
- W4313444148 cites W3000179685 @default.
- W4313444148 cites W3012269298 @default.
- W4313444148 cites W3018852185 @default.
- W4313444148 cites W3087427616 @default.
- W4313444148 cites W3112532377 @default.
- W4313444148 cites W3127718227 @default.
- W4313444148 cites W3128646645 @default.
- W4313444148 cites W3134189189 @default.
- W4313444148 cites W3159429016 @default.
- W4313444148 cites W3178620276 @default.
- W4313444148 cites W3197048794 @default.
- W4313444148 cites W3211729376 @default.
- W4313444148 cites W3217613904 @default.
- W4313444148 cites W4207043621 @default.
- W4313444148 doi "https://doi.org/10.1016/j.bspc.2022.104536" @default.
- W4313444148 hasPublicationYear "2023" @default.
- W4313444148 type Work @default.
- W4313444148 citedByCount "0" @default.
- W4313444148 crossrefType "journal-article" @default.
- W4313444148 hasAuthorship W4313444148A5019485133 @default.
- W4313444148 hasAuthorship W4313444148A5043415956 @default.
- W4313444148 hasAuthorship W4313444148A5053326897 @default.
- W4313444148 hasAuthorship W4313444148A5065208984 @default.
- W4313444148 hasAuthorship W4313444148A5066140816 @default.
- W4313444148 hasAuthorship W4313444148A5080470815 @default.
- W4313444148 hasConcept C108583219 @default.
- W4313444148 hasConcept C115961682 @default.
- W4313444148 hasConcept C121608353 @default.
- W4313444148 hasConcept C126322002 @default.
- W4313444148 hasConcept C138885662 @default.
- W4313444148 hasConcept C153180895 @default.
- W4313444148 hasConcept C154945302 @default.
- W4313444148 hasConcept C158525013 @default.
- W4313444148 hasConcept C2776401178 @default.
- W4313444148 hasConcept C2778112365 @default.
- W4313444148 hasConcept C2778971668 @default.
- W4313444148 hasConcept C41008148 @default.
- W4313444148 hasConcept C41895202 @default.
- W4313444148 hasConcept C530470458 @default.
- W4313444148 hasConcept C54355233 @default.
- W4313444148 hasConcept C69744172 @default.
- W4313444148 hasConcept C71924100 @default.
- W4313444148 hasConcept C81363708 @default.
- W4313444148 hasConcept C86803240 @default.
- W4313444148 hasConceptScore W4313444148C108583219 @default.
- W4313444148 hasConceptScore W4313444148C115961682 @default.
- W4313444148 hasConceptScore W4313444148C121608353 @default.
- W4313444148 hasConceptScore W4313444148C126322002 @default.
- W4313444148 hasConceptScore W4313444148C138885662 @default.
- W4313444148 hasConceptScore W4313444148C153180895 @default.
- W4313444148 hasConceptScore W4313444148C154945302 @default.
- W4313444148 hasConceptScore W4313444148C158525013 @default.
- W4313444148 hasConceptScore W4313444148C2776401178 @default.
- W4313444148 hasConceptScore W4313444148C2778112365 @default.
- W4313444148 hasConceptScore W4313444148C2778971668 @default.
- W4313444148 hasConceptScore W4313444148C41008148 @default.
- W4313444148 hasConceptScore W4313444148C41895202 @default.
- W4313444148 hasConceptScore W4313444148C530470458 @default.
- W4313444148 hasConceptScore W4313444148C54355233 @default.
- W4313444148 hasConceptScore W4313444148C69744172 @default.
- W4313444148 hasConceptScore W4313444148C71924100 @default.