Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378676927> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4378676927 abstract "Medical image segmentation is crucial for facilitating pathology assessment, ensuring reliable diagnosis and monitoring disease progression. Deep-learning models have been extensively applied in automating medical image analysis to reduce human effort. However, the non-transparency of deep-learning models limits their clinical practicality due to the unaffordably high risk of misdiagnosis resulted from the misleading model output. In this paper, we propose a explainability metric as part of the loss function. The proposed explainability metric comes from Class Activation Map(CAM) with learnable weights such that the model can be optimized to achieve desirable balance between segmentation performance and explainability. Experiments found that the proposed model visibly heightened Dice score from to , Jaccard similarity from to and Recall from to respectively compared with U-net. In addition, results make clear that the drawn model outdistances the conventional U-net in terms of explainability performance." @default.
- W4378676927 created "2023-05-30" @default.
- W4378676927 creator A5005621464 @default.
- W4378676927 creator A5043263283 @default.
- W4378676927 creator A5048778510 @default.
- W4378676927 creator A5054044336 @default.
- W4378676927 date "2023-03-17" @default.
- W4378676927 modified "2023-09-28" @default.
- W4378676927 title "Explainable Deep Learning for Medical Image Segmentation With Learnable Class Activation Mapping" @default.
- W4378676927 cites W1849277567 @default.
- W4378676927 cites W1901129140 @default.
- W4378676927 cites W1903029394 @default.
- W4378676927 cites W2295107390 @default.
- W4378676927 cites W2575842049 @default.
- W4378676927 cites W2594834973 @default.
- W4378676927 cites W2618530766 @default.
- W4378676927 cites W2888358068 @default.
- W4378676927 cites W2963150697 @default.
- W4378676927 cites W2963989815 @default.
- W4378676927 cites W2964303497 @default.
- W4378676927 doi "https://doi.org/10.1145/3590003.3590040" @default.
- W4378676927 hasPublicationYear "2023" @default.
- W4378676927 type Work @default.
- W4378676927 citedByCount "0" @default.
- W4378676927 crossrefType "proceedings-article" @default.
- W4378676927 hasAuthorship W4378676927A5005621464 @default.
- W4378676927 hasAuthorship W4378676927A5043263283 @default.
- W4378676927 hasAuthorship W4378676927A5048778510 @default.
- W4378676927 hasAuthorship W4378676927A5054044336 @default.
- W4378676927 hasConcept C103278499 @default.
- W4378676927 hasConcept C108583219 @default.
- W4378676927 hasConcept C115961682 @default.
- W4378676927 hasConcept C119857082 @default.
- W4378676927 hasConcept C124504099 @default.
- W4378676927 hasConcept C153180895 @default.
- W4378676927 hasConcept C154945302 @default.
- W4378676927 hasConcept C162324750 @default.
- W4378676927 hasConcept C176217482 @default.
- W4378676927 hasConcept C203519979 @default.
- W4378676927 hasConcept C21547014 @default.
- W4378676927 hasConcept C22029948 @default.
- W4378676927 hasConcept C2524010 @default.
- W4378676927 hasConcept C2777212361 @default.
- W4378676927 hasConcept C33923547 @default.
- W4378676927 hasConcept C41008148 @default.
- W4378676927 hasConcept C89600930 @default.
- W4378676927 hasConceptScore W4378676927C103278499 @default.
- W4378676927 hasConceptScore W4378676927C108583219 @default.
- W4378676927 hasConceptScore W4378676927C115961682 @default.
- W4378676927 hasConceptScore W4378676927C119857082 @default.
- W4378676927 hasConceptScore W4378676927C124504099 @default.
- W4378676927 hasConceptScore W4378676927C153180895 @default.
- W4378676927 hasConceptScore W4378676927C154945302 @default.
- W4378676927 hasConceptScore W4378676927C162324750 @default.
- W4378676927 hasConceptScore W4378676927C176217482 @default.
- W4378676927 hasConceptScore W4378676927C203519979 @default.
- W4378676927 hasConceptScore W4378676927C21547014 @default.
- W4378676927 hasConceptScore W4378676927C22029948 @default.
- W4378676927 hasConceptScore W4378676927C2524010 @default.
- W4378676927 hasConceptScore W4378676927C2777212361 @default.
- W4378676927 hasConceptScore W4378676927C33923547 @default.
- W4378676927 hasConceptScore W4378676927C41008148 @default.
- W4378676927 hasConceptScore W4378676927C89600930 @default.
- W4378676927 hasLocation W43786769271 @default.
- W4378676927 hasOpenAccess W4378676927 @default.
- W4378676927 hasPrimaryLocation W43786769271 @default.
- W4378676927 hasRelatedWork W2630229246 @default.
- W4378676927 hasRelatedWork W2790662084 @default.
- W4378676927 hasRelatedWork W2948658236 @default.
- W4378676927 hasRelatedWork W2971066617 @default.
- W4378676927 hasRelatedWork W3093926553 @default.
- W4378676927 hasRelatedWork W3118494652 @default.
- W4378676927 hasRelatedWork W3164075923 @default.
- W4378676927 hasRelatedWork W4220708658 @default.
- W4378676927 hasRelatedWork W4243168368 @default.
- W4378676927 hasRelatedWork W4287631720 @default.
- W4378676927 isParatext "false" @default.
- W4378676927 isRetracted "false" @default.
- W4378676927 workType "article" @default.