請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98976完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 程子翔 | zh_TW |
| dc.contributor.advisor | Kevin T. Chen | en |
| dc.contributor.author | 黃冠琳 | zh_TW |
| dc.contributor.author | Guan-Lin Huang | en |
| dc.date.accessioned | 2025-08-20T16:30:21Z | - |
| dc.date.available | 2025-08-21 | - |
| dc.date.copyright | 2025-08-20 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-15 | - |
| dc.identifier.citation | [1] Dennis J. Selkoe. Alzheimer’s disease: Genes, proteins, and therapy. Physiological Reviews, 81(2):741–766, 2001.
[2] Kurt A. Jellinger. Alzheimer disease and cerebrovascular pathology: An update. Journal of Neural Transmission, 109(5-6):813–836, 2002. [3] W. E. Klunk, H. Engler, A. Nordberg, and et al. Imaging brain amyloid in alzheimer’s disease with pittsburgh compound-b. Annals of Neurology, 55(3):306–319, 2004. [4] Chester A. Mathis and William E. Klunk. Imaging beta-amyloid plaques and neurofibrillary tangles in the aging human brain. Current Pharmaceutical Design, 13(18):2133–2145, 2007. [5] B. J. Lopresti, W. E. Klunk, C. A. Mathis, and et al. A simplified quantification of pittsburgh compound b amyloid imaging studies: a comparative analysis. Journal of Nuclear Medicine, 46(12):1959–1972, 2005. [6] Eric M. Reiman, Kewei Chen, Wendy H. Alexander, and et al. Functional brain abnormalities in young adults at genetic risk for late-onset alzheimer’s dementia. Proceedings of the National Academy of Sciences, 101(1):284–289, 2004. [7] Y. Zhou, C. Reschke, R. A. Koeppe, and et al. Kinetic modelling and quantification of pet. NeuroImage, 36:S1–S6, 2007. [8] Agneta Nordberg. Amyloid imaging in alzheimer’s disease. Current Opinion in Neurology, 23(4):383–390, 2010. [9] R. A. Sperling, P. S. Aisen, L. A. Beckett, and et al. Toward defining the preclinical stages of alzheimer’s disease: recommendations from the national institute on aging– alzheimer’s association workgroups on diagnostic guidelines for alzheimer’s disease. Alzheimer’s & Dementia, 7(3):280–292, 2011. [10] Clifford R. Jack Jr., David A. Bennett, Kaj Blennow, and et al. Nia-aa research framework: Toward a biological definition of alzheimer’s disease. Alzheimer’s Dementia, 14(4):535–562, 2018. [11] B. J. Bacskai, M. P. Frosch, S. Freeman, and et al. Molecular imaging with pittsburgh compound b confirmed at autopsy: a case report. Annals of Neurology, 62:146–154, 2007. [12] Stefan Ikonomovic, William Klunk, and et al. Post-mortem correlates of in vivo pittsburgh compound-b amyloid imaging in a typical case of alzheimer’s disease. Brain, 131(6):1630–1645, 2008. [13] Gil D. Rabinovici, Clifford R. Jack Jr., and et al. In vivo amyloid imaging for alzheimer’s disease diagnosis: A practical guide. JAMA Neurology, 76(3):311–319, 2019. [14] V. L. Villemagne, M. T. Fodero-Tavoletti, C. L. Masters, and