Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281777905> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4281777905 abstract "Vertebral landmark localization is a crucial step in various spine-related clinical applications, which requires detecting the corner points of 17 vertebrae. However, the neighboring landmarks often disturb each other because of the homogeneous appearance of vertebrae, making vertebral landmark localization extremely difficult. In this paper, we propose a multi-stage cascaded convolutional neural network (CNN) to split a single task into two sequential steps: center point localization to roughly locate 17 center points of vertebrae, and corner point localization to determine four corner points for each vertebra without any disturbance. The landmarks in each step were located gradually from a set of initialized points by regressing offsets using cascaded CNNs. To resist the mutual attraction of the vertebrae, principal component analysis (PCA) was employed to preserve the shape constraint in offset regression. We evaluated our method on the AASCE dataset, comprising 609 tight spinal anteroposterior X-ray images, and each image contained 17 vertebrae composed of the thoracic and lumbar spine for spinal shape characterization. The experimental results demonstrated the superior performance of vertebral landmark localization over other state-of-the-art methods, with the relative error decreasing from 3.2e−3 to 7.2e−4." @default.
- W4281777905 created "2022-06-13" @default.
- W4281777905 creator A5022526821 @default.
- W4281777905 creator A5062065250 @default.
- W4281777905 creator A5066617875 @default.
- W4281777905 creator A5067948537 @default.
- W4281777905 creator A5069771802 @default.
- W4281777905 creator A5082599988 @default.
- W4281777905 creator A5088751649 @default.
- W4281777905 creator A5090774662 @default.
- W4281777905 date "2022-11-01" @default.
- W4281777905 modified "2023-10-18" @default.
- W4281777905 title "Accurate scoliosis vertebral landmark localization on X-ray images via shape-constrained multi-stage cascaded CNNs" @default.
- W4281777905 cites W1536680647 @default.
- W4281777905 cites W1976468890 @default.
- W4281777905 cites W2125223451 @default.
- W4281777905 cites W2128728535 @default.
- W4281777905 cites W2295124130 @default.
- W4281777905 cites W2525974879 @default.
- W4281777905 cites W2618019088 @default.
- W4281777905 cites W2751970356 @default.
- W4281777905 cites W3003242569 @default.
- W4281777905 cites W3003824397 @default.
- W4281777905 cites W3004217771 @default.
- W4281777905 cites W3027484126 @default.
- W4281777905 cites W3123208191 @default.
- W4281777905 cites W3169902296 @default.
- W4281777905 cites W3202031520 @default.
- W4281777905 cites W4214508443 @default.
- W4281777905 cites W4313068951 @default.
- W4281777905 doi "https://doi.org/10.1016/j.fmre.2022.10.014" @default.
- W4281777905 hasPublicationYear "2022" @default.
- W4281777905 type Work @default.
- W4281777905 citedByCount "1" @default.
- W4281777905 crossrefType "journal-article" @default.
- W4281777905 hasAuthorship W4281777905A5022526821 @default.
- W4281777905 hasAuthorship W4281777905A5062065250 @default.
- W4281777905 hasAuthorship W4281777905A5066617875 @default.
- W4281777905 hasAuthorship W4281777905A5067948537 @default.
- W4281777905 hasAuthorship W4281777905A5069771802 @default.
- W4281777905 hasAuthorship W4281777905A5082599988 @default.
- W4281777905 hasAuthorship W4281777905A5088751649 @default.
- W4281777905 hasAuthorship W4281777905A5090774662 @default.
- W4281777905 hasBestOaLocation W42817779051 @default.
- W4281777905 hasConcept C105702510 @default.
- W4281777905 hasConcept C129641003 @default.
- W4281777905 hasConcept C153180895 @default.
- W4281777905 hasConcept C154945302 @default.
- W4281777905 hasConcept C175291020 @default.
- W4281777905 hasConcept C199360897 @default.
- W4281777905 hasConcept C27438332 @default.
- W4281777905 hasConcept C2776412215 @default.
- W4281777905 hasConcept C2780297707 @default.
- W4281777905 hasConcept C31972630 @default.
- W4281777905 hasConcept C41008148 @default.
- W4281777905 hasConcept C71924100 @default.
- W4281777905 hasConcept C81363708 @default.
- W4281777905 hasConcept C89600930 @default.
- W4281777905 hasConceptScore W4281777905C105702510 @default.
- W4281777905 hasConceptScore W4281777905C129641003 @default.
- W4281777905 hasConceptScore W4281777905C153180895 @default.
- W4281777905 hasConceptScore W4281777905C154945302 @default.
- W4281777905 hasConceptScore W4281777905C175291020 @default.
- W4281777905 hasConceptScore W4281777905C199360897 @default.
- W4281777905 hasConceptScore W4281777905C27438332 @default.
- W4281777905 hasConceptScore W4281777905C2776412215 @default.
- W4281777905 hasConceptScore W4281777905C2780297707 @default.
- W4281777905 hasConceptScore W4281777905C31972630 @default.
- W4281777905 hasConceptScore W4281777905C41008148 @default.
- W4281777905 hasConceptScore W4281777905C71924100 @default.
- W4281777905 hasConceptScore W4281777905C81363708 @default.
- W4281777905 hasConceptScore W4281777905C89600930 @default.
- W4281777905 hasFunder F4320321001 @default.
- W4281777905 hasFunder F4320325104 @default.
- W4281777905 hasFunder F4320327076 @default.
- W4281777905 hasLocation W42817779051 @default.
- W4281777905 hasLocation W42817779052 @default.
- W4281777905 hasOpenAccess W4281777905 @default.
- W4281777905 hasPrimaryLocation W42817779051 @default.
- W4281777905 hasRelatedWork W166366606 @default.
- W4281777905 hasRelatedWork W2016546218 @default.
- W4281777905 hasRelatedWork W2098911910 @default.
- W4281777905 hasRelatedWork W2148343984 @default.
- W4281777905 hasRelatedWork W2352223314 @default.
- W4281777905 hasRelatedWork W2509104183 @default.
- W4281777905 hasRelatedWork W2509618504 @default.
- W4281777905 hasRelatedWork W586143910 @default.
- W4281777905 hasRelatedWork W99616944 @default.
- W4281777905 hasRelatedWork W2156243485 @default.
- W4281777905 isParatext "false" @default.
- W4281777905 isRetracted "false" @default.
- W4281777905 workType "article" @default.