File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

postgraduate thesis: The use of neural network analysis of PET-CT brain scan regional ¹⁸F-FDG metabolism in diagnosis and prognosis of dementia subjects

TitleThe use of neural network analysis of PET-CT brain scan regional ¹⁸F-FDG metabolism in diagnosis and prognosis of dementia subjects
Authors
Issue Date2013
PublisherThe University of Hong Kong (Pokfulam, Hong Kong)
Citation
See, S. E. [施兆景]. (2013). The use of neural network analysis of PET-CT brain scan regional ¹⁸F-FDG metabolism in diagnosis and prognosis of dementia subjects. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b5071278
AbstractThe elderly population (those aged 65 years or older) in Hong Kong is expected to increase from approximately 13% in 2009 to 28% by 2039. With this rapid growth of elders, it raises attention to prevent and treat chronic diseases of aging. Dementia is particularly concerned because the short term memory loss and other cognitive malfunctions lead to a loss of independent function that has a extensive impact on individuals, families, health and social welfare systems. Currently over 70,000 people endure dementia in Hong Kong and expect quadruple rises by 2036. In order to cope with these diseases, accurate diagnosis is very useful, particular at early stage when treatment outcomes are most effective. Numerous studies have found that AD and other dementias could alter brain metabolism significantly. AD patients usually present the posterior cingulated and parietotemporal cortices hypometabolism and spread into the frontal lobes in advanced disease. In contrast, FTD patients show manifestly hypometabolism in the frontal and anterior temporal cortices, while DLB patients present hypometabolism in the posterior brain comprising primarily the parietoocipital regions. Theoretically, 18F-FDG PET scan can help in the early diagnosis of AD and other dementias by highlighting these decreased FDG uptake cortex regions before MRI or CT scans can detect any structural damage. This is a retrospective chart review study. Patients who had received FDG brain PET-CT scan previously had their regional brain metabolism quantitated using a software call Cortex-ID and clinical laboratory tests. The study is * To develop a Neural Network (NN) that can diagnose the various types of dementia using Brain PET-CT scan, testing accuracy of NN versus an expert and, * To see if the NN can correlate with the clinical severity of the disease as reflected by MMSE score. Finally, three neural networks have been designed and they all fulfill all the required specifications.
DegreeMaster of Medical Sciences
SubjectDementia - Tomography.
Neural networks (Computer science)
Dept/ProgramDiagnostic Radiology
Persistent Identifierhttp://hdl.handle.net/10722/192785
HKU Library Item IDb5071278

 

DC FieldValueLanguage
dc.contributor.authorSee, Shiu-king, Eric.-
dc.contributor.author施兆景.-
dc.date.accessioned2013-11-24T02:00:23Z-
dc.date.available2013-11-24T02:00:23Z-
dc.date.issued2013-
dc.identifier.citationSee, S. E. [施兆景]. (2013). The use of neural network analysis of PET-CT brain scan regional ¹⁸F-FDG metabolism in diagnosis and prognosis of dementia subjects. (Thesis). University of Hong Kong, Pokfulam, Hong Kong SAR. Retrieved from http://dx.doi.org/10.5353/th_b5071278-
dc.identifier.urihttp://hdl.handle.net/10722/192785-
dc.description.abstractThe elderly population (those aged 65 years or older) in Hong Kong is expected to increase from approximately 13% in 2009 to 28% by 2039. With this rapid growth of elders, it raises attention to prevent and treat chronic diseases of aging. Dementia is particularly concerned because the short term memory loss and other cognitive malfunctions lead to a loss of independent function that has a extensive impact on individuals, families, health and social welfare systems. Currently over 70,000 people endure dementia in Hong Kong and expect quadruple rises by 2036. In order to cope with these diseases, accurate diagnosis is very useful, particular at early stage when treatment outcomes are most effective. Numerous studies have found that AD and other dementias could alter brain metabolism significantly. AD patients usually present the posterior cingulated and parietotemporal cortices hypometabolism and spread into the frontal lobes in advanced disease. In contrast, FTD patients show manifestly hypometabolism in the frontal and anterior temporal cortices, while DLB patients present hypometabolism in the posterior brain comprising primarily the parietoocipital regions. Theoretically, 18F-FDG PET scan can help in the early diagnosis of AD and other dementias by highlighting these decreased FDG uptake cortex regions before MRI or CT scans can detect any structural damage. This is a retrospective chart review study. Patients who had received FDG brain PET-CT scan previously had their regional brain metabolism quantitated using a software call Cortex-ID and clinical laboratory tests. The study is * To develop a Neural Network (NN) that can diagnose the various types of dementia using Brain PET-CT scan, testing accuracy of NN versus an expert and, * To see if the NN can correlate with the clinical severity of the disease as reflected by MMSE score. Finally, three neural networks have been designed and they all fulfill all the required specifications.-
dc.languageeng-
dc.publisherThe University of Hong Kong (Pokfulam, Hong Kong)-
dc.relation.ispartofHKU Theses Online (HKUTO)-
dc.rightsThe author retains all proprietary rights, (such as patent rights) and the right to use in future works.-
dc.rightsCreative Commons: Attribution-NonCommerical 3.0 Hong Kong License-
dc.source.urihttp://hub.hku.hk/bib/B50712780-
dc.subject.lcshDementia - Tomography.-
dc.subject.lcshNeural networks (Computer science)-
dc.titleThe use of neural network analysis of PET-CT brain scan regional ¹⁸F-FDG metabolism in diagnosis and prognosis of dementia subjects-
dc.typePG_Thesis-
dc.identifier.hkulb5071278-
dc.description.thesisnameMaster of Medical Sciences-
dc.description.thesislevelMaster-
dc.description.thesisdisciplineDiagnostic Radiology-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.5353/th_b5071278-
dc.date.hkucongregation2013-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats