臺灣博碩士論文加值系統

失智症盛行率逐年上升，預估2031年到2041年失智人口比例將有2%升到3%。阿茲海默症現行藥物治療主要在於保留或改善認知功能以延遲疾病惡化。相較於目前在臨床上之失智評估量表評估，利用MRI與CT影像來檢視腦部是否有萎縮的現象可及早發現及治療。目前醫師以手動的方式評估影像中的萎縮程度較不客觀且費時，故本研究將電腦輔助偵測系統，以快速有效提供資訊供醫師做為診斷依據。
本論文主要運用影像處理之方法來計算萎縮量，並分析失智評估量表(CDR)與腦容量萎縮程度之間的相關性開發。分別以MRI影像計算腦部白質與灰質容量以及腦比例及以CT影像計算腦組織容量與比例，幫助醫師快速分析阿茲海默症患者的嚴重程度。研究步驟包含:(1)透過區域成長之影像前處理，去除雜訊並分割出完整的腦組織；(2) 藉由影像加強技術進行影像邊緣強化，將白質灰質以及腦脊髓液區分；(3) 藉由特徵之設定選取適當影像參數分析，將白質灰質及腦脊髓液體積計算；(4)將灰質白質及腦脊髓液的體積、腦比例及萎縮程度等參數結果呈現;(5)最後先以假體影像確認系統之功能後，再使用每組三張影像之50組CT影像，其中20組影像作為訓練組，30組影像為測試組，及30組MRI影像進行分析，並結合失智評估量表進行系統效能評估。
初步結果顯示: CT與MRI影像中經由統計分析結果可以得到萎縮比例與CDR分數均為正比關係。在阿茲海默症等級之判讀上，CT影像的系統判斷能力，準確率87.5%、靈敏度90%、專一性83.3%、 KAPPA 0.53，MRI影像的系統判斷能力，準確率80%、靈敏度 80%、專一性80%、KAPPA 0.50，表示系統對於阿茲海默症輔助診斷有一定的效能。此外，腦部影像手動分割及系統分割分別平均花費時間為297.2秒與7.6秒，系統亦提供醫師方便使用及加快診斷速度之介面。
初步結果顯示，本系統藉由影像處理所提供之腦部萎縮比例與CDR分數有正比之關係。在未來數據量足夠的情況下，除了提供MRI影像與CT影像評估與CDR之間的關聯性，並探討以使用CT影像取代MRI影像作為主要診斷影像，減少病患所要做的診斷步驟，並降低醫療的浪費。

It has been predicted by the Taiwan Alzheimer Disease Association that the amount of people suffering from Alzheimer’s will increase from 2%, in 2031, to 3%, in 2041. Current drug treatments for Alzheimer’s disease (AD) aim to retain cognitive function as well as delay disease progression, and the sooner the treatment is started the greater the effectiveness. We can assess the level of AD by Clinical Dementia Rating (CDR) and obtain the brain atrophy ratio via MRI and CT imaging. However, the manual assessment of the brain atrophy ratio is not objective and time-consuming. In this thesis, a computer-aided detection (CAD) system was presented based on the correlation between CDR and the brain atrophy ratio to provide relevant data for physicians.
This CAD system was developed by calculating the ratio of white matter (WM), gray matter (GM) and brain ratio. The steps of this study include: (1) removing noise and separate the full area of brain through image pre-processing; (2) detecting white matter, gray matter and cerebrospinal fluid (CSF) by edge detection; (3) calculating the volume of WM, GM and CSF; (4) determining the volume, feature, brain ratio and atrophy level on the CAD system.; and finally, (5) using phantom image to vilify developed algorithm and 50 set CT images (3 images /set), where 20 are used as the training group and 30 as the test group, and 30 MRI images to evaluate the effectiveness of the system.
Preliminary results and statistical analysis showed that the atrophy ratio and CDR scores are proportional directly. The CT image diagnostic system demonstrates an accuracy of 87.5%, sensitivity of 90%, specificity of 83.3%, and kappa of 0.53. The MRI image diagnostic system demonstrates an accuracy of 80%, sensitivity of 80%, specificity of 80%, and kappa of 0.50. These indicate that the system for the diagnosis of Alzheimer''s disease is effective and accurate. In addition, the average segmentation time for brain images in manual and developed system method are 297.2 and 7.6 seconds, respectively. The system also provides ease of use interface for physician faster diagnosis.
The results showed that the atrophy ratio of CT and MRI images and CDR scores are highly relatively. In the future, we can make use of CT imaging and MRI imaging as a primary diagnostic tool for early detection and reduce the patients’ need for other diagnostic procedures, thereby reducing medical waste.

