Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089593502> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W3089593502 abstract "Hand and wrist skeletal radiographs serve as an important medium for diversified medical and forensic tasks involving bone age assessment. As an alternative to traditional atlas-based bone age identification techniques, deep learning algorithms automatically classify the radiographs into predefined bone age classes, provided that the deep neural networks (DNN) have been well trained with large scale annotated datasets. Most of the current bone age classification DNNs directly explore the existing network models developed for other computer vision representations and understanding applications, such as VGG, Inception, and ResNet. In this work, we present a multi-scale attention-enhanced classifier with a convolutional neural network backbone, specifically designed for bone age prediction and trained to learn a subject’s bone age and gender jointly. The proposed classifier is trained with the dataset provided by the RSNA machine learning challenge, and the low-level semantic features are then transferred to a smaller Tongji dataset collected from a hospital in China. As demonstrated by the experiments, the proposed classifier achieves the MADs of 0.41 years over RSNA data and 0.36 years on Tongji data, outperforming other single model state-of-the-art and baseline algorithms for the same test. It illustrates that joint learning of gender information plays a critical role in refining the bone age assessment, while the convolution-based attention mechanism helps retrieve the key features." @default.
- W3089593502 created "2020-10-08" @default.
- W3089593502 creator A5050440016 @default.
- W3089593502 creator A5057130910 @default.
- W3089593502 creator A5072969773 @default.
- W3089593502 date "2020-09-25" @default.
- W3089593502 modified "2023-10-17" @default.
- W3089593502 title "Automatic Radiographic Bone Age Assessment Using Deep Joint Learning with Attention Modules" @default.
- W3089593502 cites W2152200595 @default.
- W3089593502 cites W2533800772 @default.
- W3089593502 cites W2903408278 @default.
- W3089593502 doi "https://doi.org/10.3233/atde200080" @default.
- W3089593502 hasPublicationYear "2020" @default.
- W3089593502 type Work @default.
- W3089593502 sameAs 3089593502 @default.
- W3089593502 citedByCount "0" @default.
- W3089593502 crossrefType "book-chapter" @default.
- W3089593502 hasAuthorship W3089593502A5050440016 @default.
- W3089593502 hasAuthorship W3089593502A5057130910 @default.
- W3089593502 hasAuthorship W3089593502A5072969773 @default.
- W3089593502 hasBestOaLocation W30895935021 @default.
- W3089593502 hasConcept C108583219 @default.
- W3089593502 hasConcept C119857082 @default.
- W3089593502 hasConcept C126322002 @default.
- W3089593502 hasConcept C153180895 @default.
- W3089593502 hasConcept C154945302 @default.
- W3089593502 hasConcept C41008148 @default.
- W3089593502 hasConcept C50644808 @default.
- W3089593502 hasConcept C71924100 @default.
- W3089593502 hasConcept C81363708 @default.
- W3089593502 hasConcept C89551170 @default.
- W3089593502 hasConcept C95623464 @default.
- W3089593502 hasConceptScore W3089593502C108583219 @default.
- W3089593502 hasConceptScore W3089593502C119857082 @default.
- W3089593502 hasConceptScore W3089593502C126322002 @default.
- W3089593502 hasConceptScore W3089593502C153180895 @default.
- W3089593502 hasConceptScore W3089593502C154945302 @default.
- W3089593502 hasConceptScore W3089593502C41008148 @default.
- W3089593502 hasConceptScore W3089593502C50644808 @default.
- W3089593502 hasConceptScore W3089593502C71924100 @default.
- W3089593502 hasConceptScore W3089593502C81363708 @default.
- W3089593502 hasConceptScore W3089593502C89551170 @default.
- W3089593502 hasConceptScore W3089593502C95623464 @default.
- W3089593502 hasLocation W30895935021 @default.
- W3089593502 hasOpenAccess W3089593502 @default.
- W3089593502 hasPrimaryLocation W30895935021 @default.
- W3089593502 hasRelatedWork W1535168 @default.
- W3089593502 hasRelatedWork W3143359 @default.
- W3089593502 hasRelatedWork W3753982 @default.
- W3089593502 hasRelatedWork W385470 @default.
- W3089593502 hasRelatedWork W4043321 @default.
- W3089593502 hasRelatedWork W5540780 @default.
- W3089593502 hasRelatedWork W7572512 @default.
- W3089593502 hasRelatedWork W8499301 @default.
- W3089593502 hasRelatedWork W8713351 @default.
- W3089593502 hasRelatedWork W4334855 @default.
- W3089593502 isParatext "false" @default.
- W3089593502 isRetracted "false" @default.
- W3089593502 magId "3089593502" @default.
- W3089593502 workType "book-chapter" @default.