Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367607000> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4367607000 endingPage "109667" @default.
- W4367607000 startingPage "109667" @default.
- W4367607000 abstract "Automatic segmentation of the left ventricle (LV) in four-chamber view images is critical for computer-aided cardiac disease diagnosis. The complex structure of the cardiac image and the encoder-decoder networks may cause coarse segmentation results. High-accuracy LV segmentation is still a challenge with existing automatic LV segmentation methods. In this paper, we propose a slide deep reinforcement learning segmentation network for pixelwise LV segmentation. The main architecture of the slide reinforcement learning networks consists of a slider item combined state, a group of morphology transforming actions and an agent network. The specifically designed reinforcement learning state comprises an image item and a slider item, which contains both original image information and network act information. The reinforcement learning actions proposed in this paper enable accurate and fast formulation of the binary segment result for each frame by controlling the length and location of the slider. Additionally, the confidence branch proposed in our experiment provides a continuous frame series environment, and the identification algorithm avoids losing the segmentation target. The segmentation result reveals that the proposed method outperforms FCN, SegNet, U-Net and TransUnet. The IoU improved by 23.01%, 15.4%, 11.24% and 6.9%. Additionally, we demonstrate how the proposed method can be used as a semisupervised method, which is more convenient for the image annotation process." @default.
- W4367607000 created "2023-05-02" @default.
- W4367607000 creator A5002487268 @default.
- W4367607000 creator A5008579085 @default.
- W4367607000 creator A5041220862 @default.
- W4367607000 creator A5048483626 @default.
- W4367607000 date "2023-09-01" @default.
- W4367607000 modified "2023-09-27" @default.
- W4367607000 title "Slide deep reinforcement learning networks: Application for left ventricle segmentation" @default.
- W4367607000 cites W1901129140 @default.
- W4367607000 cites W1963882359 @default.
- W4367607000 cites W2053934116 @default.
- W4367607000 cites W2113160493 @default.
- W4367607000 cites W2119717200 @default.
- W4367607000 cites W2120763784 @default.
- W4367607000 cites W2124618219 @default.
- W4367607000 cites W2160754664 @default.
- W4367607000 cites W2395611524 @default.
- W4367607000 cites W2572771767 @default.
- W4367607000 cites W2606576226 @default.
- W4367607000 cites W2620296437 @default.
- W4367607000 cites W2769447556 @default.
- W4367607000 cites W2791559429 @default.
- W4367607000 cites W2804860796 @default.
- W4367607000 cites W2889158831 @default.
- W4367607000 cites W2959183777 @default.
- W4367607000 cites W2963536842 @default.
- W4367607000 cites W2963881378 @default.
- W4367607000 cites W2979328813 @default.
- W4367607000 cites W3100789280 @default.
- W4367607000 cites W3105334672 @default.
- W4367607000 cites W3156365630 @default.
- W4367607000 cites W3156973498 @default.
- W4367607000 cites W32403112 @default.
- W4367607000 cites W4220710271 @default.
- W4367607000 doi "https://doi.org/10.1016/j.patcog.2023.109667" @default.
- W4367607000 hasPublicationYear "2023" @default.
- W4367607000 type Work @default.
- W4367607000 citedByCount "0" @default.
- W4367607000 crossrefType "journal-article" @default.
- W4367607000 hasAuthorship W4367607000A5002487268 @default.
- W4367607000 hasAuthorship W4367607000A5008579085 @default.
- W4367607000 hasAuthorship W4367607000A5041220862 @default.
- W4367607000 hasAuthorship W4367607000A5048483626 @default.
- W4367607000 hasConcept C108583219 @default.
- W4367607000 hasConcept C111919701 @default.
- W4367607000 hasConcept C118505674 @default.
- W4367607000 hasConcept C124504099 @default.
- W4367607000 hasConcept C126042441 @default.
- W4367607000 hasConcept C153180895 @default.
- W4367607000 hasConcept C154945302 @default.
- W4367607000 hasConcept C31972630 @default.
- W4367607000 hasConcept C41008148 @default.
- W4367607000 hasConcept C76155785 @default.
- W4367607000 hasConcept C89600930 @default.
- W4367607000 hasConcept C97541855 @default.
- W4367607000 hasConcept C98045186 @default.
- W4367607000 hasConceptScore W4367607000C108583219 @default.
- W4367607000 hasConceptScore W4367607000C111919701 @default.
- W4367607000 hasConceptScore W4367607000C118505674 @default.
- W4367607000 hasConceptScore W4367607000C124504099 @default.
- W4367607000 hasConceptScore W4367607000C126042441 @default.
- W4367607000 hasConceptScore W4367607000C153180895 @default.
- W4367607000 hasConceptScore W4367607000C154945302 @default.
- W4367607000 hasConceptScore W4367607000C31972630 @default.
- W4367607000 hasConceptScore W4367607000C41008148 @default.
- W4367607000 hasConceptScore W4367607000C76155785 @default.
- W4367607000 hasConceptScore W4367607000C89600930 @default.
- W4367607000 hasConceptScore W4367607000C97541855 @default.
- W4367607000 hasConceptScore W4367607000C98045186 @default.
- W4367607000 hasLocation W43676070001 @default.
- W4367607000 hasOpenAccess W4367607000 @default.
- W4367607000 hasPrimaryLocation W43676070001 @default.
- W4367607000 hasRelatedWork W1669643531 @default.
- W4367607000 hasRelatedWork W1982826852 @default.
- W4367607000 hasRelatedWork W2005437358 @default.
- W4367607000 hasRelatedWork W2008656436 @default.
- W4367607000 hasRelatedWork W2023558673 @default.
- W4367607000 hasRelatedWork W2110230079 @default.
- W4367607000 hasRelatedWork W2134924024 @default.
- W4367607000 hasRelatedWork W2517104666 @default.
- W4367607000 hasRelatedWork W2790662084 @default.
- W4367607000 hasRelatedWork W4285827401 @default.
- W4367607000 hasVolume "141" @default.
- W4367607000 isParatext "false" @default.
- W4367607000 isRetracted "false" @default.
- W4367607000 workType "article" @default.