Please use this identifier to cite or link to this item: https://ah.lib.nccu.edu.tw/handle/140.119/135984
DC FieldValueLanguage
dc.contributor.advisor蔡尚岳zh_TW
dc.contributor.advisorTsai, Shang-Yuehen_US
dc.contributor.author吳柏賢zh_TW
dc.contributor.authorWu, Po-Shienen_US
dc.creator吳柏賢zh_TW
dc.creatorWu, Po-Shienen_US
dc.date2021en_US
dc.date.accessioned2021-07-01T12:01:42Z-
dc.date.available2021-07-01T12:01:42Z-
dc.date.issued2021-07-01T12:01:42Z-
dc.identifierG0107755003en_US
dc.identifier.urihttp://nccur.lib.nccu.edu.tw/handle/140.119/135984-
dc.description碩士zh_TW
dc.description國立政治大學zh_TW
dc.description應用物理研究所zh_TW
dc.description107755003zh_TW
dc.description.abstract本論文旨在使用二維對位的方法下,以不同頭型切片作為模板,比較二維對位方法與三維對位方法之間的效果差異。再以切片厚度作為控制變因,使用不同厚度的切片進行對位,以判斷切片厚度對於對位的影響。對位完成後,將影像資料元素代入標準化相互資訊的公式,量化兩影像之間相似的程度,其後建立數值矩陣,計算各矩陣內元素的平均與標準差,比較各組數值之間差異,判斷使用二維對位方法時,其效果與三維對位的差距。zh_TW
dc.description.abstractIn this paper, using the two-dimensional registration method to compare the effect differences between the two-dimensional registration method and the three-dimensional registration method via using different head slices.Thesection thicknessis used as the control variable, and different slice thicknessare used for registration to determine the effect of section thickness on registration.After the registrationcompleted, Substitute theelements of image datainto the Normalized mutual information formulato quantify the degree of similarity between the two images.Then establish the numerical matrix, calculating the average and standard deviation of the elements in each matrix, comparing the difference between the values of each group, and judging the difference between using three-dimensional registration methodand two-dimensional registration method.en_US
dc.description.tableofcontents第一章 緒論 1\n1.1 內容大綱 1\n1.2 研究動機 1\n1.3 研究目的 2\n1.4 研究方法 2\n第二章 方法與步驟 3\n2.1 三維全腦對位 3\n2.2 二維對位 14\n2.3 標準化相互資訊 22\n2.4 建立NMI數值矩陣 27\n第三章 數據結果 28\n3.1 取用與計算數值矩陣內元素 28\n3.2 NMI數值矩陣之平均與標準差結果 29\n第四章 結論 34\n參考文獻 36\n附件 37\n附件A -二維對位 37\n附件B -NMI算法一 38\n附件C- NMI算法二 39zh_TW
dc.format.extent2846280 bytes-
dc.format.mimetypeapplication/pdf-
dc.source.urihttp://thesis.lib.nccu.edu.tw/record/#G0107755003en_US
dc.subject二維對位zh_TW
dc.subject三維對位zh_TW
dc.subject對位zh_TW
dc.subject相互資訊zh_TW
dc.subject標準化相互資訊zh_TW
dc.subjectTwo-dimensional registrationen_US
dc.subjectThree-dimensional registrationen_US
dc.subjectRegistrationen_US
dc.subjectMutual informationen_US
dc.subjectNormalized mutual informationen_US
dc.title大腦核磁共振影像之二維對位比較zh_TW
dc.titleTwo-dimensional image registration on MRSI metabolite concentration mapsen_US
dc.typethesisen_US
dc.relation.reference[1]郭盈昇、陳啟仁、王宣惠、關婉君、蔡承坤、邱文達, “磁振造影於中樞神經系統之運用”,科儀新知,Vol.32,No.4,(2016)。\n[2]JohnKurhanewiczDaniel, B.VigneronSarah,and J.Nelsonm, “Three-Dimensional Magnetic Resonance Spectroscopic Imaging of Brain and Prostate Cancer1,” Neoplasia, Vol. 2, Issue1-2, pp.166-189(2000).\n[3]Senthil Periaswamy andHany Farid,“Elastic Registration in the Presence ofIntensity Variations,” IEEE Transactions on Medical Imaging, Vol.22,No.7(2003).\n[4]Senthil Periaswamy and Hany Farid,“Medical Image Registration with Partial Data,”Medical Image Analysis, Vol. 10,Issue 10, pp.452-464(2006).\n[5]Thomas M. Coverand Joy A. Thomas, “Elements of Information Theory,” JOHN WILEY & SONS, New Jersey,2006.\n[6] La The Vinh, Sungyoung Lee, Young-Tack Park, and Brian J. d’Auriol, “A novel feature selection method based on normalized mutual information,” Applied Intelligence, Vol. 37, pp.100-120(2012).zh_TW
dc.identifier.doi10.6814/NCCU202100531en_US
item.fulltextWith Fulltext-
item.grantfulltextopen-
item.openairetypethesis-
item.openairecristypehttp://purl.org/coar/resource_type/c_46ec-
item.cerifentitytypePublications-
Appears in Collections:學位論文
Files in This Item:
File Description SizeFormat
500301.pdf2.78 MBAdobe PDF2View/Open
Show simple item record

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.