Matches in SemOpenAlex for { <https://semopenalex.org/work/W3026036385> ?p ?o ?g. }
- W3026036385 endingPage "98704" @default.
- W3026036385 startingPage "98693" @default.
- W3026036385 abstract "Medical image analysis is motivated by the success of deep learning, where annotations are usually expensive and not easy to obtain. In this paper, we propose a deep quintuplet network CXNet-m3, where the classification of lesion type of chest x-ray images (CXRs) could benefit from easily accessible annotations like patient age, gender, identity and view position. To improve classification performance, a novel loss function combining both deep metric learning and deep learning is first designed based on multiple labels. Then, a deep model based on transfer learning is built to optimize the loss function. To solve the problem of slow convergence, a quintuplet mining algorithm is presented to provide valuable training samples for the proposed classification model. The experimental results on Chest X-ray14 database show that our classification method outperforms some state-of-art models under Area Under Curve (AUC) score, reaching 0.824 on an average. Besides, our proposal achieves more than 0.9 AUC values in the case of Infiltration, Atelectasis, Cardiomegaly and Nodule." @default.
- W3026036385 created "2020-05-29" @default.
- W3026036385 creator A5002911384 @default.
- W3026036385 creator A5005149886 @default.
- W3026036385 creator A5030902303 @default.
- W3026036385 creator A5058990428 @default.
- W3026036385 creator A5085259225 @default.
- W3026036385 creator A5089552486 @default.
- W3026036385 date "2020-01-01" @default.
- W3026036385 modified "2023-10-16" @default.
- W3026036385 title "Cxnet-M3: A Deep Quintuplet Network for Multi-Lesion Classification in Chest X-Ray Images Via Multi-Label Supervision" @default.
- W3026036385 cites W1162378864 @default.
- W3026036385 cites W1498436455 @default.
- W3026036385 cites W1973965874 @default.
- W3026036385 cites W2035347051 @default.
- W3026036385 cites W2063505420 @default.
- W3026036385 cites W2097117768 @default.
- W3026036385 cites W2117691146 @default.
- W3026036385 cites W2138621090 @default.
- W3026036385 cites W2165698076 @default.
- W3026036385 cites W2194775991 @default.
- W3026036385 cites W2221409856 @default.
- W3026036385 cites W2334763311 @default.
- W3026036385 cites W2510597476 @default.
- W3026036385 cites W2519653196 @default.
- W3026036385 cites W2520774990 @default.
- W3026036385 cites W2558208069 @default.
- W3026036385 cites W2558991945 @default.
- W3026036385 cites W2605102252 @default.
- W3026036385 cites W2608231518 @default.
- W3026036385 cites W2789632256 @default.
- W3026036385 cites W2790275230 @default.
- W3026036385 cites W2793830050 @default.
- W3026036385 cites W2794022343 @default.
- W3026036385 cites W2803042806 @default.
- W3026036385 cites W2889646458 @default.
- W3026036385 cites W2901228371 @default.
- W3026036385 cites W2904060505 @default.
- W3026036385 cites W2904335605 @default.
- W3026036385 cites W2910440949 @default.
- W3026036385 cites W2912742764 @default.
- W3026036385 cites W2951092891 @default.
- W3026036385 cites W2962708065 @default.
- W3026036385 cites W2962838801 @default.
- W3026036385 cites W2962878352 @default.
- W3026036385 cites W2963446712 @default.
- W3026036385 cites W2963842104 @default.
- W3026036385 cites W2974888503 @default.
- W3026036385 cites W2995942064 @default.
- W3026036385 cites W3099206234 @default.
- W3026036385 cites W3101156210 @default.
- W3026036385 cites W3101227480 @default.
- W3026036385 cites W3104871643 @default.
- W3026036385 cites W63020733 @default.
- W3026036385 doi "https://doi.org/10.1109/access.2020.2996217" @default.
- W3026036385 hasPublicationYear "2020" @default.
- W3026036385 type Work @default.
- W3026036385 sameAs 3026036385 @default.
- W3026036385 citedByCount "5" @default.
- W3026036385 countsByYear W30260363852022 @default.
- W3026036385 countsByYear W30260363852023 @default.
- W3026036385 crossrefType "journal-article" @default.
- W3026036385 hasAuthorship W3026036385A5002911384 @default.
- W3026036385 hasAuthorship W3026036385A5005149886 @default.
- W3026036385 hasAuthorship W3026036385A5030902303 @default.
- W3026036385 hasAuthorship W3026036385A5058990428 @default.
- W3026036385 hasAuthorship W3026036385A5085259225 @default.
- W3026036385 hasAuthorship W3026036385A5089552486 @default.
- W3026036385 hasBestOaLocation W30260363851 @default.
- W3026036385 hasConcept C108583219 @default.
- W3026036385 hasConcept C115961682 @default.
- W3026036385 hasConcept C119857082 @default.
- W3026036385 hasConcept C153180895 @default.
- W3026036385 hasConcept C154945302 @default.
- W3026036385 hasConcept C162324750 @default.
- W3026036385 hasConcept C176217482 @default.
- W3026036385 hasConcept C21547014 @default.
- W3026036385 hasConcept C41008148 @default.
- W3026036385 hasConcept C75294576 @default.
- W3026036385 hasConceptScore W3026036385C108583219 @default.
- W3026036385 hasConceptScore W3026036385C115961682 @default.
- W3026036385 hasConceptScore W3026036385C119857082 @default.
- W3026036385 hasConceptScore W3026036385C153180895 @default.
- W3026036385 hasConceptScore W3026036385C154945302 @default.
- W3026036385 hasConceptScore W3026036385C162324750 @default.
- W3026036385 hasConceptScore W3026036385C176217482 @default.
- W3026036385 hasConceptScore W3026036385C21547014 @default.
- W3026036385 hasConceptScore W3026036385C41008148 @default.
- W3026036385 hasConceptScore W3026036385C75294576 @default.
- W3026036385 hasFunder F4320321001 @default.
- W3026036385 hasLocation W30260363851 @default.
- W3026036385 hasOpenAccess W3026036385 @default.
- W3026036385 hasPrimaryLocation W30260363851 @default.
- W3026036385 hasRelatedWork W3014300295 @default.
- W3026036385 hasRelatedWork W3164822677 @default.
- W3026036385 hasRelatedWork W4223943233 @default.
- W3026036385 hasRelatedWork W4225161397 @default.
- W3026036385 hasRelatedWork W4295088746 @default.