FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W99021019> ?p ?o ?g. }

• W99021019 endingPage "136" @default.
• W99021019 startingPage "111" @default.
• W99021019 abstract "The previous chapter discussed the extraction of fracture points and fracture surfaces in the event of a major fracture where the bone fragments are well separated. In contrast, the focus of this chapter is on the detection of hairline fractures or minor fractures. Mandibular fractures are observed to possess certain distinct patterns in X-ray or CT images. In some cases, the fractures are observed to be hairline or minor in nature. By the terms hairline fracture or minor fracture we refer to those situations where the broken bone fragments are not visibly out of alignment or have incurred very little relative displacement, respectively. The presence of noise makes the detection and subsequent visualization of such types of fractures in X-ray or CT images a very challenging task. In case of a major fracture, i.e., fractures where the broken fragments are clearly displaced relative to each other, surgical intervention is almost mandatory. However, in the case of a hairline fracture or minor fracture, the decision regarding surgical intervention is less clear since the surgeon can rely on natural bone healing for fracture reduction without having to perform reconstructive surgery. In this chapter, we propose a Markov Random Field (MRF)-based hierarchical Bayesian paradigm for detection of hairline or minor fractures and generation of the reconstructed jaw (i.e., target pattern) in such cases. Here, we model the fracture as a local stochastic degradation of a hypothetical intact mandible. In the presence of noise, the detection and subsequent visualization of hairline fractures becomes a clinically challenging task. Furthermore, the decision regarding surgical intervention for this type of fracture is often unclear as a surgeon can choose to rely solely on natural bone healing without any surgical intervention. In addition to aiding in the detection and visualization of the hairline fracture, the generated target pattern depicts how a jaw with a hairline fracture would appear if allowed to heal naturally without explicit surgical intervention. The Bayesian estimation of the mode of the posterior distribution corresponds to the target pattern (i.e., reconstructed jaw), and the differences in intensity between the input data and the MAP estimate at specific pixel locations denote the occurrence and location of a hairline fracture." @default.
• W99021019 created "2016-06-24" @default.
• W99021019 creator A5031703924 @default.
• W99021019 creator A5064001163 @default.
• W99021019 date "2011-01-01" @default.
• W99021019 modified "2023-09-23" @default.
• W99021019 title "Fracture Detection in an MRF-Based Hierarchical Bayesian Framework" @default.
• W99021019 cites W1988520084 @default.
• W99021019 cites W2003282940 @default.
• W99021019 cites W2016258057 @default.
• W99021019 cites W2018456853 @default.
• W99021019 cites W2020999234 @default.
• W99021019 cites W2094655924 @default.
• W99021019 cites W2096651134 @default.
• W99021019 cites W2127857142 @default.
• W99021019 cites W2136639154 @default.
• W99021019 cites W2145517326 @default.
• W99021019 cites W2147868149 @default.
• W99021019 cites W2150139648 @default.
• W99021019 cites W2160748123 @default.
• W99021019 cites W2165411585 @default.
• W99021019 cites W4241812044 @default.
• W99021019 doi "https://doi.org/10.1007/978-0-85729-296-4_7" @default.
• W99021019 hasPublicationYear "2011" @default.
• W99021019 type Work @default.
• W99021019 sameAs 99021019 @default.
• W99021019 citedByCount "0" @default.
• W99021019 crossrefType "book-chapter" @default.
• W99021019 hasAuthorship W99021019A5031703924 @default.
• W99021019 hasAuthorship W99021019A5064001163 @default.
• W99021019 hasConcept C107673813 @default.
• W99021019 hasConcept C127313418 @default.
• W99021019 hasConcept C151730666 @default.
• W99021019 hasConcept C153180895 @default.
• W99021019 hasConcept C154945302 @default.
• W99021019 hasConcept C41008148 @default.
• W99021019 hasConcept C43369102 @default.
• W99021019 hasConceptScore W99021019C107673813 @default.
• W99021019 hasConceptScore W99021019C127313418 @default.
• W99021019 hasConceptScore W99021019C151730666 @default.
• W99021019 hasConceptScore W99021019C153180895 @default.
• W99021019 hasConceptScore W99021019C154945302 @default.
• W99021019 hasConceptScore W99021019C41008148 @default.
• W99021019 hasConceptScore W99021019C43369102 @default.
• W99021019 hasLocation W990210191 @default.
• W99021019 hasOpenAccess W99021019 @default.
• W99021019 hasPrimaryLocation W990210191 @default.
• W99021019 hasRelatedWork W1978450727 @default.
• W99021019 hasRelatedWork W2033914206 @default.
• W99021019 hasRelatedWork W2146076056 @default.
• W99021019 hasRelatedWork W2163831990 @default.
• W99021019 hasRelatedWork W2378160586 @default.
• W99021019 hasRelatedWork W2996038082 @default.
• W99021019 hasRelatedWork W3003836766 @default.
• W99021019 hasRelatedWork W3107474891 @default.
• W99021019 hasRelatedWork W4244943737 @default.
• W99021019 hasRelatedWork W2289108895 @default.
• W99021019 isParatext "false" @default.
• W99021019 isRetracted "false" @default.
• W99021019 magId "99021019" @default.
• W99021019 workType "book-chapter" @default.