FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313482711> ?p ?o ?g. }

• W4313482711 endingPage "320" @default.
• W4313482711 startingPage "309" @default.
• W4313482711 abstract "Accurate retinal fluid segmentation on Optical Coherence Tomography (OCT) images plays an important role in diagnosing and treating various eye diseases. The art deep models have shown promising performance on OCT image segmentation given pixel-wise annotated training data. However, the learned model will achieve poor performance on OCT images that are obtained from different devices (domains) due to the domain shift issue. This problem largely limits the real-world application of OCT image segmentation since the types of devices usually are different in each hospital. In this paper, we study the task of cross-domain OCT fluid segmentation, where we are given a labeled dataset of the source device (domain) and an unlabeled dataset of the target device (domain). The goal is to learn a model that can perform well on the target domain. To solve this problem, in this paper, we propose a novel Structure-guided Cross-Attention Network (SCAN), which leverages the retinal layer structure to facilitate domain alignment. Our SCAN is inspired by the fact that the retinal layer structure is robust to domains and can reflect regions that are important to fluid segmentation. In light of this, we build our SCAN in a multi-task manner by jointly learning the retinal structure prediction and fluid segmentation. To exploit the mutual benefit between layer structure and fluid segmentation, we further introduce a cross-attention module to measure the correlation between the layer-specific feature and the fluid-specific feature encouraging the model to concentrate on highly relative regions during domain alignment. Moreover, an adaptation difficulty map is evaluated based on the retinal structure predictions from different domains, which enforces the model focus on hard regions during structure-aware adversarial learning. Extensive experiments on the three domains of the RETOUCH dataset demonstrate the effectiveness of the proposed method and show that our approach produces state-of-the-art performance on cross-domain OCT fluid segmentation." @default.
• W4313482711 created "2023-01-06" @default.
• W4313482711 creator A5027171279 @default.
• W4313482711 creator A5027769937 @default.
• W4313482711 creator A5057837485 @default.
• W4313482711 creator A5065061505 @default.
• W4313482711 creator A5065328976 @default.
• W4313482711 date "2023-01-01" @default.
• W4313482711 modified "2023-09-26" @default.
• W4313482711 title "Structure-Guided Cross-Attention Network for Cross-Domain OCT Fluid Segmentation" @default.
• W4313482711 cites W1903029394 @default.
• W4313482711 cites W2074598933 @default.
• W4313482711 cites W2075206985 @default.
• W4313482711 cites W2133059825 @default.
• W4313482711 cites W2152883336 @default.
• W4313482711 cites W2418802570 @default.
• W4313482711 cites W2590822257 @default.
• W4313482711 cites W2592517646 @default.
• W4313482711 cites W2593768305 @default.
• W4313482711 cites W2606534623 @default.
• W4313482711 cites W2607661563 @default.
• W4313482711 cites W2742820103 @default.
• W4313482711 cites W2772059204 @default.
• W4313482711 cites W2886281300 @default.
• W4313482711 cites W2888867330 @default.
• W4313482711 cites W2898829509 @default.
• W4313482711 cites W2907100905 @default.
• W4313482711 cites W2917393555 @default.
• W4313482711 cites W2919070891 @default.
• W4313482711 cites W2940740645 @default.
• W4313482711 cites W2944774584 @default.
• W4313482711 cites W2949122205 @default.
• W4313482711 cites W2950111065 @default.
• W4313482711 cites W2963073217 @default.
• W4313482711 cites W2963091558 @default.
• W4313482711 cites W2963107255 @default.
• W4313482711 cites W2966495887 @default.
• W4313482711 cites W2972285644 @default.
• W4313482711 cites W2981429991 @default.
• W4313482711 cites W2986831462 @default.
• W4313482711 cites W3022379890 @default.
• W4313482711 cites W3034417116 @default.
• W4313482711 cites W3034954654 @default.
• W4313482711 cites W3100823116 @default.
• W4313482711 cites W3101468328 @default.
• W4313482711 cites W3110486195 @default.
• W4313482711 cites W3112557529 @default.
• W4313482711 cites W3134134173 @default.
• W4313482711 cites W3173206925 @default.
• W4313482711 cites W3180003570 @default.
• W4313482711 cites W3216552527 @default.
• W4313482711 cites W4226040545 @default.
• W4313482711 doi "https://doi.org/10.1109/tip.2022.3228163" @default.
• W4313482711 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37015552" @default.
• W4313482711 hasPublicationYear "2023" @default.
• W4313482711 type Work @default.
• W4313482711 citedByCount "0" @default.
• W4313482711 crossrefType "journal-article" @default.
• W4313482711 hasAuthorship W4313482711A5027171279 @default.
• W4313482711 hasAuthorship W4313482711A5027769937 @default.
• W4313482711 hasAuthorship W4313482711A5057837485 @default.
• W4313482711 hasAuthorship W4313482711A5065061505 @default.
• W4313482711 hasAuthorship W4313482711A5065328976 @default.
• W4313482711 hasConcept C108583219 @default.
• W4313482711 hasConcept C118487528 @default.
• W4313482711 hasConcept C124504099 @default.
• W4313482711 hasConcept C134306372 @default.
• W4313482711 hasConcept C138885662 @default.
• W4313482711 hasConcept C153180895 @default.
• W4313482711 hasConcept C154945302 @default.
• W4313482711 hasConcept C2776401178 @default.
• W4313482711 hasConcept C2778818243 @default.
• W4313482711 hasConcept C31972630 @default.
• W4313482711 hasConcept C33923547 @default.
• W4313482711 hasConcept C36503486 @default.
• W4313482711 hasConcept C41008148 @default.
• W4313482711 hasConcept C41895202 @default.
• W4313482711 hasConcept C71924100 @default.
• W4313482711 hasConcept C89600930 @default.
• W4313482711 hasConceptScore W4313482711C108583219 @default.
• W4313482711 hasConceptScore W4313482711C118487528 @default.
• W4313482711 hasConceptScore W4313482711C124504099 @default.
• W4313482711 hasConceptScore W4313482711C134306372 @default.
• W4313482711 hasConceptScore W4313482711C138885662 @default.
• W4313482711 hasConceptScore W4313482711C153180895 @default.
• W4313482711 hasConceptScore W4313482711C154945302 @default.
• W4313482711 hasConceptScore W4313482711C2776401178 @default.
• W4313482711 hasConceptScore W4313482711C2778818243 @default.
• W4313482711 hasConceptScore W4313482711C31972630 @default.
• W4313482711 hasConceptScore W4313482711C33923547 @default.
• W4313482711 hasConceptScore W4313482711C36503486 @default.
• W4313482711 hasConceptScore W4313482711C41008148 @default.
• W4313482711 hasConceptScore W4313482711C41895202 @default.
• W4313482711 hasConceptScore W4313482711C71924100 @default.
• W4313482711 hasConceptScore W4313482711C89600930 @default.
• W4313482711 hasFunder F4320321001 @default.
• W4313482711 hasFunder F4320330206 @default.
• W4313482711 hasLocation W43134827111 @default.

• next