Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217687501> ?p ?o ?g. }
- W3217687501 abstract "Deep learning models have gained remarkable performance on a variety of image classification tasks. However, many models suffer from limited performance in clinical or medical settings when data are imbalanced. To address this challenge, we propose a medical-knowledge-guided one-class classification approach that leverages domain-specific knowledge of classification tasks to boost the model's performance. The rationale behind our approach is that some existing prior medical knowledge can be incorporated into data-driven deep learning to facilitate model learning. We design a deep learning-based one-class classification pipeline for imbalanced image classification, and demonstrate in three use cases how we take advantage of medical knowledge of each specific classification task by generating additional middle classes to achieve higher classification performances. We evaluate our approach on three different clinical image classification tasks (a total of 8459 images) and show superior model performance when compared to six state-of-the-art methods. All codes of this work will be publicly available upon acceptance of the paper." @default.
- W3217687501 created "2021-12-06" @default.
- W3217687501 creator A5022256556 @default.
- W3217687501 creator A5028418236 @default.
- W3217687501 creator A5054344119 @default.
- W3217687501 creator A5065882309 @default.
- W3217687501 creator A5074743495 @default.
- W3217687501 creator A5085947646 @default.
- W3217687501 date "2021-11-20" @default.
- W3217687501 modified "2023-10-16" @default.
- W3217687501 title "Medical Knowledge-Guided Deep Learning for Imbalanced Medical Image Classification" @default.
- W3217687501 cites W146076398 @default.
- W3217687501 cites W1970088130 @default.
- W3217687501 cites W2105497548 @default.
- W3217687501 cites W2109197306 @default.
- W3217687501 cites W2113282793 @default.
- W3217687501 cites W2131992491 @default.
- W3217687501 cites W2132791018 @default.
- W3217687501 cites W2133949619 @default.
- W3217687501 cites W2142261479 @default.
- W3217687501 cites W2142596292 @default.
- W3217687501 cites W2164598857 @default.
- W3217687501 cites W2168508521 @default.
- W3217687501 cites W2398119937 @default.
- W3217687501 cites W2401231614 @default.
- W3217687501 cites W2592929672 @default.
- W3217687501 cites W2599354622 @default.
- W3217687501 cites W2752856697 @default.
- W3217687501 cites W2753582981 @default.
- W3217687501 cites W2786088545 @default.
- W3217687501 cites W2791103947 @default.
- W3217687501 cites W2803697594 @default.
- W3217687501 cites W2886438696 @default.
- W3217687501 cites W2913331367 @default.
- W3217687501 cites W2913939497 @default.
- W3217687501 cites W2921612408 @default.
- W3217687501 cites W2936503027 @default.
- W3217687501 cites W2954996726 @default.
- W3217687501 cites W2963351448 @default.
- W3217687501 cites W2963773039 @default.
- W3217687501 cites W2964121744 @default.
- W3217687501 cites W2964269771 @default.
- W3217687501 cites W2971403019 @default.
- W3217687501 cites W2981025625 @default.
- W3217687501 cites W2997601829 @default.
- W3217687501 cites W3011738477 @default.
- W3217687501 cites W3102785203 @default.
- W3217687501 cites W3148140980 @default.
- W3217687501 cites W3196898581 @default.
- W3217687501 doi "https://doi.org/10.48550/arxiv.2111.10620" @default.
- W3217687501 hasPublicationYear "2021" @default.
- W3217687501 type Work @default.
- W3217687501 sameAs 3217687501 @default.
- W3217687501 citedByCount "1" @default.
- W3217687501 countsByYear W32176875012023 @default.
- W3217687501 crossrefType "posted-content" @default.
- W3217687501 hasAuthorship W3217687501A5022256556 @default.
- W3217687501 hasAuthorship W3217687501A5028418236 @default.
- W3217687501 hasAuthorship W3217687501A5054344119 @default.
- W3217687501 hasAuthorship W3217687501A5065882309 @default.
- W3217687501 hasAuthorship W3217687501A5074743495 @default.
- W3217687501 hasAuthorship W3217687501A5085947646 @default.
- W3217687501 hasBestOaLocation W32176875011 @default.
- W3217687501 hasConcept C108583219 @default.
- W3217687501 hasConcept C115961682 @default.
- W3217687501 hasConcept C119857082 @default.
- W3217687501 hasConcept C127413603 @default.
- W3217687501 hasConcept C134306372 @default.
- W3217687501 hasConcept C136197465 @default.
- W3217687501 hasConcept C154945302 @default.
- W3217687501 hasConcept C199360897 @default.
- W3217687501 hasConcept C201995342 @default.
- W3217687501 hasConcept C207685749 @default.
- W3217687501 hasConcept C2776482837 @default.
- W3217687501 hasConcept C2777212361 @default.
- W3217687501 hasConcept C2780451532 @default.
- W3217687501 hasConcept C33923547 @default.
- W3217687501 hasConcept C36503486 @default.
- W3217687501 hasConcept C41008148 @default.
- W3217687501 hasConcept C43521106 @default.
- W3217687501 hasConcept C75294576 @default.
- W3217687501 hasConceptScore W3217687501C108583219 @default.
- W3217687501 hasConceptScore W3217687501C115961682 @default.
- W3217687501 hasConceptScore W3217687501C119857082 @default.
- W3217687501 hasConceptScore W3217687501C127413603 @default.
- W3217687501 hasConceptScore W3217687501C134306372 @default.
- W3217687501 hasConceptScore W3217687501C136197465 @default.
- W3217687501 hasConceptScore W3217687501C154945302 @default.
- W3217687501 hasConceptScore W3217687501C199360897 @default.
- W3217687501 hasConceptScore W3217687501C201995342 @default.
- W3217687501 hasConceptScore W3217687501C207685749 @default.
- W3217687501 hasConceptScore W3217687501C2776482837 @default.
- W3217687501 hasConceptScore W3217687501C2777212361 @default.
- W3217687501 hasConceptScore W3217687501C2780451532 @default.
- W3217687501 hasConceptScore W3217687501C33923547 @default.
- W3217687501 hasConceptScore W3217687501C36503486 @default.
- W3217687501 hasConceptScore W3217687501C41008148 @default.
- W3217687501 hasConceptScore W3217687501C43521106 @default.
- W3217687501 hasConceptScore W3217687501C75294576 @default.
- W3217687501 hasLocation W32176875011 @default.