Matches in SemOpenAlex for { <https://semopenalex.org/work/W3115231197> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3115231197 abstract "Accurate classification and comprehensive explanation is crucial to build a computer aided diagnosis (CAD) system of diffuse lung disease (DLD). Although deep neural networks (DNNs) have been applied to this task, the classification performance and reliability are not satisfied for medical clinical requirements. Specifically, DNNs are regarded as unexplainable “black-box” in general, and, thus, are not deemed reliable by expects. In this paper, we propose a neural network structure search approach based on evolutionary algorithm to improve the DNN's effectiveness and interpretability, and applied to the pulmonary textures classification problem. Through this network structure search approach, we find out how a DNN's subnet recognize the pulmonary textures features, then filter out the redundant subnets, and retain the most distinctive feature subnets. Besides, we utilize the method of feature visualization and the fine-grained heat map of the activation to interpret network's decision-making process. Finally, through quantitatively and qualitatively evaluate on a real dataset of diffuse lung disease, we verify the effectiveness of this neural network structure search approach on VggNet and ResNet, and achieve the state-of-the-art performance. We can classify the pulmonary textures on high-resolution computed tomography (HRCT) images." @default.
- W3115231197 created "2021-01-05" @default.
- W3115231197 creator A5012224052 @default.
- W3115231197 creator A5015860750 @default.
- W3115231197 creator A5052003105 @default.
- W3115231197 creator A5058381808 @default.
- W3115231197 creator A5071445293 @default.
- W3115231197 creator A5085473287 @default.
- W3115231197 date "2020-11-01" @default.
- W3115231197 modified "2023-09-24" @default.
- W3115231197 title "Evolutionary Neural Network and Visualization for CNN-based Pulmonary Textures Classification" @default.
- W3115231197 cites W116480831 @default.
- W3115231197 cites W1536680647 @default.
- W3115231197 cites W1962363309 @default.
- W3115231197 cites W1981261828 @default.
- W3115231197 cites W2056168656 @default.
- W3115231197 cites W2085206647 @default.
- W3115231197 cites W2097117768 @default.
- W3115231197 cites W2112796928 @default.
- W3115231197 cites W2194775991 @default.
- W3115231197 cites W2253429366 @default.
- W3115231197 cites W2294394056 @default.
- W3115231197 cites W2295107390 @default.
- W3115231197 cites W2618530766 @default.
- W3115231197 cites W2800617335 @default.
- W3115231197 cites W2962858109 @default.
- W3115231197 cites W2973941913 @default.
- W3115231197 cites W2983483859 @default.
- W3115231197 cites W4229494842 @default.
- W3115231197 doi "https://doi.org/10.1109/ictai50040.2020.00092" @default.
- W3115231197 hasPublicationYear "2020" @default.
- W3115231197 type Work @default.
- W3115231197 sameAs 3115231197 @default.
- W3115231197 citedByCount "2" @default.
- W3115231197 countsByYear W31152311972022 @default.
- W3115231197 countsByYear W31152311972023 @default.
- W3115231197 crossrefType "proceedings-article" @default.
- W3115231197 hasAuthorship W3115231197A5012224052 @default.
- W3115231197 hasAuthorship W3115231197A5015860750 @default.
- W3115231197 hasAuthorship W3115231197A5052003105 @default.
- W3115231197 hasAuthorship W3115231197A5058381808 @default.
- W3115231197 hasAuthorship W3115231197A5071445293 @default.
- W3115231197 hasAuthorship W3115231197A5085473287 @default.
- W3115231197 hasConcept C108583219 @default.
- W3115231197 hasConcept C119857082 @default.
- W3115231197 hasConcept C124101348 @default.
- W3115231197 hasConcept C127413603 @default.
- W3115231197 hasConcept C138885662 @default.
- W3115231197 hasConcept C153180895 @default.
- W3115231197 hasConcept C154945302 @default.
- W3115231197 hasConcept C194789388 @default.
- W3115231197 hasConcept C199639397 @default.
- W3115231197 hasConcept C21099817 @default.
- W3115231197 hasConcept C2776401178 @default.
- W3115231197 hasConcept C2781067378 @default.
- W3115231197 hasConcept C31258907 @default.
- W3115231197 hasConcept C36464697 @default.
- W3115231197 hasConcept C41008148 @default.
- W3115231197 hasConcept C41895202 @default.
- W3115231197 hasConcept C50644808 @default.
- W3115231197 hasConcept C81363708 @default.
- W3115231197 hasConceptScore W3115231197C108583219 @default.
- W3115231197 hasConceptScore W3115231197C119857082 @default.
- W3115231197 hasConceptScore W3115231197C124101348 @default.
- W3115231197 hasConceptScore W3115231197C127413603 @default.
- W3115231197 hasConceptScore W3115231197C138885662 @default.
- W3115231197 hasConceptScore W3115231197C153180895 @default.
- W3115231197 hasConceptScore W3115231197C154945302 @default.
- W3115231197 hasConceptScore W3115231197C194789388 @default.
- W3115231197 hasConceptScore W3115231197C199639397 @default.
- W3115231197 hasConceptScore W3115231197C21099817 @default.
- W3115231197 hasConceptScore W3115231197C2776401178 @default.
- W3115231197 hasConceptScore W3115231197C2781067378 @default.
- W3115231197 hasConceptScore W3115231197C31258907 @default.
- W3115231197 hasConceptScore W3115231197C36464697 @default.
- W3115231197 hasConceptScore W3115231197C41008148 @default.
- W3115231197 hasConceptScore W3115231197C41895202 @default.
- W3115231197 hasConceptScore W3115231197C50644808 @default.
- W3115231197 hasConceptScore W3115231197C81363708 @default.
- W3115231197 hasFunder F4320321630 @default.
- W3115231197 hasLocation W31152311971 @default.
- W3115231197 hasOpenAccess W3115231197 @default.
- W3115231197 hasPrimaryLocation W31152311971 @default.
- W3115231197 hasRelatedWork W11765363 @default.
- W3115231197 hasRelatedWork W1493022169 @default.
- W3115231197 hasRelatedWork W1563030733 @default.
- W3115231197 hasRelatedWork W1582096518 @default.
- W3115231197 hasRelatedWork W1584304702 @default.
- W3115231197 hasRelatedWork W2363669182 @default.
- W3115231197 hasRelatedWork W2386387936 @default.
- W3115231197 hasRelatedWork W2525150146 @default.
- W3115231197 hasRelatedWork W3107474891 @default.
- W3115231197 hasRelatedWork W1549056443 @default.
- W3115231197 isParatext "false" @default.
- W3115231197 isRetracted "false" @default.
- W3115231197 magId "3115231197" @default.
- W3115231197 workType "article" @default.