摘　要 I
ABSTRACT III
謝誌 V
目錄 VI
圖索引 IX
表索引 XIII
第一章、 緒論 1
1-1研究背景 1
1-2 、國內外文獻回顧 4
1-3、研究目的 8
1-4論文架構 10
第二章、理論基礎 11
2-1 阿茲海默症(Alzheimer''s Disease)之介紹及其診斷 11
2-2電腦斷層(Computed Tomography CT) 16
2-3磁振造影(Magnetic Resonance Imaging MRI) 18
2.3.1、核磁共振之原理 19
2.3.2 磁振造影之成像方式 20
2.3.3 磁振造影之成像應用 21
2-4影像處理 22
2-5錐台體積計算 24
2-6系統評估方式及主要參數之定義 25
第三章、研究架構與方法 28
3-1 材料與設備 28
3.1.1 研究材料 28
3-2研究流程 30
3-3研究方法 31
3.3.2 腦脊髓液分離 33
3.3.3 計算各組織體積與比例 34
3.3.4 MRI影像處理方式 34
3.3.5 灰質、白質腦與腦脊髓液分割 36
3.3.6 各組織體積與比例 37
3-4實驗設計 38
第四章、結果與討論 40
4-1 系統驗證結果 40
4-2手動分割與系統分割時間與重疊率 42
4-3 參數、體積與比例 44
4-4 參數分析結果 46
4-5 臨界值之決定 51
4-6 測試組之系統效能驗證 52
4-7 誤判影像之討論 53
4-8 系統限制 54
4-9系統之程式介面及操作流程 55
4-9-1 CT系統程式介面 55
4-9-2 CT系統操作流程 57
4-9-3 MRI系統程式介面 59
4-9-2 MRI系統操作流程 61
第五章、結論與未來展望 65
5-1結論 65
5-2 未來展望 66
參考文獻 68
附錄A.不同CDR之各組影像面積與體積 72

圖索引
圖1-1、正常與阿茲海默症患者腦部影像差異 3
圖1-2、利用支持向量機(SVM)所訓練與測詴之結果 6
圖1-3、手動圈選計算面積 -7
圖2-1、神經纖維糾結的神經細胞示意圖 13
圖2-2、電腦斷層結構圖 17
圖2-3、不同切面之電腦斷層影像 18
圖2-4、磁振造影之示意圖 19
圖2-5、氫原子自旋變化示意圖 20
圖2-6、磁振造影不同角度的成像 21
圖2-7、區域成長法示意圖 23
圖2-8、臨界值法直方圖示意圖 23
圖2-9、錐台與錐體各長度之示意圖 24
圖2-10、錐體與錐台結合之示意圖 25
圖3-1、本研究使用經確診阿茲海默症患者之CT 影像 29
圖3-2、本研究使用經確診阿茲海默症患者之MRI 影像 29
圖3-3、系統流程圖 30
圖3-4、頭顱骨與腦組織分割 32
圖3-5、經臨界值法後之影像 33
圖3-6、選取腦脊隨液之影像 33
圖3-7、計算腦脊髓液及腦組織體積與比例 34
圖3-8、臨界值法後腦部之影像 35
圖3-10、分割白質之影像白質 36
圖3-11、分割灰質之影像 37
圖3-12、計算腦組織與比例 38
圖3-13、已知面積的腦部影像假體 39
圖4-1、去除頭顱骨之假體影像 41
圖4-2、還原腦主組織之假體影像 41
圖4-3、分割灰質與白質之假體影像 41
圖4-4、醫師手動分割結果 43
圖4-5、不同切面之MRI 影像分割灰質與白質的結果 45
圖4-6、不同切面之CT 影像之腦脊髓液分割 45
圖4-7、MRI 影像經分割後之體積與比例計算 46
圖4-8、CT 影像經閾值法後體積與比例計算 46
圖4-9、CT 影像萎縮比例與CDR 分數統計圖 47
圖4-10、萎縮比例與CDR 之統計分析圖 48
圖4-11、MRI 腦部影像萎縮比例與CDR 分數統計分析圖 49
圖4-12、MRI 腦部影像萎縮比例與CDR 分數統計分析圖 49
圖4-13、MRI 影像灰質比例與CDR 分數統計圖 50
圖4-14、MRI 影像灰質比例與CDR 分數之統計分析圖 50
圖4-15、MRI 影像白質比例與CDR 分數統計圖 51
圖4-16、MRI 影像白質比例與CDR 分數之統計分析圖 51
圖4-17、灰質分割容易誤判的地方 54
圖4-18、CT 影像與MRI 影像解析度之差異 54
圖4-19、MRI 腦部影像中容易誤判之部位 55
圖4-20、原始圖介面 56
圖4-21、頭顱骨之分割介面 56
圖4-22、腦脊髓液分割及結果輸出 57
圖4-23、程式原始介面 57
圖4-24、區域成長法之處理 58
圖4-25、分割與結果參數 59
圖4-26、頭顱骨分割之介面 59
圖4-27、白質分割之介面 60
圖4-28、白質分割之介面 60
圖4-29、結果數據分析 61
圖4-30、取出頭顱骨之影像 62
圖4-31、計算該切面支全腦面積 62
圖4-32、白質分割與計算體積 63
圖4-33、灰質分割與體積計算 64
圖4-34、數據分析結果 64

表索引
表1-1、台灣失智人口推估 2
表1-2、5 歲分年齡失智症盛行率 2
表2-1、臨床失智評估量表（CDR）之分期 16
表2-1、顱內組織構造及病變之MRI 訊號強度 21
表2-2、決策矩陣於病理檢查上的應用方式 26
表4-1、系統驗證假體面積 41
表4-3、手動分割與系統分割花費時間 43
表4-4、白質分割重疊率 43
表4-5、經訓練後萎縮比例與灰質比例臨界值與CDR 對照表 52
表4-6、測詴組與CDR 總表 52
表4-7、測詴組系統診斷能力之決策矩陣表 53

[1]J. Hardy, and D. J. Selkoe, “The amyloid hypothesis of Alzheimer''s disease: progress and problems on the road to therapeutics,” Science, vol. 297, no. 5580, pp. 353-356, 2002-07-19 00:00:00, 2002.
[2]徐榮隆, 陳威宏, 邱浩彰, and 沈幸梅, “不同時期失智症之認知功能,” 臺灣醫學, vol. 4, no. 4, pp. 371-378, 2000.
[3]G. Rabinovici, W. Seeley, E. Kim, M. Gorno-Tempini, K. Rascovsky, T. Pagliaro, S. Allison, C. Halabi, J. Kramer, and J. Johnson, “Distinct MRI atrophy patterns in autopsy-proven Alzheimer''s disease and frontotemporal lobar degeneration,” American journal of Alzheimer''s disease and other dementias, vol. 22, no. 6, pp. 474-488, 2008.
[4]C. Jack, M. Shiung, J. Gunter, P. O’brien, S. Weigand, D. S. Knopman, B. F. Boeve, R. J. Ivnik, G. E. Smith, and R. Cha, “Comparison of different MRI brain atrophy rate measures with clinical disease progression in AD,” Neurology, vol. 62, no. 4, pp. 591-600, 2004.
[5]S. Kim, Y. C. Youn, G.-Y. R. Hsiung, S.-Y. Ha, K.-Y. Park, H.-W. Shin, D.-K. Kim, S.-S. Kim, and B. S. Kee, “Voxel-based morphometric study of brain volume changes in patients with Alzheimer’s disease assessed according to the Clinical Dementia Rating score,” Journal of Clinical Neuroscience, vol. 18, no. 7, pp. 916-921, 2011.
[6]台灣失智症協會. "認識失智症," http://www.tada2002.org.tw/tada_know_02.html.
[7]吳柏勳, “利用簡易智能評估量表研究退化型與血管型失智症之差異性,” 臺北醫學大學醫學資訊研究所學位論文, pp. 1-65, 2010.
[8]C. R. Jack, V. J. Lowe, S. D. Weigand, H. J. Wiste, M. L. Senjem, D. S. Knopman, M. M. Shiung, J. L. Gunter, B. F. Boeve, and B. J. Kemp, “Serial PIB and MRI in normal, mild cognitive impairment and Alzheimer''s disease: implications for sequence of pathological events in Alzheimer''s disease,” Brain, pp. awp062, 2009.
[9]G. A. Chase, and M. Folstein, “Psychiatric symptoms and nursing home placement of patients with Alzheimer’s disease,” Am J Psychiatry, vol. 147, no. 8, pp. 1049-105, 1990.
[10]J. A. Luchsinger, M.-X. Tang, Y. Stern, S. Shea, and R. Mayeux, “Diabetes mellitus and risk of Alzheimer''s disease and dementia with stroke in a multiethnic cohort,” American journal of epidemiology, vol. 154, no. 7, pp. 635-641, 2001.
[11]陳靖中, 連恒裕, 洪維憲, 黃錦章, 徐文俊, and 黃美涓, “比較輕微阿茲海默症及血管性失智症老年患者同時之動作表現,” 台灣復健醫學雜誌, vol. 36, no. 3, pp. 159-168, 2008.
[12]E. D. Bigler, and D. F. Tate, “Brain volume, intracranial volume, and dementia,” Investigative radiology, vol. 36, no. 9, pp. 539-546, 2001.