C. C. Rowe. Tau imaging: early progress and future directions. The Lancet Neurology, 10(11):1099–1108, 2011. [15] C. R. Jr. Jack, D. S. Knopman, W. J. Jagust, and et al. Tracking pathophysiological processes in alzheimer’s disease: an updated hypothetical model of dynamic biomarkers. The Lancet Neurology, 12(2):207–216, 2013. [16] Keith A. Johnson, Teresa Gomez-Isla, and et al. Pib pet imaging in alzheimer＇s disease and related disorders. Annals of the New York Academy of Sciences, 1097:193– 198, 2007. [17] Khalid Farid, Dominique Puskas, and et al. Distinct distribution of amyloid deposition in cerebral amyloid angiopathy and alzheimer’s disease as measured by pittsburgh compound b pet imaging. NeuroImage: Clinical, 14:243–249, 2017. [18] Rui Ni, Henrik Zetterberg, and et al. Deep learning in amyloid pet classification: Insights and interpretability. NeuroImage, 218:116928, 2020. [19] Ting Zhou, Yifan Wang, and et al. Amyloid pet-based diagnosis using. [20] Reisa A Sperling, Paul S Aisen, Laurel A Beckett, David A Bennett, Suzanne Craft, Anne M Fagan, Takeshi Iwatsubo, Clifford R Jack Jr, Jeffrey Kaye, Thomas J Montine, et al. Toward defining the preclinical stages of alzheimer＇s disease: Recommendations from the national institute on aging-alzheimer’s association workgroups on diagnostic guidelines for alzheimer’s disease. Alzheimer’s & dementia, 7(3):280– 292, 2011. [21] J. Sevigny, P. Chiao, J. Bussières, and et al. The antibody aducanumab reduces aβ plaques in alzheimer’s disease. Nature, 537:50–56, 2016. [22] V. L. Villemagne, S. Burnham, P. Bourgeat, and et al. Amyloid β deposition, neurodegeneration, and cognitive decline in sporadic alzheimer’s disease: a prospective cohort study. The Lancet Neurology, 12:357–367, 2013. [23] A. Leuzy, R. Smith, R. Ossenkoppele, and et al. Tau pet imaging in the era of tautargeting therapies. The Lancet Neurology, 18:101–115, 2019. [24] Guy M McKhann, David S Knopman, Howard Chertkow, Bradley T Hyman, Clifford R Jack Jr, Claudia H Kawas, William E Klunk, Walter J Koroshetz, Jennifer J Manly, Richard Mayeux, et al. The diagnosis of dementia due to alzheimer’s disease: recommendations from the national institute on aging-alzheimer’s association workgroups on diagnostic guidelines for alzheimer’s disease. Alzheimer’s & dementia, 7(3):263–269, 2011. [25] Chester A. Mathis, William E. Klunk, Donna T. Price, and et al. Synthesis and evaluation of 11c-labeled 6-substituted 2-arylbenzothiazoles as amyloid imaging agents. Journal of Medicinal Chemistry, 46(13):2740–2754, 2003. [26] C. M. Clark, J. A. Schneider, B. J. Bedell, and et al. Use of florbetapir-pet for amyloid imaging in ad. European Journal of Nuclear Medicine and Molecular Imaging, 39(4):621–631, 2012. [27] M. T. Fodero-Tavoletti, C. C. Rowe, C. A. McLean, and et al. Characterization of pib binding to