Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361761992> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4361761992 endingPage "407" @default.
- W4361761992 startingPage "398" @default.
- W4361761992 abstract "Anomaly segmentation refers to leveraging only normal images for model training to detect pixel-level anomalies in abnormal images in test phase, which gets rid of the reliance on expensive manual labels and is able to detect rare anomalies that are hard to collect in training dataset. However, previous works performing anomaly segmentation in retinal OCT images heavily relied on complex post-processing methods and cannot detect anomalies in an end-to-end manner. To overcome that, in this paper, a novel anomaly segmentation method is proposed to segment retinopathy based on normative prior network. Specifically, a segmentation network and a variational autoencoder is constructed to extract retinal regions and learn normative prior of normal retinal structure, respectively. In inference phase, the anomalous region can be directly segmented by low structural similarity between abnormal retinal structure and the normal one reconstructed by variational autoencoder. Extensive experiments are conducted to evaluate the performance of the proposed method and the experimental results show that it achieves the state-of-the-art (SOTA) performance for anomaly segmentation in retinal OCT images." @default.
- W4361761992 created "2023-04-04" @default.
- W4361761992 creator A5001005426 @default.
- W4361761992 creator A5005999997 @default.
- W4361761992 creator A5007518360 @default.
- W4361761992 creator A5021222060 @default.
- W4361761992 creator A5051682933 @default.
- W4361761992 creator A5074760943 @default.
- W4361761992 date "2023-01-01" @default.
- W4361761992 modified "2023-09-25" @default.
- W4361761992 title "Normative Prior Network for Anomaly Segmentation in Retinal OCT Images" @default.
- W4361761992 cites W1901129140 @default.
- W4361761992 cites W2194775991 @default.
- W4361761992 cites W2599354622 @default.
- W4361761992 cites W2754699981 @default.
- W4361761992 cites W2788633781 @default.
- W4361761992 cites W2796762894 @default.
- W4361761992 cites W2797401432 @default.
- W4361761992 cites W2914570111 @default.
- W4361761992 cites W2947805333 @default.
- W4361761992 cites W3027067201 @default.
- W4361761992 cites W3034648032 @default.
- W4361761992 cites W3106336869 @default.
- W4361761992 cites W3118868805 @default.
- W4361761992 cites W3169077988 @default.
- W4361761992 cites W3175238080 @default.
- W4361761992 cites W3175716777 @default.
- W4361761992 cites W3189108671 @default.
- W4361761992 cites W3204685480 @default.
- W4361761992 doi "https://doi.org/10.1007/978-981-99-0923-0_40" @default.
- W4361761992 hasPublicationYear "2023" @default.
- W4361761992 type Work @default.
- W4361761992 citedByCount "0" @default.
- W4361761992 crossrefType "book-chapter" @default.
- W4361761992 hasAuthorship W4361761992A5001005426 @default.
- W4361761992 hasAuthorship W4361761992A5005999997 @default.
- W4361761992 hasAuthorship W4361761992A5007518360 @default.
- W4361761992 hasAuthorship W4361761992A5021222060 @default.
- W4361761992 hasAuthorship W4361761992A5051682933 @default.
- W4361761992 hasAuthorship W4361761992A5074760943 @default.
- W4361761992 hasConcept C101738243 @default.
- W4361761992 hasConcept C108583219 @default.
- W4361761992 hasConcept C121332964 @default.
- W4361761992 hasConcept C12997251 @default.
- W4361761992 hasConcept C153180895 @default.
- W4361761992 hasConcept C154945302 @default.
- W4361761992 hasConcept C26873012 @default.
- W4361761992 hasConcept C31972630 @default.
- W4361761992 hasConcept C41008148 @default.
- W4361761992 hasConcept C739882 @default.
- W4361761992 hasConcept C89600930 @default.
- W4361761992 hasConceptScore W4361761992C101738243 @default.
- W4361761992 hasConceptScore W4361761992C108583219 @default.
- W4361761992 hasConceptScore W4361761992C121332964 @default.
- W4361761992 hasConceptScore W4361761992C12997251 @default.
- W4361761992 hasConceptScore W4361761992C153180895 @default.
- W4361761992 hasConceptScore W4361761992C154945302 @default.
- W4361761992 hasConceptScore W4361761992C26873012 @default.
- W4361761992 hasConceptScore W4361761992C31972630 @default.
- W4361761992 hasConceptScore W4361761992C41008148 @default.
- W4361761992 hasConceptScore W4361761992C739882 @default.
- W4361761992 hasConceptScore W4361761992C89600930 @default.
- W4361761992 hasLocation W43617619921 @default.
- W4361761992 hasOpenAccess W4361761992 @default.
- W4361761992 hasPrimaryLocation W43617619921 @default.
- W4361761992 hasRelatedWork W2776466379 @default.
- W4361761992 hasRelatedWork W2998168123 @default.
- W4361761992 hasRelatedWork W3116554004 @default.
- W4361761992 hasRelatedWork W3186512740 @default.
- W4361761992 hasRelatedWork W4220775285 @default.
- W4361761992 hasRelatedWork W4287995534 @default.
- W4361761992 hasRelatedWork W4296210064 @default.
- W4361761992 hasRelatedWork W4308482784 @default.
- W4361761992 hasRelatedWork W4312467842 @default.
- W4361761992 hasRelatedWork W4363671829 @default.
- W4361761992 isParatext "false" @default.
- W4361761992 isRetracted "false" @default.
- W4361761992 workType "book-chapter" @default.