影像處理技術於血管定量之判斷

Quantitative Analysis of Vascular Structures Using Image Processing

林怡君(Lin,Yichun)

指導教授 ： 江佩如

國立中正大學/工學院/機械工程學系/碩士(2012年)

摘要

血管新生常常會引起許多疾病，例如:在視網膜和脈絡膜的血管新生，會造成早產兒視網膜病變、老年性黃斑部病變、糖尿病視網膜病變，甚至癌症的發展也與血管新生有關。要定義血管新生的程度，因此血管定量是很重要的。目前血管定量，經常是用人工來量測，然而用人工的方式來量測往往是費時且主觀的。因此，本文利用影像處理的技術來定量血管新生的程度，不僅可以避免人為的定量誤差，並且同時縮短量測的所需的時間。為了定量血管，我們會提供九種定量參數的自動定量。此外把自動定量的迴路數、管長及分支點與人工定量結果與商業軟體分析結果做比較，根據比較結果，證明本文提出的方法能夠提供一個方便且準確的血管定量工具供使用者使用。

關鍵字

模糊類神經網路 ； 熵 ； 成管測定法 ； 影像處理 ； 血管定量

並列摘要

Vascularization, the growth of new blood vessels from the existing vessels, implies many pathological processes and needs to be reasonably quantified. However, most vascular analysis is done manually. This is a tedious and laborious work without consistence. In this paper, we will demonstrate the feasibility of automatic quantification of vascular structures by image processing. The formation of blood vessels are quantified by 9 parameters from the processed images. In addition, the obtained number of loops, tube length and branching points are compared with the values measured manually and compared with the commercial software. According to the result, the proposed method can provide a convenient and accurate vascular quantitative tool for users.

並列關鍵字

image processing ； fuzzy-neural network ； entropy ； tube formation assay ； quantification of vascular structures

參考文獻

[1] Y. Chen, X.X. Li, N.Z. Xing, X.G. Cao, “Quercetin inhibits choroidal and retinal angiogenesis in vitro”, Graefes Arch. Clin. Exp. Ophthalmol, v 246, pp 373–378 ,2008.

[7] R. Auerbach, R. Lewis, B. Shinners, L. Kubai, N. Akhtar, “Angiogenesis assays: a critical overview”, Clinical Chemistry, v 49, pp 32–40, 2003.

[8] D. Guidolin, A. Vacca, G.G. Nussdorfer, D. Ribatti, “ A new image analysis method based on topological and fractal parameters to evaluate the angiostatic activity of docetaxel by using the Matrigel assay in vitro”, Microvascular Research, v 67, pp 117–124, 2004.

[9] F. Lamberti, B. Montrucchio, “Segmentation of in-vitro endothelial cell networks”, Biomedical Imaging: Nano to Macro, v 1, pp129 – 132 ,2004.

[10] F. Lamberti, B. Montrucchio, A. Gamba, “Quantitative analysis of vascular structures geometry using neural networks”, Signal Processing Systems Design and Implementation, pp 378 – 383 ,2005.