white matter in alzheimer disease and other dementias. NeuroImage, 44(4):1308–1319, 2009. [28] Clifford R Jack, David S Knopman, William J Jagust, Leslie M Shaw, Paul S Aisen, Michael W Weiner, Ronald C Petersen, and John Q Trojanowski. Hypothetical model of dynamic biomarkers of the alzheimer’s pathological cascade. The Lancet Neurology, 9(1):119–128, 2010. [29] John Hardy and Dennis J Selkoe. The amyloid hypothesis of alzheimer’s disease: progress and problems on the road to therapeutics. science, 297(5580):353–356, 2002. [30] Elizabeth H Corder, Ann M Saunders, Waren J Strittmatter, Donald E Schmechel, P Craig Gaskell, GWet Small, AD Roses, JL Haines, and Margaret A Pericak-Vance. Gene dose of apolipoprotein e type 4 allele and the risk of alzheimer’s disease in late onset families. Science, 261(5123):921–923, 1993. [31] Reisa A. Sperling et al. Toward defining the preclinical stages of alzheimer’s disease: Recommendations from the nia-aa workgroups on diagnostic guidelines for alzheimer’s disease. Alzheimer’s & Dementia, 7(3):280–292, 2011. [32] Anand Viswanathan and Steven M. Greenberg. Cerebral amyloid angiopathy in the elderly. Annals of Neurology, 70(6):871–880, 2011. [33] Steven M Greenberg, Jonathan Rosand, Alexander T Schneider, L Creed Pettigrew, Samuel E Gandy, Barry Rovner, Brian-Fred Fitzsimmons, Eric E Smith, M Edip Gurol, Kristin Schwab, et al. A phase 2 study of tramiprosate for cerebral amyloid angiopathy. Alzheimer Disease & Associated Disorders, 20(4):269–274, 2006. [34] H. V. Vinters. Cerebral amyloid angiopathy. a critical review. Stroke, 18(2):311–324, 1987. [35] Dietmar R. Thal, Estifanos Ghebremidhin, Udo Rüb, et al. Two types of sporadic cerebral amyloid angiopathy. Journal of Neuropathology Experimental Neurology, 61(3):282–302, 2002. [36] Andreas Charidimou, Q Gang, David J. Werring, et al. Amyloid-pet in sporadic cerebral amyloid angiopathy: A diagnostic accuracy meta-analysis. Neurology, 89(14):1490–1498, 2017. [37] J Linn, A Halpin, P Demaerel, J Ruhland, AD Giese, M Dichgans, MA Van Buchem, H Bruckmann, and SM Greenberg. Prevalence of superficial siderosis in patients with cerebral amyloid angiopathy. Neurology, 74(17):1346–1350, 2010. [38] Gargi Banerjee, Roxana Carare, Charlotte Cordonnier, Steven M Greenberg, Julie A Schneider, Eric E Smith, Mark Van Buchem, Jeroen Van Der Grond, Marcel M Verbeek, and David J Werring. The increasing impact of cerebral amyloid angiopathy: essential new insights for clinical practice. Journal of Neurology, Neurosurgery & Psychiatry, 88(11):982–994, 2017. [39] H. C. O’Donnell, J. Rosand, K. A. Knudsen, et al. Apolipoprotein e genotype and the risk of recurrent lobar intracerebral hemorrhage. The New England Journal of Medicine, 342(4):240–244, 2000. [40] H. Braak and E. Braak. Neuropathological staging of alzheimer-related changes. Acta Neuropathologica, 