Matches in SemOpenAlex for { <https://semopenalex.org/work/W3038310014> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3038310014 abstract "Intracranial hemorrhage is a serious health problem worldwide requiring rapid and often intensive medical treatment. However, the diagnosis process of intracranial hemorrhage is complicated and often time consuming when looking for the presence, location and type of hemorrhage on head computed tomography (CT), even for highly trained specialists. Therefore, it's a key challenge to achieve automated detection of intracranial hemorrhage on head CT with a promising detection accuracy at the examination level, leaving an urgent and critical issue to be addressed. In this paper, to accomplish this crucial task, we utilize a series of deep convolutional neural networks based on SE-ResNeXt50 and EfficientNet-B3 to simultaneously extract features from head CT and learn the classification for 5 subtypes of intracranial hemorrhage. The image dataset of head CT is provided by Radiological Society of North America through a featured competition on the Kaggle platform. The results show that the ensemble of SE-ResNeXt50 and EfficientNet-B3 trained with weighted multi-label logarithmic loss achieves an expert-level performance regarding the classification accuracy of intracranial hemorrhage. Our deep learning model obtain a score 0.0548 on the test set, which locates at the top 4% among all teams and can get a silver medal prize in the Kaggle competition." @default.
- W3038310014 created "2020-07-10" @default.
- W3038310014 creator A5003398846 @default.
- W3038310014 date "2020-09-15" @default.
- W3038310014 modified "2023-10-11" @default.
- W3038310014 title "Automated Detection of Intracranial Hemorrhage on Head Computed Tomography with Deep Learning" @default.
- W3038310014 cites W1677182931 @default.
- W3038310014 cites W1901129140 @default.
- W3038310014 cites W2183182206 @default.
- W3038310014 cites W2194775991 @default.
- W3038310014 cites W2549139847 @default.
- W3038310014 cites W2557738935 @default.
- W3038310014 cites W2581082771 @default.
- W3038310014 cites W2752782242 @default.
- W3038310014 cites W2772723798 @default.
- W3038310014 cites W2787894218 @default.
- W3038310014 cites W2963351448 @default.
- W3038310014 cites W2981941315 @default.
- W3038310014 cites W4211064847 @default.
- W3038310014 doi "https://doi.org/10.1145/3397391.3397436" @default.
- W3038310014 hasPublicationYear "2020" @default.
- W3038310014 type Work @default.
- W3038310014 sameAs 3038310014 @default.
- W3038310014 citedByCount "6" @default.
- W3038310014 countsByYear W30383100142021 @default.
- W3038310014 countsByYear W30383100142022 @default.
- W3038310014 countsByYear W30383100142023 @default.
- W3038310014 crossrefType "proceedings-article" @default.
- W3038310014 hasAuthorship W3038310014A5003398846 @default.
- W3038310014 hasConcept C108583219 @default.
- W3038310014 hasConcept C114793014 @default.
- W3038310014 hasConcept C119857082 @default.
- W3038310014 hasConcept C126838900 @default.
- W3038310014 hasConcept C127313418 @default.
- W3038310014 hasConcept C154945302 @default.
- W3038310014 hasConcept C162324750 @default.
- W3038310014 hasConcept C187736073 @default.
- W3038310014 hasConcept C2780312720 @default.
- W3038310014 hasConcept C2780451532 @default.
- W3038310014 hasConcept C31601959 @default.
- W3038310014 hasConcept C41008148 @default.
- W3038310014 hasConcept C544519230 @default.
- W3038310014 hasConcept C71924100 @default.
- W3038310014 hasConcept C81363708 @default.
- W3038310014 hasConceptScore W3038310014C108583219 @default.
- W3038310014 hasConceptScore W3038310014C114793014 @default.
- W3038310014 hasConceptScore W3038310014C119857082 @default.
- W3038310014 hasConceptScore W3038310014C126838900 @default.
- W3038310014 hasConceptScore W3038310014C127313418 @default.
- W3038310014 hasConceptScore W3038310014C154945302 @default.
- W3038310014 hasConceptScore W3038310014C162324750 @default.
- W3038310014 hasConceptScore W3038310014C187736073 @default.
- W3038310014 hasConceptScore W3038310014C2780312720 @default.
- W3038310014 hasConceptScore W3038310014C2780451532 @default.
- W3038310014 hasConceptScore W3038310014C31601959 @default.
- W3038310014 hasConceptScore W3038310014C41008148 @default.
- W3038310014 hasConceptScore W3038310014C544519230 @default.
- W3038310014 hasConceptScore W3038310014C71924100 @default.
- W3038310014 hasConceptScore W3038310014C81363708 @default.
- W3038310014 hasLocation W30383100141 @default.
- W3038310014 hasOpenAccess W3038310014 @default.
- W3038310014 hasPrimaryLocation W30383100141 @default.
- W3038310014 hasRelatedWork W3024479225 @default.
- W3038310014 hasRelatedWork W3029198973 @default.
- W3038310014 hasRelatedWork W3133861977 @default.
- W3038310014 hasRelatedWork W3167935049 @default.
- W3038310014 hasRelatedWork W3171371563 @default.
- W3038310014 hasRelatedWork W3193565141 @default.
- W3038310014 hasRelatedWork W4226493464 @default.
- W3038310014 hasRelatedWork W4312417841 @default.
- W3038310014 hasRelatedWork W4323287533 @default.
- W3038310014 hasRelatedWork W4360994352 @default.
- W3038310014 isParatext "false" @default.
- W3038310014 isRetracted "false" @default.
- W3038310014 magId "3038310014" @default.
- W3038310014 workType "article" @default.