[13]C. Möller, H. Vrenken, L. Jiskoot, A. Versteeg, F. Barkhof, P. Scheltens, and W. M. van der Flier, “Different patterns of gray matter atrophy in early-and late-onset Alzheimer’s disease,” Neurobiology of aging, vol. 34, no. 8, pp. 2014-2022, 2013.
[14]N. Zhu, D. R. Jacobs, P. J. Schreiner, L. J. Launer, R. A. Whitmer, S. Sidney, E. Demerath, W. Thomas, C. Bouchard, and K. He, “Cardiorespiratory fitness and brain volume and white matter integrity The CARDIA Study,” Neurology, vol. 84, no. 23, pp. 2347-2353, 2015.
[15]K. M. Pohl, S. Bouix, M. Nakamura, T. Rohlfing, R. W. McCarley, R. Kikinis, W. E. L. Grimson, M. E. Shenton, and W. M. Wells, “A hierarchical algorithm for MR brain image parcellation,” IEEE transactions on medical imaging, vol. 26, no. 9, pp. 1201, 2007.
[16]S. R. Barnes, E. M. Haacke, M. Ayaz, A. S. Boikov, W. Kirsch, and D. Kido, “Semiautomated detection of cerebral microbleeds in magnetic resonance images,” Magnetic resonance imaging, vol. 29, no. 6, pp. 844-852, 2011.
[17]R. Nordenskjöld, F. Malmberg, E.-M. Larsson, A. Simmons, S. J. Brooks, L. Lind, H. Ahlström, L. Johansson, and J. Kullberg, “Intracranial volume estimated with commonly used methods could introduce bias in studies including brain volume measurements,” Neuroimage, vol. 83, pp. 355-360, 2013.
[18]D. García-Lorenzo, S. Francis, S. Narayanan, D. L. Arnold, and D. L. Collins, “Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging,” Medical image analysis, vol. 17, no. 1, pp. 1-18, 2013.
[19]M. S. Devine, M. C. Kiernan, S. Heggie, P. A. McCombe, and R. D. Henderson, “Study of motor asymmetry in ALS indicates an effect of limb dominance on onset and spread of weakness, and an important role for upper motor neurons,” Amyotrophic Lateral Sclerosis and Frontotemporal Degeneration, vol. 15, no. 7-8, pp. 481-487, 2014.
[20]K. Shimoda, M. Kimura, M. Yokota, and Y. Okubo, “Comparison of regional gray matter volume abnormalities in Alzheimer׳ s disease and late life depression with hippocampal atrophy using VSRAD analysis: A voxel-based morphometry study,” Psychiatry Research: Neuroimaging, vol. 232, no. 1, pp. 71-75, 2015.
[21]邱逸榛, 何玉婷, 陳婉庭, and 徐亞瑛, “簡介阿茲海默氏症與其照護,” 長期照護雜誌, vol. 7, no. 4, pp. 289-304, 2004.
[22]范齡勻, 陳達夫, and 邱銘章, “阿茲海默症藥物治療的現在與未來,” 臺灣醫學, vol. 16, no. 4, pp. 397-403, 2012.
[23]R. Moan, “MRI software accurately IDs preclinical Alzheimer''s disease,” Diagnostic Imaging, 2009.
[24]莊明宗, 李宜堅, and 李明陽, “擴散張量磁振造影於自發性常壓水腦症之研究,” 2011.
[25]林克能, and 劉秀枝, “臨床失智評量表,” Acta Neurologica Taiwanica, vol. 12, no. 3, pp. 154-165, 2003.
[26]王培寧, 林克能, and 劉秀枝, “輕度認知障礙之診斷與治療: 台北榮總經驗,” 應用心理研究, no. 55, pp. 15-35, 2012.
[27]莊克士, 醫學影像物理學, p.^pp. PP.238-241: 合記圖書出版社, 2003.
[28]B. S. BAXTER, and J. A. SORENSON, “Factors affecting the measurement of size and CT number in computed tomography,” Investigative radiology, vol. 16, no. 4, pp. 337-341, 1981.
[29]L. Lindgren, “Medical CAT-scanning: X-ray absorption coefficients, CT-numbers and their relation to wood density,” Wood Science and Technology, vol. 25, no. 5, pp. 341-349, 1991.
[30]沈戊忠, 神經放射診斷學, 台灣: 合記圖書出版社, 2008.
[31]G. Woods, Digital Image Processing, 2008.
[32]賴宣宇, “電腦輔助診斷系統於乳房腫瘤 X 光與超音波影像之整合應用,” 中原大學醫學工程研究所學位論文, pp. 1-70, 2005.
[33]曾林維, “利用紋理分析於電腦斷層影像偵測急性缺血性中大腦動脈中風,” 中原大學醫學工程研究所學位論文, pp. 1-112, 2006.