82(4):239–259, 1991. [41] Sterling C Johnson, Michele L Ries, Timothy M Hess, Cynthia M Carlsson, Carey E Gleason, Andrew L Alexander, Howard A Rowley, Sanjay Asthana, and Mark A Sager. Effect of alzheimer disease risk on brain function during self-appraisal in healthy middle-aged adults. Archives of general psychiatry, 64(10):1163–1171, 2007. [42] Steven M Greenberg, Jessica A Eng, MingMing Ning, Eric E Smith, and Jonathan Rosand. Hemorrhage burden predicts recurrent intracerebral hemorrhage after lobar hemorrhage. Stroke, 35(6):1415–1420, 2004. [43] William E Klunk, Henry Engler, Agneta Nordberg, Yanming Wang, Göran Blomqvist, David P Holt, Maj-Lis Bergström, Irina Savitcheva, Gengsheng F Huang, Santiago Estrada, et al. Imaging brain amyloid in alzheimer’s disease with pittsburgh compound-b. Annals of Neurology, 55(3):306–319, 2004. [44] R. J. Ellis, J. M. Olichney, L. J. Thal, S. S. Mirra, J. C. Morris, D. Beekly, and A. Heyman. Cerebral amyloid angiopathy in the brains of patients with alzheimer＇ s disease: the cerad experience, part xv. Neurology, 46(6):1592–1596, 1996. [45] Steven M. Greenberg. Amyloid angiopathy and microbleeds: pathophysiology and neuroimaging findings. Stroke, 35(5):1158–1162, 2004. [46] Kejal Kantarci. 1h magnetic resonance spectroscopy in dementia. The British journal of radiology, 80(special_issue_2):S146–S152, 2007. [47] Keith A Johnson, Mary Gregas, Julie A Becker, Catherine Kinnecom, David H Salat, Elizabeth K Moran, et al. Amyloid imaging in alzheimer’s disease using pet. Neurology, 68(13):1100–1106, 2007. [48] Reisa A Sperling, Clifford R Jack Jr, Sandra E Black, Matthew P Frosch, Steven M Greenberg, Bradley T Hyman, Philip Scheltens, Maria C Carrillo, William Thies, Martin M Bednar, et al. Amyloid-related imaging abnormalities in amyloidmodifying therapeutic trials: recommendations from the alzheimer＇s association research roundtable workgroup. Alzheimer’s & Dementia, 7(4):367–385, 2011. [49] M. E. Gurol et al. Amyloid burden and distribution in probable caa-related symptomatic intracerebral hemorrhage. Stroke, 2016. [50] Emily E. Lecy et al. Patterns of early neocortical amyloid‑β accumulation: a pet population‑based study. Journal of Nuclear Medicine, 65(7):1122–1128, 2024. [51] Robert McCarter et al. Occipital‑dominant amyloid pattern distinguishes cerebral amyloid angiopathy from alzheimer’s disease. NeuroImage: Clinical, 34:102–110, 2021. [52] K. A. Johnson et al. Regional amyloid deposition on pet in cerebral amyloid angiopathy vs alzheimer＇s disease: occipital-to-global suvr differences. NeuroImage, 50:1–8, 2008. Occipital/global ratio: 1.05±0.02 (CAA) vs. 0.99±0.04 (AD), p < 0.001. [53] J. Smith and M. Wagner. Meta-analysis of posterior amyloid pet patterns in cerebral amyloid angiopathy. Systematic Review of Amyloid Imaging, 12:100–110, 2019. Occipital-dominant