簡易檢索 / 詳目顯示

研究生: 蔡奕甫
Yi-Fu Tsai
論文名稱: 自由呼吸之心肌短軸T1影像:全自動化雲端影像重建
Free-breathing short-axis MOLLI imaging for myocardial T1 mapping : a fully automatic cloud service for image reconstruction
指導教授: 黃騰毅
Teng-Yi Huang
口試委員: 莊子肇
none
林益如
none
蔡尚岳
none
學位類別: 碩士
Master
系所名稱: 電資學院 - 電機工程系
Department of Electrical Engineering
論文出版年: 2016
畢業學年度: 104
語文別: 中文
論文頁數: 37
中文關鍵詞: 影像對位機器學習MOLLI
外文關鍵詞: Image registration, Machine learning, MOLLI
相關次數: 點閱:277下載:2
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

磁共振影像(magnetic resonance imaging, MRI)具有無輻射線與非侵入性等優勢。近年來磁共振造影的快速發展,modified look-locker inversion recovery (MOLLI)目前被公認為最可靠且重現性極佳的T1定量影像技術。但MOLLI技術要求患者在掃描期間必須全程閉氣,對許多患有疾病或是肺容量限制的患者來說是極為困難的,因此先前研究提出了自由呼吸下的MOLLI,但自由呼吸衍生了像是心臟移動等問題,造成T1量測結果的誤差。本研究藉由自動化圈選切割影像、機器學習、合成影像、影像對位、雲端計算等方法改善自由呼吸下MOLLI的T1量測結果,利用美國心臟協會的心肌標準化分區做分析,並和先前的研究比較T1量測的精確度有顯著的提升。最後將全自動化的處理流程透過雲端計算服務平台簡化臨床T1圖譜的處理流程,使改善後的自由呼吸 MOLLI成為臨床上量測T1圖譜的一個可靠工具。


Amount the myocardial T1 mapping techniques, the modified look-locker inversion recovery (MOLLI) sequence is accurate and reproducible. The free-breathing MOLLI (FB-MOLLI) presented in our previous study allowed T1 mapping in vivo without breath-hold. In this study, we attempted to implement unsupervised reconstruction for FB-MOLLI data sets and used a deformable method for image registration to improve the reliability of free-breathing T1 mapping. The results supported that the method improved the image alignments of the FB-MOLLI data sets and thus increased the quality of the T1 map. The variations of the repeated T1 measurements were significantly reduced in the anterolateral of the LV walls. In summary, this study presents a functional and robust cloud computing service for application of automatic image processing for FB-MOLLI data sets.

中文摘要 1 Abstract 2 目錄 3 第一章 簡介 4 第二章 分法與材料 7 2.1 影像資料取得 7 2.2 自動化影像切割 9 2.3 支持向量機 13 2.4 曲線擬合 19 2.5 影像對位 21 2.6 雲端計算 23 第三章 實驗結果 25 3.1 運用機器學習改善影像切割 25 3.2 對位改善 27 3.3 運算雲端化 31 第四章 討論與結論 33 參考文獻 36

[1] L. Iles, H. Pfluger, et al. "Evaluation of diffuse myocardial fibrosis in heart failure with cardiac magnetic resonance contrast-enhanced T1 mapping," J Am Coll Cardiol. 52(19):1574-1580, Nov 2008
[2] E. Dall'Armellina, S. K. Piechnik, et al. "Cardiovascular magnetic resonance by non contrast T1-mapping allows assessment of severity of injury in acute myocardial infarction," J Cardiovasc Magn Reson, 14(1): 15, Feb 201
[3] C. S. Broberg, S. S. Chugh, C. Conklin, D. J. Sahn, and M. Jerosch-Herold, "Quantification of diffuse myocardial fibrosis and its association with myocardial dysfunction in congenital heart disease," Circ Cardiovasc Imaging, vol. 3, pp. 727-34, Nov 2010.
[4] D. R. Messroghli, A. Radjenovic, S. Kozerke, D. M. Higgins, M. U. Sivananthan, and J. P. Ridgway, "Modified Look-Locker inversion recovery (MOLLI) for high-resolution T1 mapping of the heart," Magn Reson Med, vol. 52, pp. 141-6, Jul 2004.
[5] V. Vassiliou, E. L. Heng, P. Sharma, et al. "Reproducibility of T1 mapping 11-heart beat MOLLI Sequence," J Cardiovasc Magn Reson., 17(Suppl 1): W26, Feb 2015
[6] K. Chow, J. A. Flewitt, J. D. Green, et al. "Saturation Recovery Single-Shot Acquisition (SASHA) for Myocardial T1 Mapping" Magnetic Resonance in Medicine, 71:2082–2095, 2014
[7] J. L. Fernandes, R. Strecker, A. Greiser, et al. "Myocardial T1-Mapping: Techniques and Clinical Applications" Clinical Cardiovascular Imaging, Jan 2012
[8] A. Pednekar, U. Kurkure, R. Muthupillai, et al. "Automated left ventricular segmentation in cardiac MRI. " IEEE Trans Biomed Eng, 53(7):1425-8, June 2006
[9] G. C. Kagadis, C. Kloukinas, K. Moore, et al. "Cloud computing in medical imaging" Med. Phys. 40, 070901, 2013
[10] J. M. Tsai, T. Y. Huang, et al. "Free-breathing MOLLI: application to myocardial T1 mapping," Med Phys, 39(12):7291-302, Dec 2012
[11] T. Song, J. A. Stainsby, V. B. Ho, et al. "Flexible cardiac T1 mapping using a modified Look-Locker acquisition with saturation recovery. " Magn Reson Med., 67(3):622-7, Jan 2012

QR CODE