Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367043608> ?p ?o ?g. }
- W4367043608 endingPage "102559" @default.
- W4367043608 startingPage "102559" @default.
- W4367043608 abstract "Significant difficulties in medical image segmentation include the high variability of images caused by their origin (multi-center), the acquisition protocols (multi-parametric), the variability of human anatomy, illness severity, the effect of age and gender, and notable other factors. This work addresses problems associated with the automatic semantic segmentation of lumbar spine magnetic resonance images using convolutional neural networks. We aimed to assign a class label to each pixel of an image, with classes defined by radiologists corresponding to structural elements such as vertebrae, intervertebral discs, nerves, blood vessels, and other tissues. The proposed network topologies represent variants of the U-Net architecture, and we used several complementary blocks to define the variants: three types of convolutional blocks, spatial attention models, deep supervision, and multilevel feature extractor. Here, we describe the topologies and analyze the results of the neural network designs that obtained the most accurate segmentation. Several proposed designs outperform the standard U-Net used as a baseline, primarily when used in ensembles, where the outputs of multiple neural networks are combined according to different strategies." @default.
- W4367043608 created "2023-04-27" @default.
- W4367043608 creator A5055090051 @default.
- W4367043608 creator A5071742083 @default.
- W4367043608 creator A5074465861 @default.
- W4367043608 creator A5076987182 @default.
- W4367043608 creator A5085225667 @default.
- W4367043608 date "2023-06-01" @default.
- W4367043608 modified "2023-10-14" @default.
- W4367043608 title "Automatic semantic segmentation of the lumbar spine: Clinical applicability in a multi-parametric and multi-center study on magnetic resonance images" @default.
- W4367043608 cites W1519750838 @default.
- W4367043608 cites W1745334888 @default.
- W4367043608 cites W1903029394 @default.
- W4367043608 cites W1967881219 @default.
- W4367043608 cites W1970557382 @default.
- W4367043608 cites W1980936048 @default.
- W4367043608 cites W2031489346 @default.
- W4367043608 cites W2052644075 @default.
- W4367043608 cites W2063213455 @default.
- W4367043608 cites W2072678773 @default.
- W4367043608 cites W2074206498 @default.
- W4367043608 cites W2095994519 @default.
- W4367043608 cites W2097117768 @default.
- W4367043608 cites W2114751029 @default.
- W4367043608 cites W2127890285 @default.
- W4367043608 cites W2138044008 @default.
- W4367043608 cites W2148726987 @default.
- W4367043608 cites W2395611524 @default.
- W4367043608 cites W2592929672 @default.
- W4367043608 cites W2604790786 @default.
- W4367043608 cites W2607306668 @default.
- W4367043608 cites W2618412219 @default.
- W4367043608 cites W28412257 @default.
- W4367043608 cites W2888358068 @default.
- W4367043608 cites W2894802018 @default.
- W4367043608 cites W2901434856 @default.
- W4367043608 cites W2911964244 @default.
- W4367043608 cites W2912426796 @default.
- W4367043608 cites W2934562040 @default.
- W4367043608 cites W2950565945 @default.
- W4367043608 cites W2963516899 @default.
- W4367043608 cites W2963881378 @default.
- W4367043608 cites W2977883299 @default.
- W4367043608 cites W2980934859 @default.
- W4367043608 cites W2991613957 @default.
- W4367043608 cites W3094071141 @default.
- W4367043608 cites W3135433242 @default.
- W4367043608 cites W3160465045 @default.
- W4367043608 cites W3165072155 @default.
- W4367043608 cites W4233056867 @default.
- W4367043608 cites W4235770099 @default.
- W4367043608 cites W4237029343 @default.
- W4367043608 doi "https://doi.org/10.1016/j.artmed.2023.102559" @default.
- W4367043608 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37210154" @default.
- W4367043608 hasPublicationYear "2023" @default.
- W4367043608 type Work @default.
- W4367043608 citedByCount "1" @default.
- W4367043608 crossrefType "journal-article" @default.
- W4367043608 hasAuthorship W4367043608A5055090051 @default.
- W4367043608 hasAuthorship W4367043608A5071742083 @default.
- W4367043608 hasAuthorship W4367043608A5074465861 @default.
- W4367043608 hasAuthorship W4367043608A5076987182 @default.
- W4367043608 hasAuthorship W4367043608A5085225667 @default.
- W4367043608 hasBestOaLocation W43670436081 @default.
- W4367043608 hasConcept C105795698 @default.
- W4367043608 hasConcept C108583219 @default.
- W4367043608 hasConcept C117251300 @default.
- W4367043608 hasConcept C124504099 @default.
- W4367043608 hasConcept C126838900 @default.
- W4367043608 hasConcept C138885662 @default.
- W4367043608 hasConcept C143409427 @default.
- W4367043608 hasConcept C153180895 @default.
- W4367043608 hasConcept C154945302 @default.
- W4367043608 hasConcept C2524010 @default.
- W4367043608 hasConcept C2776401178 @default.
- W4367043608 hasConcept C2777210771 @default.
- W4367043608 hasConcept C31972630 @default.
- W4367043608 hasConcept C33923547 @default.
- W4367043608 hasConcept C41008148 @default.
- W4367043608 hasConcept C41895202 @default.
- W4367043608 hasConcept C50644808 @default.
- W4367043608 hasConcept C71924100 @default.
- W4367043608 hasConcept C81363708 @default.
- W4367043608 hasConcept C89600930 @default.
- W4367043608 hasConceptScore W4367043608C105795698 @default.
- W4367043608 hasConceptScore W4367043608C108583219 @default.
- W4367043608 hasConceptScore W4367043608C117251300 @default.
- W4367043608 hasConceptScore W4367043608C124504099 @default.
- W4367043608 hasConceptScore W4367043608C126838900 @default.
- W4367043608 hasConceptScore W4367043608C138885662 @default.
- W4367043608 hasConceptScore W4367043608C143409427 @default.
- W4367043608 hasConceptScore W4367043608C153180895 @default.
- W4367043608 hasConceptScore W4367043608C154945302 @default.
- W4367043608 hasConceptScore W4367043608C2524010 @default.
- W4367043608 hasConceptScore W4367043608C2776401178 @default.
- W4367043608 hasConceptScore W4367043608C2777210771 @default.
- W4367043608 hasConceptScore W4367043608C31972630 @default.
- W4367043608 hasConceptScore W4367043608C33923547 @default.