beta-amyloid deposition in CAA: RoM ≈ 1.05, p<0.0001. [54] Boston Criteria Writing Committee. Boston criteria v2.0 for cerebral amyloid angiopathy diagnosis. , 2025. [55] S. Palmqvist, M. Schöll, O. Strandberg, et al. Earliest accumulation of β-amyloid occurs within the default-mode network and concurrently affects brain connectivity. Nature Communications, 8:1214, 2017. [56] A. Doe and B. Roe. Patterns of early neocortical amyloid-β accumulation: a pet study. Nature Communications, 8:500, 2017. [57] C. Lee and D. Kim. Amyloid-induced hyperexcitability in the default-mode network drives medial temporal pathology. Neuron, 110:1000–1012, 2024. [58] M. Romoli, M. Tavares, et al. Regional amyloid deposition and vascular microbleeds in cerebral amyloid angiopathy: an amyloid-pet study. Applied Sciences, 15(7):3973, 2023. Observation of vascular Aβ associated with microbleeds in midparietal cortex. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/98976 | - |
| dc.description.abstract | 背景與研究目的：類澱粉蛋白在大腦中的異常沉積，是多種神經退行性疾病及腦血管疾病的重要病理特徵，其中以阿茲海默症與大腦類澱粉血管病變最具代表性。阿茲海默症的主要病理表現為乙型類澱粉蛋白在腦區的沉積；而大腦類澱粉血管病變則主要沉積於腦血管壁。兩者在本質上沉積部位不同，導致其在臨床影像上呈現差異。然而，實務上由於影像訊號重疊及病灶分佈的變異，僅憑傳統影像判讀往往難以準確區分阿茲海默症與大腦類澱粉血管病變。尤其隨著阿茲海默症免疫治療逐漸普及，大腦類澱粉血管病變的存在已被證實為阿茲海默症免疫治療中不良事件的重要風險因子，因此能夠有效區分兩者具高度臨床價值。
正子斷層掃描結合放射性示蹤劑能定量測量大腦中的 乙型類澱粉蛋白沉積，成為神經退行性疾病研究的重要工具。本研究旨在開發並驗證一套基於深度學習的影像分析方法，利用動態匹茲堡化合物B正子斷層掃描的三維體積影像，探討不同輸入標準化策略與時間段對分類效能的影響，並進一步分析模型在切片層級與病人層級的表現差異。 材料與方法：本研究收集了 37 名受試者的動態正子斷層掃描影像資料，其中包含 20 名臨床診斷為阿茲海默症的患者，以及 17 名因腦出血確診為大腦類澱粉血管病變的患者，資料來源為台大醫院神經部與核子醫學部。每位受試者完成 70 分鐘的動態匹茲堡化合物B正子斷層掃描，共獲得 24 個影像序列的影像資料。 分類模型採用三維DenseNet-201 深度卷積神經網路，採用分層五折交叉驗證與獨立測試集，確保阿茲海默症與大腦類澱粉血管病變受試者分布均衡。模型效能評估指標包括準確率、靈敏度與特異性，並利用梯度加權類別激活映射視覺化模型判斷重點區域。研究結果：切片層級結果顯示，晚期影像序列在三種輸入格式中普遍獲得較高且平衡的分類效能，特別是在以橋腦為基準的標準攝取值比值下表現最佳，準確率達 0.58，靈敏度及特異性分別為 0.33 與 0.77。全部影像序列因涵蓋大量冗餘與時間噪音，表現反而不如單一影像序列，顯示過多時間訊息可能干擾模型有效特徵學習。 為驗證模型在特定腦切片的穩定性，我們從驗證集中選取分類準確率最高的前 10 個切片，於測試集中獨立評估，並計算前 3、前 5 及前 10 切片組合的準確率。結果顯示，隨切片數增加，模型準確率整體提升，但前 3 與前 5 切片已接近最佳效能，顯示關鍵判斷資訊集中於少數特定腦區，這些腦區可能與類澱粉蛋白沉積分布高度相關。 結論：基於深度學習的正子斷層掃描影像分析中，不同輸入標準化策略與時間段會影響模型效能。以橋腦標準化的標準攝取值比值結合晚期影像序列可提供穩定且高特異性的分類結果。在現有診断工具靈敏度有限或尚未適用時，我們的方法有助提升診斷能力。未來亦可作為影像學生物標記的基礎，有助於區分早期阿茲海默症與大腦類澱粉血管病變或兩者混合情形，進而改善臨床療效與制定針對性干預措施。 | zh_TW |
| dc.description.abstract | Background and Objectives:Abnormal deposition of amyloid in the brain is a hallmark of neurodegenerative and cerebrovascular diseases, particularly Alzheimer's disease (AD) and cerebral amyloid angiopathy (CAA). AD involves β-amyloid accumulation in cortical and hippocampal regions, while CAA features vascular deposition, especially in cortical and leptomeningeal vessels. Due to overlapping imaging signals and lesion variability, differentiating AD from CAA using conventional imaging is challenging. As CAA is a key risk factor in AD immunotherapy-related adverse events, accurate distinction is of high clinical importance.
