FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892073452> ?p ?o ?g. }

• W2892073452 endingPage "4863" @default.
• W2892073452 startingPage "4863" @default.
• W2892073452 abstract "Diabetic retinopathy (DR) is a leading cause of blindness worldwide. However, 90% of DR caused blindness can be prevented if diagnosed and intervened early. Retinal exudates can be observed at the early stage of DR and can be used as signs for early DR diagnosis. Deep convolutional neural networks (DCNNs) have been applied for exudate detection with promising results. However, there exist two main challenges when applying the DCNN based methods for exudate detection. One is the very limited number of labeled data available from medical experts, and another is the severely imbalanced distribution of data of different classes. First, there are many more images of normal eyes than those of eyes with exudates, particularly for screening datasets. Second, the number of normal pixels (non-exudates) is much greater than the number of abnormal pixels (exudates) in images containing exudates. To tackle the small sample set problem, an ensemble convolutional neural network (MU-net) based on a U-net structure is presented in this paper. To alleviate the imbalance data problem, the conditional generative adversarial network (cGAN) is adopted to generate label-preserving minority class data specifically to implement the data augmentation. The network was trained on one dataset (e_ophtha_EX) and tested on the other three public datasets (DiaReTDB1, HEI-MED and MESSIDOR). CGAN, as a data augmentation method, significantly improves network robustness and generalization properties, achieving F1-scores of 92.79%, 92.46%, 91.27%, and 94.34%, respectively, as measured at the lesion level. While without cGAN, the corresponding F1-scores were 92.66%, 91.41%, 90.72%, and 90.58%, respectively. When measured at the image level, with cGAN we achieved the accuracy of 95.45%, 92.13%, 88.76%, and 89.58%, compared with the values achieved without cGAN of 86.36%, 87.64%, 76.33%, and 86.42%, respectively." @default.
• W2892073452 created "2018-09-27" @default.
• W2892073452 creator A5001730991 @default.
• W2892073452 creator A5017325467 @default.
• W2892073452 creator A5020147975 @default.
• W2892073452 creator A5024182063 @default.
• W2892073452 creator A5055541105 @default.
• W2892073452 creator A5057386168 @default.
• W2892073452 creator A5084946271 @default.
• W2892073452 creator A5086751264 @default.
• W2892073452 date "2018-09-14" @default.
• W2892073452 modified "2023-10-18" @default.
• W2892073452 title "Detection of exudates in fundus photographs with imbalanced learning using conditional generative adversarial network" @default.
• W2892073452 cites W1480729244 @default.
• W2892073452 cites W1969496006 @default.
• W2892073452 cites W1984154895 @default.
• W2892073452 cites W1988742259 @default.
• W2892073452 cites W1992728454 @default.
• W2892073452 cites W1993138166 @default.
• W2892073452 cites W1995023030 @default.
• W2892073452 cites W1996459699 @default.
• W2892073452 cites W2010099973 @default.
• W2892073452 cites W2031272895 @default.
• W2892073452 cites W2039286858 @default.
• W2892073452 cites W2040904686 @default.
• W2892073452 cites W2053392410 @default.
• W2892073452 cites W2054931962 @default.
• W2892073452 cites W2056518953 @default.
• W2892073452 cites W2059036143 @default.
• W2892073452 cites W2078767451 @default.
• W2892073452 cites W2078789324 @default.
• W2892073452 cites W2115278098 @default.
• W2892073452 cites W2118461103 @default.
• W2892073452 cites W2121737033 @default.
• W2892073452 cites W2123303981 @default.
• W2892073452 cites W2136856007 @default.
• W2892073452 cites W2142866653 @default.
• W2892073452 cites W2148143831 @default.
• W2892073452 cites W2158518042 @default.
• W2892073452 cites W2162698990 @default.
• W2892073452 cites W2166214224 @default.
• W2892073452 cites W2169736040 @default.
• W2892073452 cites W2169961704 @default.
• W2892073452 cites W2309022991 @default.
• W2892073452 cites W2433157206 @default.
• W2892073452 cites W2529609428 @default.
• W2892073452 cites W2593230217 @default.
• W2892073452 cites W2749049648 @default.
• W2892073452 cites W2756182389 @default.
• W2892073452 cites W2765885311 @default.
• W2892073452 cites W2919115771 @default.
• W2892073452 cites W4212883601 @default.
• W2892073452 doi "https://doi.org/10.1364/boe.9.004863" @default.
• W2892073452 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6179403" @default.
• W2892073452 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30319908" @default.
• W2892073452 hasPublicationYear "2018" @default.
• W2892073452 type Work @default.
• W2892073452 sameAs 2892073452 @default.
• W2892073452 citedByCount "41" @default.
• W2892073452 countsByYear W28920734522019 @default.
• W2892073452 countsByYear W28920734522020 @default.
• W2892073452 countsByYear W28920734522021 @default.
• W2892073452 countsByYear W28920734522022 @default.
• W2892073452 countsByYear W28920734522023 @default.
• W2892073452 crossrefType "journal-article" @default.
• W2892073452 hasAuthorship W2892073452A5001730991 @default.
• W2892073452 hasAuthorship W2892073452A5017325467 @default.
• W2892073452 hasAuthorship W2892073452A5020147975 @default.
• W2892073452 hasAuthorship W2892073452A5024182063 @default.
• W2892073452 hasAuthorship W2892073452A5055541105 @default.
• W2892073452 hasAuthorship W2892073452A5057386168 @default.
• W2892073452 hasAuthorship W2892073452A5084946271 @default.
• W2892073452 hasAuthorship W2892073452A5086751264 @default.
• W2892073452 hasBestOaLocation W28920734521 @default.
• W2892073452 hasConcept C104317684 @default.
• W2892073452 hasConcept C108583219 @default.
• W2892073452 hasConcept C118487528 @default.
• W2892073452 hasConcept C119767625 @default.
• W2892073452 hasConcept C153180895 @default.
• W2892073452 hasConcept C154945302 @default.
• W2892073452 hasConcept C160633673 @default.
• W2892073452 hasConcept C185592680 @default.
• W2892073452 hasConcept C2776391266 @default.
• W2892073452 hasConcept C2780929884 @default.
• W2892073452 hasConcept C2988773926 @default.
• W2892073452 hasConcept C41008148 @default.
• W2892073452 hasConcept C55493867 @default.
• W2892073452 hasConcept C58489278 @default.
• W2892073452 hasConcept C63479239 @default.
• W2892073452 hasConcept C71924100 @default.
• W2892073452 hasConcept C81363708 @default.
• W2892073452 hasConceptScore W2892073452C104317684 @default.
• W2892073452 hasConceptScore W2892073452C108583219 @default.
• W2892073452 hasConceptScore W2892073452C118487528 @default.
• W2892073452 hasConceptScore W2892073452C119767625 @default.
• W2892073452 hasConceptScore W2892073452C153180895 @default.
• W2892073452 hasConceptScore W2892073452C154945302 @default.
• W2892073452 hasConceptScore W2892073452C160633673 @default.

• next