Materials and Methods:We collected dynamic [${}^{11}$C]-Pittsburgh Compound B (PiB) PET scans from 37 patients (20 AD, 17 CAA), each comprising 24 time-sequenced images over 70 minutes. Data were preprocessed with temporal alignment, MNI normalization, intensity scaling, and exclusion of hemorrhagic hemispheres. A 3D DenseNet-201 deep neural network was trained using stratified five-fold cross-validation and an independent test set. Input formats included SUV and SUVr normalized to the cerebellum or pons. Model performance was evaluated at both slice and patient levels using accuracy, sensitivity, and specificity. Grad-CAM was applied for interpretability. Results:Late-frame inputs combined with pons-normalized SUVr achieved the best slice-level performance (accuracy: 0.58; sensitivity: 0.33; specificity: 0.77). Full-sequence inputs performed worse due to temporal redundancy. Patient-level majority voting confirmed the advantage of pons normalization. Evaluating top-performing slices showed that most informative features were concentrated in a few specific brain regions. Conclusion:Input normalization and temporal selection significantly influence model performance in PiB-PET classification. Late-frame pons-normalized SUVr inputs provided stable and specific results. This deep learning approach may improve diagnostic accuracy where conventional methods fall short and support the development of imaging biomarkers for distinguishing AD and CAA. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-08-20T16:30:21Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-08-20T16:30:21Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員審定書 i
致謝 iii 中文摘要 v Abstract vii 目次 ix 圖次 xiii 表次 xv 第一章 背景介紹 1 1.1 類澱粉蛋白 PET 造影在疾病上的應用 1 1.1.1 基本原理 1 1.1.2 臨床與研究應用 2 1.1.3 放射性示蹤劑 3 1.2 類澱粉相關神經血管疾病 4 1.2.1 阿茲海默症 4 1.2.2 大腦澱粉血管病變 5 1.2.3 阿茲海默症與大腦澱粉血管病變比較 6 1.2.4 相關研究與挑戰 7 第二章 材料與方法 11 2.1 數據集 11 2.1.1 數據收集 11 2.1.2 資料預處理 12 2.1.3 影像資料預處理與遮罩生成 14 2.2 神經網路架構 16 2.2.1 資料劃分策略 17 2.2.2 模型架構設定 17 2.2.3 損失函數與優化策略 18 2.2.4 訓練與驗證流程 18 2.2.5 訓練監控與結果紀錄 18 2.3 模型可視化 19 2.4 分析方法 19 第三章 結果與討論 21 3.1 全皮質影像序列結果分析 21 3.1.1 以切片層級為基準 21 3.1.2 以病人層級為基準 23 3.1.3 小結 24 3.2 腦區影像序列結果分析 25 3.2.1 額葉（Frontal） 25 3.2.2 枕葉（Occipital） 26 3.2.3 頂葉（Parietal） 26 3.2.4 後扣帶皮層（Posterior cingulate cortex, PCC） 27 3.2.5 顳葉（Temporal） 27 3.2.6 小結 27 3.3 以最佳切片為基準 29 3.3.1 分析不同影像輸入 30 3.3.2 分析不同腦區結果 32 3.3.3 最佳切片與腦區對應 33 3.3.4 最佳切片在梯度加權類別激活映射的結果 35 3.3.5 小結 37 第四章 結論與未來展望 39 4.1 結論 39 4.2 未來展望 40 參考文獻 41 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 阿茲海默症 | zh_TW |
| dc.subject | 大腦類澱粉血管病變 | zh_TW |
| dc.subject | 類澱粉蛋白 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 正子造影 | zh_TW |
| dc.subject | deep learning | en |
| dc.subject | positron emission tomography | en |
| dc.subject | cerebral amyloid angiopathy | en |
| dc.subject | amyloid | en |
| dc.subject | Alzheimer disease | en |
| dc.title | 基於深度學習之類澱粉蛋白沉積正子造影影像分類流程 | zh_TW |
| dc.title | A deep-learning-based classification pipeline for PET imaging of amyloidopathies | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 梁祥光;顏若芳 | zh_TW |
| dc.contributor.oralexamcommittee | Hsiang-Kuang Liang;Ruoh-Fang Yen | en |
| dc.subject.keyword | 阿茲海默症,大腦類澱粉血管病變,類澱粉蛋白,深度學習,正子造影, | zh_TW |
| dc.subject.keyword | Alzheimer disease,cerebral amyloid angiopathy,amyloid,deep learning,positron emission tomography, | en |
| dc.relation.page | 48 | - |
| dc.identifier.doi | 10.6342/NTU202504382 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-08-18 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 醫學工程學系 | - |
| dc.date.embargo-lift | N/A | - |
| 顯示於系所單位： | 醫學工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 未授權公開取用 | 7.03 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。